
Transform AI conversations and chat transcripts into publishable content including blog posts, documentation, tutorials, and knowledge base entries. Covers extraction, restructuring, and editorial refinement. Triggers on conversation-to-content, transcript processing, or chat-to-doc requests.
Transfer context between AI agent sessions with structured handoff protocols, state serialization, and decision log preservation. Covers multi-agent coordination, context compression, and continuity patterns. Triggers on agent handoff, session transfer, or multi-agent continuity requests.
Dry-run audit + targeted cleanup for shell command history. Currently wraps atuin (stats today, prune, dedup with dated preview artifacts); extensible to zsh/bash/mcfly backends. Always previews before applying — apply commands are echoed for the human to run, never auto-executed. Triggers on "/shell-history-hygiene", "audit atuin", "audit shell history", "clean shell history", "atuin prune", "atuin dedup", "shell history hygiene", "history cleanup". Replaces ad-hoc one-liners (e.g. `... | tee cmd > file.txt` which wrote two files, swallowed dedup output, and left a junk `cmd` file).
Four-phase protocol for clearing accumulated drift between memory claims, CLAUDE.md citations, and on-disk reality. Detects stale citations, missing files, and orphan plans; classifies findings; emits proposed diffs; codifies prevention. Companion to closeout (closeout discovers orphans; this skill polishes them). Discovery ≠ remediation — Phase 3 emits proposed diffs only; constitutional doc edits require explicit conductor authorization.
Self-improvement patterns for AI agents to learn from feedback, errors, and successful patterns across sessions
Automated code style enforcement with linters, formatters, and pre-commit hooks for consistent codebases
Reflective pass over your memory files — merge duplicates, fix stale facts, prune the index.
Promote creative and technical work through strategic content distribution. Covers platform selection, audience building, content repurposing, and engagement strategies without becoming a full-time marketer. Triggers on promotion, audience building, social media strategy, or content marketing requests.
Analyzes freelance contracts and Statements of Work (SOW) to identify potential risks, scope creep, and unfavorable terms, providing plain-language explanations.
Craft compelling fiction and creative nonfiction with attention to structure, voice, prose style, and revision. Supports short stories, novel chapters, essays, and hybrid forms. Triggers on creative writing, fiction writing, story craft, prose style, or literary technique requests.
Comprehensive quality verification system for code changes with build, type, lint, test, and security checks
Four-phase protocol for clearing accumulated drift between memory claims, CLAUDE.md citations, and on-disk reality. Detects stale citations, missing files, and orphan plans; classifies findings; emits proposed diffs; codifies prevention. Companion to closeout (closeout discovers orphans; this skill polishes them). Discovery ≠ remediation — Phase 3 emits proposed diffs only; constitutional doc edits require explicit conductor authorization.
Build inclusive web experiences following WCAG guidelines. Covers semantic HTML, ARIA, keyboard navigation, color contrast, and testing strategies. Triggers on accessibility, a11y, WCAG, screen readers, or inclusive design requests.
Curated bundle for building, testing, and coordinating AI agent systems. Includes multi-agent orchestration, agent testing, cross-agent handoff, MCP server building, and prompt engineering. Use when developing AI agent workflows or multi-agent systems.
Designs multi-agent systems with coordinated agent swarms, task distribution, inter-agent communication, and emergent collective behavior.
Test AI agent systems including tool use, multi-turn conversations, error recovery, and non-deterministic outputs. Covers mock strategies, evaluation metrics, and regression testing for agent workflows. Triggers on AI agent testing, LLM evaluation, or agent quality assurance requests.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Design robust APIs with RESTful patterns, GraphQL schemas, versioning strategies, and error handling conventions. Supports OpenAPI/Swagger documentation and SDK generation patterns. Triggers on API design, schema definition, endpoint architecture, or developer experience requests.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Four-phase protocol for clearing accumulated drift between memory claims, CLAUDE.md citations, and on-disk reality. Detects stale citations, missing files, and orphan plans; classifies findings; emits proposed diffs; codifies prevention. Companion to closeout (closeout discovers orphans; this skill polishes them). Discovery ≠ remediation — Phase 3 emits proposed diffs only; constitutional doc edits require explicit conductor authorization.
Production-ready backend API implementation patterns including REST, GraphQL, authentication, error handling, and data validation
Comprehensive quality verification system for code changes with build, type, lint, test, and security checks
Audio production concepts, DSP fundamentals, mixing/mastering techniques, and DAW workflows. Bridges modular synthesis philosophy with practical audio engineering. Triggers on audio production, mixing, sound design, DSP, or music technology requests.
Design and implement blockchain integrations across chains and frameworks with emphasis on patterns over specific technologies. Use when building Web3 applications, smart contract systems, token mechanics, decentralized identity, or blockchain-verified data. Triggers on blockchain architecture, smart contract design, Web3 integration, token systems, or decentralized application development. Framework-agnostic—applies to Ethereum, Solana, or emerging chains.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Creates annotated bibliography-style manifests for Claude projects, tracking files, conversation threads, and relationships with unique IDs and annotations. Use when documenting project contents, creating file inventories, tracking conversation history, or building navigable knowledge maps.
Session-end ritual that walks back through plans authored and atoms touched in this session, assigning each a closure status (DONE-NNN, IRF-XXX-NNN, or `~/.Codex/plans/abandoned/`). Verifies git state. Produces CLOSEOUT_SUMMARY.md. Triggers on "/closeout", "close out the session", "end of session", "wrap up", "session close", or before any planned `git push`. Addresses the 90.4% plan-orphan rate documented in docs/evaluation/self-review-2026-05-05/stale-plans-and-orphan-commits.md.
Systematic approach to refactoring code for improved maintainability, performance, and clarity while preserving functionality
Resolve and load any agent capability across the whole fleet from one place. Given an intent, finds the matching skill, command, or agent across Claude, Codex, Gemini, .agents, a-i--skills, OpenCode, and OpenClaw — then loads it through a single portal. Use for cross-agent skill discovery, "which agent has a skill for X", capability routing, or "find a skill that does Y" when capabilities are spread across multiple agent ecosystems.
Systematic approach to building consistent, maintainable frontend UI components with design systems and component libraries
Resolve and load any agent capability across the whole fleet from one place. Given an intent, finds the matching skill, command, or agent across Claude, Codex, Gemini, .agents, a-i--skills, OpenCode, and OpenClaw — then loads it through a single portal. Use for cross-agent skill discovery, "which agent has a skill for X", capability routing, or "find a skill that does Y" when capabilities are spread across multiple agent ecosystems.
Optimize resumes and CVs for impact, ATS compatibility, and audience targeting. Supports multiple formats (chronological, functional, hybrid), accomplishment framing (STAR/XYZ), and tailoring for specific roles. Triggers on resume review, CV update, job application prep, or career document requests.
Designs ETL/ELT data pipelines with proper extraction, transformation, and loading patterns, including orchestration, error handling, and data quality validation.
Transforms raw data into compelling visual narratives using Python or R, focusing on clarity, insight, and aesthetic presentation.
Designs DeFi trading systems for perpetual futures, liquidity provision, and automated strategies with risk management and MEV protection.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Deploy applications with confidence using CI/CD pipelines, containerization, and infrastructure as code. Covers GitHub Actions, Docker, Vercel, and cloud deployment patterns. Triggers on deployment, CI/CD, Docker, GitHub Actions, or DevOps requests.
Guides the creation of a "Minimal Root" home directory using the XDG Base Directory specification and a Bare Git Repository. Manages config separation, secrets, and cross-platform syncing.
Design and generate curriculum materials for college composition courses (ENC1101 and similar). Use when creating syllabi, assignment prompts, rubrics, lesson plans, scaffolded writing sequences, peer review guides, or D2L/LMS-formatted content. Triggers on requests for composition pedagogy, writing assignment design, grading criteria, or freshman writing course materials.
Orchestrate a full directory-graph autopsy across an ORGANVM workspace, then emit migration signals that unite repositories under canonical governance. Thin wrapper over organvm ecosystem + organvm irf + promotion-readiness-checklist. Triggers on auto-autopsy, map all directories, governance migration, ecosystem discovery, or "send the signal to unite" requests.
Foundational layer beneath PDE. Governs eight-strata substrate (ontology, lineage, constellation, gap-map, agent-fleet, production-stack, internal-magnet, external-contribution) plus four operators (selfish-altruistic loop, magnetic membrane, portfolio operator, reflexive operator) for any domain a flag pierces — chess, fitness, voodoo, education, design, taxidermy. Pre-instantiates engine reuse via Phase 0 portfolio audit and stretching-rack gap diagnosis.
Multi-perspective collaborative inquiry. Decomposes a topic into six cognitive lenses (Scope, Logic, Mythos, Bridge, Meta, Pattern) that operate as a chorus rather than a single voice, then synthesizes meta-patterns no single lens could find alone. MANDATORY TRIGGERS: 'expansive inquiry', 'multi-perspective inquiry', 'explore this from every angle', 'six-lens analysis', 'run a chorus on this'. STRONG TRIGGERS: 'help me think through X deeply', 'mythopoetic AND logical analysis'. Do NOT trigger on simple Q&A or failure-focused inquiries — use premortem for those.
End-to-end feature development orchestration from planning through deployment with quality gates
Systematic content evaluation framework progressing through Critique → Reinforcement → Risk Analysis → Growth. Use when reviewing writing, arguments, proposals, code documentation, or any content requiring rigorous multi-dimensional assessment. Supports interactive guided mode or autonomous full-report mode, with output as markdown report, structured checklist, or inline revision suggestions. Triggers on requests to evaluate, critique, improve, strengthen, or review content quality.
Optimize Google Cloud Platform resource allocation and manage cloud credits efficiently. Use when planning GCP deployments, analyzing cloud spend, maximizing value from expiring credits, right-sizing instances, or designing cost-effective architectures. Triggers on GCP cost optimization, credit management, resource allocation planning, or cloud budget concerns.
Give effective feedback that promotes learning and growth. Covers written feedback on student work, rubric design, peer review facilitation, and constructive critique techniques. Triggers on grading, feedback, rubrics, peer review, or critique requests.
Manage freelance and client work professionally—proposals, contracts, scope management, invoicing, and client communication. Covers the business side of creative work. Triggers on freelance, client work, proposals, contracts, pricing, or project scope requests.
Designs engaging gameplay loops, economies, and progression systems, balancing challenge and reward for interactive experiences.
Audits web applications and architectures for compliance with GDPR, CCPA, and other privacy regulations, focusing on consent, data minimization, and user rights.
Create algorithmic and generative art using mathematical patterns, noise functions, particle systems, and procedural generation. Covers flow fields, L-systems, fractals, and creative coding foundations. Triggers on generative art, algorithmic art, creative coding, procedural generation, or mathematical visualization requests.
Curated bundle of essential skills for fullstack web development. Installs API design, testing, deployment, backend patterns, frontend architecture, and code quality skills together. Use when starting a new fullstack project or onboarding onto a codebase.
Implement structured logging, error hierarchies, and observability patterns for production systems. Covers structured JSON logging, error classification, correlation IDs, and alerting integration. Triggers on logging architecture, error handling strategy, or observability requests.
Implement reliable data backup and recovery strategies with automated scheduling, encryption, rotation policies, and disaster recovery testing. Covers database backups, file system snapshots, and cloud storage patterns. Triggers on backup strategy, disaster recovery, or data protection requests.
Manage database schema changes safely with migration tools, zero-downtime strategies, and rollback procedures. Covers Alembic, SQL migrations, data migrations, and testing strategies. Triggers on database migration, schema changes, or Alembic configuration requests.
Containerize applications with multi-stage Dockerfiles, Docker Compose orchestration, image optimization, and container security. Covers Python, Node.js, and multi-service architectures. Triggers on Docker, containerization, or container orchestration requests.
Curated bundle for the full essay lifecycle from writing through multi-platform distribution. Includes publishing pipeline, creative writing craft, content distribution strategy, and POSSE architecture. Use when building an end-to-end content publishing workflow.
Audit document collections to extract features, identify patterns, assess quality, and build structured inventories. Covers metadata extraction, content classification, gap analysis, and coverage mapping. Triggers on document audit, content inventory, or document feature extraction requests.
Publish essays and long-form content through a structured pipeline from draft to distribution. Covers markdown-to-HTML conversion, metadata management, cross-posting strategies, and RSS/Atom feed generation. Triggers on essay publishing, content pipeline, or blog deployment requests.
Build data ingestion pipelines for batch and streaming data from multiple sources. Covers extraction strategies, format normalization, deduplication, validation gates, and staging patterns. Triggers on data ingestion, ETL pipeline, or data import architecture requests.
Build production FastAPI applications with dependency injection, middleware, background tasks, and structured project layouts. Covers async patterns, Pydantic models, OpenAPI customization, and testing strategies. Triggers on FastAPI development, Python API, or async web framework requests.
Build community platforms with user profiles, discussion forums, event management, and moderation tools. Covers real-time features, content moderation, and community engagement patterns. Triggers on community platform development, forum design, or social feature requests.
Build browser extensions with Manifest V3 for Chrome, Firefox, and cross-browser compatibility. Covers content scripts, background workers, popup UI, storage APIs, and extension messaging. Triggers on browser extension development, Manifest V3, or Chrome extension requests.
Design command-line interfaces with clear argument parsing, subcommands, help text, output formatting, and exit codes. Covers Click, Typer, argparse, and shell completion. Triggers on CLI tool development, argument parsing, or terminal UX design requests.
Manage application configuration across environments with layered config loading, environment variables, secrets management, and validation. Covers 12-factor app patterns and config file formats. Triggers on configuration management, environment variables, or settings architecture requests.
Designs and builds knowledge graphs to represent entities, relationships, and semantic connections, with query patterns for Neo4j, RDF, and property graphs.
Guides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniques like LoRA and QLoRA.
Designs location-based augmented reality experiences with geospatial anchoring, GPS integration, and real-world interactive overlays.
Builds MCP (Model Context Protocol) servers and clients for extending AI assistants with custom tools, resources, and prompts.
Configure, deploy, and troubleshoot Model Context Protocol (MCP) servers for AI agent workflows. Use when setting up MCP servers, debugging connection issues, managing multi-server configurations, integrating with Claude Desktop/Code/Cowork, or designing custom tool servers. Triggers on MCP configuration, tool server development, Claude integration issues, or agent infrastructure setup.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Architects cross-platform and native mobile applications, providing guidance on state management, navigation, and platform-specific best practices for React Native, Flutter, iOS, and Android.
Guides ML experiment logging, versioning, and reproducibility using tools like MLflow, Weights & Biases, and DVC for systematic model development.
Apply modular synthesis principles to system design, workflow architecture, and conceptual frameworks. Use when designing modular systems, creating architecture diagrams using synthesis metaphors, applying signal flow thinking to data pipelines, or translating between audio engineering and software concepts. Triggers on modular architecture design, signal flow diagrams, synthesis-inspired system thinking, or "oscillator/patch" metaphors.
Self-improvement patterns for AI agents to learn from feedback, errors, and successful patterns across sessions
Curated bundle of governance and quality skills for ORGANVM ecosystem management. Includes ecosystem autopsy and discovery, promotion readiness, onboarding flows, stranger testing, repository standards, verification, and coding standards. Use when establishing or auditing governance practices for repositories.
Conducts a full automated autopsy of the current workspace directory to map files, identifies structural issues, proposes a restructuring plan (the signal), and establishes unified governance using templates. Use this skill when a user asks to map, restructure, reorganize, or apply new governance to an existing messy repository.
Orchestrate a full directory-graph autopsy across an ORGANVM workspace, then emit migration signals that unite repositories under canonical governance. Thin wrapper over organvm ecosystem + organvm irf + promotion-readiness-checklist. Triggers on auto-autopsy, map all directories, governance migration, ecosystem discovery, or "send the signal to unite" requests.
Self-improvement patterns for AI agents to learn from feedback, errors, and successful patterns across sessions
Orchestrate a full directory-graph autopsy across an ORGANVM workspace, then emit migration signals that unite repositories under canonical governance. Thin wrapper over organvm ecosystem + organvm irf + promotion-readiness-checklist. Triggers on auto-autopsy, map all directories, governance migration, ecosystem discovery, or "send the signal to unite" requests.
Build browser extensions with Manifest V3 for Chrome, Firefox, and cross-browser compatibility. Covers content scripts, background workers, popup UI, storage APIs, and extension messaging. Triggers on browser extension development, Manifest V3, or Chrome extension requests.
Transform AI conversations and chat transcripts into publishable content including blog posts, documentation, tutorials, and knowledge base entries. Covers extraction, restructuring, and editorial refinement. Triggers on conversation-to-content, transcript processing, or chat-to-doc requests.
Curated bundle of essential skills for fullstack web development. Installs API design, testing, deployment, backend patterns, frontend architecture, and code quality skills together. Use when starting a new fullstack project or onboarding onto a codebase.
Publish essays and long-form content through a structured pipeline from draft to distribution. Covers markdown-to-HTML conversion, metadata management, cross-posting strategies, and RSS/Atom feed generation. Triggers on essay publishing, content pipeline, or blog deployment requests.
Implement structured logging, error hierarchies, and observability patterns for production systems. Covers structured JSON logging, error classification, correlation IDs, and alerting integration. Triggers on logging architecture, error handling strategy, or observability requests.
Build production FastAPI applications with dependency injection, middleware, background tasks, and structured project layouts. Covers async patterns, Pydantic models, OpenAPI customization, and testing strategies. Triggers on FastAPI development, Python API, or async web framework requests.
Deploy generative art projects for exhibition, web galleries, and print production. Covers rendering pipelines, resolution management, gallery hosting, and archival strategies for algorithmic artworks. Triggers on generative art deployment, art exhibition setup, or digital art publishing requests.
Build production FastAPI applications with dependency injection, middleware, background tasks, and structured project layouts. Covers async patterns, Pydantic models, OpenAPI customization, and testing strategies. Triggers on FastAPI development, Python API, or async web framework requests.
Curated bundle for the full essay lifecycle from writing through multi-platform distribution. Includes publishing pipeline, creative writing craft, content distribution strategy, and POSSE architecture. Use when building an end-to-end content publishing workflow.
Advanced PostgreSQL patterns for performance optimization, complex queries, indexing strategies, and database design
Design and validate JSON Schemas for API contracts, configuration files, and data exchange formats. Covers schema composition, conditional validation, and code generation from schemas. Triggers on JSON Schema creation, data validation, or API contract design requests.
Analyze market positioning, identify underserved segments, and map competitive gaps using systematic frameworks. Covers SWOT analysis, competitive landscape mapping, opportunity scoring, and positioning strategy. Triggers on market analysis, competitive research, or gap identification requests.
Curated bundle for managing monorepos with containerized deployment pipelines. Includes monorepo management, Docker containerization, CI/CD deployment, and coding standards. Use when setting up or improving multi-package repository infrastructure.
Manage monorepos and multi-package repositories with workspace tools, dependency management, selective builds, and change detection. Covers npm/pnpm workspaces, Turborepo, and Python monorepo patterns. Triggers on monorepo setup, workspace management, or multi-package repository requests.
Mobile-first responsive design patterns with breakpoints, fluid layouts, and adaptive components
Builds MCP (Model Context Protocol) servers and clients for extending AI assistants with custom tools, resources, and prompts.
Curated bundle of essential skills for fullstack web development. Installs API design, testing, deployment, backend patterns, frontend architecture, and code quality skills together. Use when starting a new fullstack project or onboarding onto a codebase.
Design and validate JSON Schemas for API contracts, configuration files, and data exchange formats. Covers schema composition, conditional validation, and code generation from schemas. Triggers on JSON Schema creation, data validation, or API contract design requests.
Publish essays and long-form content through a structured pipeline from draft to distribution. Covers markdown-to-HTML conversion, metadata management, cross-posting strategies, and RSS/Atom feed generation. Triggers on essay publishing, content pipeline, or blog deployment requests.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Test AI agent systems including tool use, multi-turn conversations, error recovery, and non-deterministic outputs. Covers mock strategies, evaluation metrics, and regression testing for agent workflows. Triggers on AI agent testing, LLM evaluation, or agent quality assurance requests.
Creates annotated bibliography-style manifests for Claude projects, tracking files, conversation threads, and relationships with unique IDs and annotations. Use when documenting project contents, creating file inventories, tracking conversation history, or building navigable knowledge maps.
Systematic approach to refactoring code for improved maintainability, performance, and clarity while preserving functionality
Automated code style enforcement with linters, formatters, and pre-commit hooks for consistent codebases
Craft compelling fiction and creative nonfiction with attention to structure, voice, prose style, and revision. Supports short stories, novel chapters, essays, and hybrid forms. Triggers on creative writing, fiction writing, story craft, prose style, or literary technique requests.
Optimize resumes and CVs for impact, ATS compatibility, and audience targeting. Supports multiple formats (chronological, functional, hybrid), accomplishment framing (STAR/XYZ), and tailoring for specific roles. Triggers on resume review, CV update, job application prep, or career document requests.
Designs DeFi trading systems for perpetual futures, liquidity provision, and automated strategies with risk management and MEV protection.
Deploy applications with confidence using CI/CD pipelines, containerization, and infrastructure as code. Covers GitHub Actions, Docker, Vercel, and cloud deployment patterns. Triggers on deployment, CI/CD, Docker, GitHub Actions, or DevOps requests.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Guides the creation of a "Minimal Root" home directory using the XDG Base Directory specification and a Bare Git Repository. Manages config separation, secrets, and cross-platform syncing.
Design and generate curriculum materials for college composition courses (ENC1101 and similar). Use when creating syllabi, assignment prompts, rubrics, lesson plans, scaffolded writing sequences, peer review guides, or D2L/LMS-formatted content. Triggers on requests for composition pedagogy, writing assignment design, grading criteria, or freshman writing course materials.
Systematic content evaluation framework progressing through Critique → Reinforcement → Risk Analysis → Growth. Use when reviewing writing, arguments, proposals, code documentation, or any content requiring rigorous multi-dimensional assessment. Supports interactive guided mode or autonomous full-report mode, with output as markdown report, structured checklist, or inline revision suggestions. Triggers on requests to evaluate, critique, improve, strengthen, or review content quality.
End-to-end feature development orchestration from planning through deployment with quality gates
Manage freelance and client work professionally—proposals, contracts, scope management, invoicing, and client communication. Covers the business side of creative work. Triggers on freelance, client work, proposals, contracts, pricing, or project scope requests.
Systematic approach to building consistent, maintainable frontend UI components with design systems and component libraries
Designs engaging gameplay loops, economies, and progression systems, balancing challenge and reward for interactive experiences.
Optimize Google Cloud Platform resource allocation and manage cloud credits efficiently. Use when planning GCP deployments, analyzing cloud spend, maximizing value from expiring credits, right-sizing instances, or designing cost-effective architectures. Triggers on GCP cost optimization, credit management, resource allocation planning, or cloud budget concerns.
Audits web applications and architectures for compliance with GDPR, CCPA, and other privacy regulations, focusing on consent, data minimization, and user rights.
Creates algorithmic music composition systems using procedural generation, Markov chains, L-systems, and neural approaches for ambient, adaptive, and experimental music.
Architects high-impact GitHub Profile READMEs using the "Special Repository" mechanism. optimizing for recruitment signaling, visual semiotics, and dynamic automation (Actions, WakaTime).
Organize GitHub repositories for professional presentation and maintainability. README templates, documentation standards, repo organization patterns, and profile optimization. Triggers on GitHub cleanup, repo organization, README writing, or open source presentation requests.
Enforces the "Minimal Root" philosophy for repository organization and implements "World-Class README" standards. Moves config clutter to `.config/` and creates high-conversion documentation.
operationalizes GitHub Projects (V2) as a dynamic roadmap system. Defines field taxonomy, "Triage" protocols, and synchronizes Strategy (Roadmap) with Execution (Issues).
Guides teams through IT outages and security incidents, providing structured workflows for detection, containment, eradication, and post-mortem analysis.
Generate sacred geometry patterns with interfaith symbolism for spiritual visualizations and art. Use when creating visual representations that honor multiple religious traditions, designing meditation aids, building soul journey visualizations, or producing art that bridges sacred traditions through geometric harmony. Triggers on sacred geometry requests, interfaith symbol design, spiritual visualization projects, or multi-tradition sacred art.
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Prepare for job interviews across formats—behavioral, technical, portfolio reviews, and negotiations. STAR/CAR frameworks for stories, common question patterns, research strategies, and follow-up templates. Triggers on interview prep, job interviews, behavioral questions, or salary negotiation requests.
Design knowledge systems using ontological principles—organizing by what things ARE rather than arbitrary hierarchies. Use when structuring personal knowledge bases, designing documentation systems, creating cross-domain linking patterns, building the {OS.me} ecosystem, or architecting information that reveals rather than obscures essential nature. Triggers on knowledge management, documentation architecture, information ontology, or systematic organization of complex domains.
Designs and builds knowledge graphs to represent entities, relationships, and semantic connections, with query patterns for Neo4j, RDF, and property graphs.
Guides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniques like LoRA and QLoRA.
Designs location-based augmented reality experiences with geospatial anchoring, GPS integration, and real-world interactive overlays.
Configure, deploy, and troubleshoot Model Context Protocol (MCP) servers for AI agent workflows. Use when setting up MCP servers, debugging connection issues, managing multi-server configurations, integrating with Claude Desktop/Code/Cowork, or designing custom tool servers. Triggers on MCP configuration, tool server development, Claude integration issues, or agent infrastructure setup.
Guides ML experiment logging, versioning, and reproducibility using tools like MLflow, Weights & Biases, and DVC for systematic model development.
Apply modular synthesis principles to system design, workflow architecture, and conceptual frameworks. Use when designing modular systems, creating architecture diagrams using synthesis metaphors, applying signal flow thinking to data pipelines, or translating between audio engineering and software concepts. Triggers on modular architecture design, signal flow diagrams, synthesis-inspired system thinking, or "oscillator/patch" metaphors.
Designs parallel agent workstreams for large feature sets by analyzing dependencies, assigning specialized agent types (Explore, Plan, Bash, Edit), maximizing parallelization, and creating execution plans with progress tracking and failure recovery. Use when breaking down large features into parallel agent work.
Build professional relationships through strategic outreach—cold emails, LinkedIn engagement, informational interviews, and follow-up sequences. Authentic connection over transactional networking. Triggers on networking, cold outreach, LinkedIn strategy, or informational interview requests.
Build production Next.js applications with App Router patterns, server components, data fetching strategies, authentication, and deployment. Covers the full stack from database to UI. Triggers on Next.js development, React server components, App Router, or full-stack TypeScript requests.
Comprehensive product requirements documentation from problem definition through launch planning. Supports both enterprise PRD (full specs, cross-functional alignment) and lean/startup style (hypothesis-driven one-pagers). Framework-agnostic with templates for Agile, Jobs-to-Be-Done, and hybrid approaches. Scaffolds related artifacts including user stories, acceptance criteria, wireframes brief, and technical handoff specs. Triggers on PRD creation, product specs, feature requirements, or product design documentation.
Curated bundle of essential Python backend development skills. Includes FastAPI patterns, packaging, database migrations, CLI design, and Redis caching. Use when building Python API services or backend systems.
Structure Python projects for distribution with pyproject.toml, src layouts, dependency management, and publishing workflows. Covers packaging tools (hatch, setuptools, flit, poetry), versioning strategies, and editable installs. Triggers on Python project setup, packaging configuration, or dependency management requests.
Implement real-time features with WebSockets, Server-Sent Events, and long polling. Covers connection management, room-based messaging, presence tracking, and scaling strategies. Triggers on WebSocket implementation, real-time communication, or live update feature requests.
Designs self-referential and recursive systems that examine, modify, or generate themselves, including metacognitive architectures and strange loops.
Build fault-tolerant systems with circuit breakers, retries with backoff, bulkheads, timeouts, and graceful degradation. Covers distributed system failure modes and recovery strategies. Triggers on reliability engineering, fault tolerance, or distributed system resilience requests.
Orchestrate multi-skill workflows with prompt-based skill chaining. Define sequential or parallel skill invocations using YAML chain definitions, track progress through chains, and use pre-built chains for development, documentation, and career workflows. Use when coordinating multiple skills for complex tasks.
Comprehensive security patterns for authentication, authorization, input validation, and common vulnerability prevention
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Multi-perspective collaborative inquiry. Decomposes a topic into six cognitive lenses (Scope, Logic, Mythos, Bridge, Meta, Pattern) that operate as a chorus rather than a single voice, then synthesizes meta-patterns no single lens could find alone. MANDATORY TRIGGERS: 'expansive inquiry', 'multi-perspective inquiry', 'explore this from every angle', 'six-lens analysis', 'run a chorus on this'. STRONG TRIGGERS: 'help me think through X deeply', 'mythopoetic AND logical analysis'. Do NOT trigger on simple Q&A or failure-focused inquiries — use premortem for those.
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Run a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed 6 months from now and works backward to find every reason why. Produces a revised plan with blind spots exposed. MANDATORY TRIGGERS: 'premortem this', 'run a premortem', 'what could kill this', 'future-proof this', 'stress test this plan', 'what am i missing here', 'find the blind spots'. STRONG TRIGGERS: 'poke holes in this', 'devil's advocate this', 'where will this break'. Do NOT trigger on factual questions or LLM Council requests. DO trigger when the cost of being wrong is high.
Create a scheduled task that can be run on demand or automatically on an interval. Distills the current session into a self-contained reusable prompt with cronExpression or fireAt, then calls the create_scheduled_task tool. Use when the user wants a recurring or one-time task scheduled — e.g. 'remind me every Friday', 'run this hourly', 'schedule a daily inbox check'.
Design effective prompts for LLM agents with structured input/output formats, chain-of-thought reasoning, few-shot examples, and system prompt architecture. Covers Claude-specific patterns and multi-turn conversation design. Triggers on prompt design, LLM interaction patterns, or system prompt architecture requests.
Manage monorepos and multi-package repositories with workspace tools, dependency management, selective builds, and change detection. Covers npm/pnpm workspaces, Turborepo, and Python monorepo patterns. Triggers on monorepo setup, workspace management, or multi-package repository requests.
Curated bundle for managing monorepos with containerized deployment pipelines. Includes monorepo management, Docker containerization, CI/CD deployment, and coding standards. Use when setting up or improving multi-package repository infrastructure.
Foundational layer beneath PDE. Governs eight-strata substrate (ontology, lineage, constellation, gap-map, agent-fleet, production-stack, internal-magnet, external-contribution) plus four operators (selfish-altruistic loop, magnetic membrane, portfolio operator, reflexive operator) for any domain a flag pierces — chess, fitness, voodoo, education, design, taxidermy. Pre-instantiates engine reuse via Phase 0 portfolio audit and stretching-rack gap diagnosis.
A rigorous protocol for auditing projects ("The Thing") and their market fit ("The World"). Uses parallel analysis lanes, friction mapping, and outcome testing to create actionable 30/60/90 day plans.
Translate internal markdown artifacts (pitch decks, business plans, research) into per-persona client-facing storefront surfaces in the client's domain language with ELI5/TLDR layers. Sits above Product Domain Engine and 8-Strata Domain Ideal-Whole; invokes voice-enforcement against persona-specific voice_constitution. Triggers on requests for client-facing surfaces, persona-tuned translation, ELI5/TLDR projections, or storefront-style client deliverables. Render is scaffold-and-curate (never auto-publish) to protect client trust.
Guided Cowork setup — install role-matched plugins, connect your tools, try a skill.
Integrate with social media platform APIs for automated posting, scheduling, analytics retrieval, and content syndication. Covers OAuth flows, rate limiting, and multi-platform strategies. Triggers on social media API integration, automated posting, or platform API requests.
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
A pedagogical aid that uses the Socratic method to guide users to answers through questioning, rather than providing direct solutions, to deepen understanding.
Evaluate source quality, build annotated bibliographies, and maintain curated reference collections. Covers the CRAAP test, source classification, citation management, and research documentation patterns. Triggers on source evaluation, bibliography creation, or research documentation requests.
Install a pre-commit hook that scans .specstory/history for secrets before commits. Run when user says "set up secret scanning", "install specstory guard", "protect my history", or "check for secrets".
Fetch project statistics from SpecStory Cloud. Run when user says "get project stats", "show SpecStory stats", "project statistics", "how many sessions", or "SpecStory metrics".
Specification-Driven Development (SDD) toolkit. Transforms ideas into executable specifications, implementation plans, and task lists. Use for feature planning, PRD creation, or when user invokes /speckit.specify, /speckit.plan, /speckit.tasks commands.
Track all URLs fetched during SpecStory AI coding sessions. Run when user says "show my link trail", "what URLs did I visit", "list fetched links", or "show web fetches".
Organize SpecStory AI coding sessions in .specstory/history into year/month folders. Run when user says "organize my history", "clean up specstory", "sort my sessions", or "organize specstory files".
Summarize recent SpecStory AI coding sessions in standup format. Use when the user wants to review sessions from .specstory/history, prepare for standups, track work progress, or understand what was accomplished.
Analyzes complex SQL queries to improve performance, suggesting indexing strategies, schema refactoring, and query rewrites.
Validate that documentation, READMEs, and onboarding guides are comprehensible to someone with zero prior context. Systematic approach to testing docs from a stranger's perspective with actionable feedback. Triggers on documentation review, onboarding validation, or README quality assessment requests.
Test-driven development workflow with comprehensive coverage requirements including unit, integration, and E2E tests
Write clear technical analysis, system architecture documents, decision records, and research synthesis. Covers argument structure, evidence-based reasoning, and technical communication patterns. Triggers on technical writing, architecture documentation, ADR creation, or analytical essay requests.
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
Write effective tests across the stack—unit, integration, E2E, and visual regression. Covers testing philosophy, framework selection, mocking strategies, and CI integration. Triggers on testing, test coverage, TDD, or quality assurance requests.
Enforce the Orchestrator Voice Constitution during text generation. Provides voice constraints, anti-pattern awareness, and scoring guidance. Use when writing or reviewing prose-heavy documents (READMEs, design docs, essays, manifestos).
Scaffold and build interactive 3D visualizations using Three.js with emphasis on algorithmic art, sacred geometry, temporal animations, and modular architecture. Use when creating WebGL visualizations, generative art pieces, interactive 3D experiences, particle systems, flow fields, or projects like gravitational spirals, temporal perspective pieces, or illuminated visual narratives. Triggers on requests for Three.js projects, 3D web graphics, algorithmic visualizations, or sacred geometry renders.
Implement vector similarity search with embedding generation, index selection, and hybrid retrieval strategies. Covers ChromaDB, pgvector, FAISS, and RAG pipeline design. Triggers on vector search, embeddings, semantic search, or RAG architecture requests.
Analyzes time-series data for patterns, trends, seasonality, and anomalies, with forecasting using statistical and machine learning methods.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Design engaging workshops, conference talks, and educational presentations. Covers learning objectives, activity design, slide craft, and facilitation techniques. Triggers on workshop design, presentation prep, talk structure, or training session requests.
Design robust APIs with RESTful patterns, GraphQL schemas, versioning strategies, and error handling conventions. Supports OpenAPI/Swagger documentation and SDK generation patterns. Triggers on API design, schema definition, endpoint architecture, or developer experience requests.
Curated bundle for building, testing, and coordinating AI agent systems. Includes multi-agent orchestration, agent testing, cross-agent handoff, MCP server building, and prompt engineering. Use when developing AI agent workflows or multi-agent systems.
Reflective pass over your memory files — merge duplicates, fix stale facts, prune the index.
Comprehensive dramaturgical analysis of screenplays and scripts. Use when asked to analyze, break down, map, or provide feedback on a script. Triggers on requests involving beat mapping, act structure analysis, scene-by-scene breakdown, first-reader reports, production notes, or any comprehensive script coverage. Claude assumes combined roles of aesthete, dramaturgist, narratologist, art historian, cinephile, rhetorician, producer, academic, and first-reader.
Designs systems for encoding, scoring, and generating choreographic movement using Laban notation, computational geometry, and procedural animation principles.
Distill artist/theorist narrative principles into formal, implementable algorithmic frameworks. Use when asked to extract, formalize, or systematize narrative techniques from any storytelling source—filmmakers, writers, theorists, game designers, showrunners. Triggers on requests involving narrative principle extraction, story structure analysis, craft methodology formalization, or creating implementable storytelling protocols.
Designs parallel agent workstreams for large feature sets by analyzing dependencies, assigning specialized agent types (Explore, Plan, Bash, Edit), maximizing parallelization, and creating execution plans with progress tracking and failure recovery. Use when breaking down large features into parallel agent work.
Build professional relationships through strategic outreach—cold emails, LinkedIn engagement, informational interviews, and follow-up sequences. Authentic connection over transactional networking. Triggers on networking, cold outreach, LinkedIn strategy, or informational interview requests.
Build production Next.js applications with App Router patterns, server components, data fetching strategies, authentication, and deployment. Covers the full stack from database to UI. Triggers on Next.js development, React server components, App Router, or full-stack TypeScript requests.
Implements OAuth 2.0 and OpenID Connect authentication flows with proper security, token management, and common provider integrations.
Translate internal markdown artifacts (pitch decks, business plans, research) into per-persona client-facing storefront surfaces in the client's domain language with ELI5/TLDR layers. Sits above Product Domain Engine and 8-Strata Domain Ideal-Whole; invokes voice-enforcement against persona-specific voice_constitution. Triggers on requests for client-facing surfaces, persona-tuned translation, ELI5/TLDR projections, or storefront-style client deliverables. Render is scaffold-and-curate (never auto-publish) to protect client trust.
Curated bundle of governance and quality skills for ORGANVM ecosystem management. Includes ecosystem autopsy and discovery, promotion readiness, onboarding flows, stranger testing, repository standards, verification, and coding standards. Use when establishing or auditing governance practices for repositories.
Create compelling pitch decks for startups, projects, and internal proposals. Covers narrative structure, slide design principles, data visualization, and audience-specific adaptation. Triggers on pitch deck creation, presentation design, or fundraising deck requests.
Renames projects and content with dense, meaningful ontological titles that describe essence and function. Combines 3-4 words using separator conventions (- for compound/close words, -- for distant concepts). Provides translations to Latin and Greek. Use when naming projects, repositories, systems, or concepts.
Implement POSSE (Publish on Own Site, Syndicate Elsewhere) content distribution with canonical URLs, cross-platform syndication, backfeed collection, and resilient delivery. Covers multi-platform publishing automation and IndieWeb patterns. Triggers on POSSE implementation, content syndication architecture, or IndieWeb publishing requests.
Advanced PostgreSQL patterns for performance optimization, complex queries, indexing strategies, and database design
Curate and present creative/technical work for maximum impact. Structure case studies, craft project narratives, optimize for different audiences (hiring managers, clients, collaborators). Supports portfolio websites, PDF decks, and presentation formats. Triggers on portfolio review, case study writing, project showcase, or work presentation requests.
Run a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed 6 months from now and works backward to find every reason why. Produces a revised plan with blind spots exposed. MANDATORY TRIGGERS: 'premortem this', 'run a premortem', 'what could kill this', 'future-proof this', 'stress test this plan', 'what am i missing here', 'find the blind spots'. STRONG TRIGGERS: 'poke holes in this', 'devil's advocate this', 'where will this break'. Do NOT trigger on factual questions or LLM Council requests. DO trigger when the cost of being wrong is high.
Conductor skill that formalizes any domain-tied product through a 5-phase protocol (identify-map-encode-express-deploy) expressed through four rhetorical modes (logos-ethos-pathos-kairos). Orchestrates seven existing skills.
Comprehensive product requirements documentation from problem definition through launch planning. Supports both enterprise PRD (full specs, cross-functional alignment) and lean/startup style (hypothesis-driven one-pagers). Framework-agnostic with templates for Agile, Jobs-to-Be-Done, and hybrid approaches. Scaffolds related artifacts including user stories, acceptance criteria, wireframes brief, and technical handoff specs. Triggers on PRD creation, product specs, feature requirements, or product design documentation.
A strategic guide for managing complex creative portfolios as a system of "organs" (Art, Commerce, Tools), diagnosing lifecycle stages (Nigredo, Albedo, Rubedo), and balancing the "Four Fields" of creative labor.
Assess repository readiness for promotion through governance states (LOCAL, CANDIDATE, PUBLIC_PROCESS, GRADUATED) with structured checklists, quality gates, and evidence requirements. Triggers on promotion assessment, readiness review, or governance state transition requests.
Personal multi-project coordination for creative practitioners managing many concurrent initiatives. Not PM methodology—practical systems for tracking progress, managing energy, and moving projects forward. Triggers on project management, multi-project coordination, progress tracking, or overwhelm with concurrent work.
Curated bundle of essential Python backend development skills. Includes FastAPI patterns, packaging, database migrations, CLI design, and Redis caching. Use when building Python API services or backend systems.
Structure Python projects for distribution with pyproject.toml, src layouts, dependency management, and publishing workflows. Covers packaging tools (hatch, setuptools, flit, poetry), versioning strategies, and editable installs. Triggers on Python project setup, packaging configuration, or dependency management requests.
Build interactive 3D experiences in React using react-three-fiber (R3F), drei helpers, and shader integration. Covers scene composition, performance optimization, and animation patterns. Triggers on R3F development, React + Three.js, or declarative 3D scene requests.
Implement real-time features with WebSockets, Server-Sent Events, and long polling. Covers connection management, room-based messaging, presence tracking, and scaling strategies. Triggers on WebSocket implementation, real-time communication, or live update feature requests.
Analyze narrative structures, character arcs, and genre conventions in reality television for academic research and content analysis. Use when studying reality TV editing patterns, mapping contestant storylines, analyzing producer manipulation techniques, comparing show formats, or writing about unscripted television. Triggers on reality TV analysis, unscripted television research, character arc mapping, or genre convention studies.
Use Redis effectively for caching, pub/sub messaging, rate limiting, distributed locks, and session storage. Covers data structure selection, expiration strategies, and cluster patterns. Triggers on Redis usage, caching architecture, or pub/sub messaging requests.
Onboard new repositories into a managed ecosystem with seed.yaml contracts, CI/CD setup, documentation standards, and governance integration. Covers the full lifecycle from repo creation through promotion readiness. Triggers on new repository setup, repo onboarding, or ecosystem integration requests.
Designs self-referential and recursive systems that examine, modify, or generate themselves, including metacognitive architectures and strange loops.
Build fault-tolerant systems with circuit breakers, retries with backoff, bulkheads, timeouts, and graceful degradation. Covers distributed system failure modes and recovery strategies. Triggers on reliability engineering, fault tolerance, or distributed system resilience requests.
Systematic methodology for gathering, analyzing, and synthesizing research from multiple sources into coherent insights and actionable knowledge.
Provides expert guidance on Rust programming, focusing on memory safety, concurrency patterns, and idiomatic architectural choices for systems software.
Mobile-first responsive design patterns with breakpoints, fluid layouts, and adaptive components
Create a scheduled task that can be run on demand or automatically on an interval. Distills the current session into a self-contained reusable prompt with cronExpression or fireAt, then calls the create_scheduled_task tool. Use when the user wants a recurring or one-time task scheduled — e.g. 'remind me every Friday', 'run this hourly', 'schedule a daily inbox check'.
Comprehensive security patterns for authentication, authorization, input validation, and common vulnerability prevention
Helps users organize knowledge, categorize notes, and discover connections within their personal knowledge management systems (e.g., Obsidian, Notion).
Comprehensive dramaturgical analysis of screenplays and scripts. Use when asked to analyze, break down, map, or provide feedback on a script. Triggers on requests involving beat mapping, act structure analysis, scene-by-scene breakdown, first-reader reports, production notes, or any comprehensive script coverage. Claude assumes combined roles of aesthete, dramaturgist, narratologist, art historian, cinephile, rhetorician, producer, academic, and first-reader.
Curated bundle of essential security skills for building secure applications. Includes threat modeling, hardening guides, audit checklists, compliance frameworks, and contract analysis. Use when establishing security practices for a project.
Conducts systematic security analyses using methodologies like STRIDE to identify vulnerabilities in software architectures and propose mitigations.
Manage AI agent session lifecycles with structured phases (FRAME, SHAPE, BUILD, PROVE), context preservation across sessions, handoff protocols, and session metadata tracking. Triggers on session management, agent lifecycle, or multi-session workflow requests.
Guided Cowork setup — install role-matched plugins, connect your tools, try a skill.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Orchestrate multi-skill workflows with prompt-based skill chaining. Define sequential or parallel skill invocations using YAML chain definitions, track progress through chains, and use pre-built chains for development, documentation, and career workflows. Use when coordinating multiple skills for complex tasks.
Integrate with social media platform APIs for automated posting, scheduling, analytics retrieval, and content syndication. Covers OAuth flows, rate limiting, and multi-platform strategies. Triggers on social media API integration, automated posting, or platform API requests.
A pedagogical aid that uses the Socratic method to guide users to answers through questioning, rather than providing direct solutions, to deepen understanding.
Evaluate source quality, build annotated bibliographies, and maintain curated reference collections. Covers the CRAAP test, source classification, citation management, and research documentation patterns. Triggers on source evaluation, bibliography creation, or research documentation requests.
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
Specification-Driven Development (SDD) toolkit. Transforms ideas into executable specifications, implementation plans, and task lists. Use for feature planning, PRD creation, or when user invokes /speckit.specify, /speckit.plan, /speckit.tasks commands.
Promote creative and technical work through strategic content distribution. Covers platform selection, audience building, content repurposing, and engagement strategies without becoming a full-time marketer. Triggers on promotion, audience building, social media strategy, or content marketing requests.
Designs ETL/ELT data pipelines with proper extraction, transformation, and loading patterns, including orchestration, error handling, and data quality validation.
Progressive context retrieval pattern for understanding unfamiliar codebases through iterative refinement
Designs reliable webhook systems with proper delivery guarantees, retry logic, signature verification, and idempotent processing for event-driven integrations.
Designs interactive theatrical experiences with branching narratives, audience participation systems, and immersive environmental storytelling.
Write compelling grant proposals for academic research, creative projects, and nonprofit initiatives. Covers federal (NSF, NEA, NEH), foundation, and institutional grants with attention to narrative, budget justification, and review criteria. Triggers on grant writing, funding proposals, research funding, or fellowship applications.
Create algorithmic and generative art using mathematical patterns, noise functions, particle systems, and procedural generation. Covers flow fields, L-systems, fractals, and creative coding foundations. Triggers on generative art, algorithmic art, creative coding, procedural generation, or mathematical visualization requests.
Give effective feedback that promotes learning and growth. Covers written feedback on student work, rubric design, peer review facilitation, and constructive critique techniques. Triggers on grading, feedback, rubrics, peer review, or critique requests.
Transforms raw data into compelling visual narratives using Python or R, focusing on clarity, insight, and aesthetic presentation.
Analyzes freelance contracts and Statements of Work (SOW) to identify potential risks, scope creep, and unfavorable terms, providing plain-language explanations.
Use when substantive inline content delivered during a session lives only in the JSONL transcript and needs promotion to a durable, surface-discoverable, remote-backed artifact. Triggers on "persist this", "promote to a plan", "make this survive context exit", "engine log N", or when closeout flags a deliverable as "inline only — not file-persisted". Provides the four-phase extract → frontmatter → propagate → register protocol. Sibling to artifact-resurfacing (which reconciles citations pointing at nothing); this one rescues content that exists without citation.
Install a pre-commit hook that scans .specstory/history for secrets before commits. Run when user says "set up secret scanning", "install specstory guard", "protect my history", or "check for secrets".
Track all URLs fetched during SpecStory AI coding sessions. Run when user says "show my link trail", "what URLs did I visit", "list fetched links", or "show web fetches".
Organize SpecStory AI coding sessions in .specstory/history into year/month folders. Run when user says "organize my history", "clean up specstory", "sort my sessions", or "organize specstory files".
Fetch project statistics from SpecStory Cloud. Run when user says "get project stats", "show SpecStory stats", "project statistics", "how many sessions", or "SpecStory metrics".
Summarize recent SpecStory AI coding sessions in standup format. Use when the user wants to review sessions from .specstory/history, prepare for standups, track work progress, or understand what was accomplished.
Analyzes complex SQL queries to improve performance, suggesting indexing strategies, schema refactoring, and query rewrites.
Validate that documentation, READMEs, and onboarding guides are comprehensible to someone with zero prior context. Systematic approach to testing docs from a stranger's perspective with actionable feedback. Triggers on documentation review, onboarding validation, or README quality assessment requests.
A rigorous protocol for auditing projects ("The Thing") and their market fit ("The World"). Uses parallel analysis lanes, friction mapping, and outcome testing to create actionable 30/60/90 day plans.
Analyze your SpecStory AI coding sessions in .specstory/history for yak shaving - when your initial goal got derailed into rabbit holes. Run when user says "analyze my yak shaving", "check for rabbit holes", "how distracted was I", or "yak shave score".
Test-driven development workflow with comprehensive coverage requirements including unit, integration, and E2E tests
Write clear technical analysis, system architecture documents, decision records, and research synthesis. Covers argument structure, evidence-based reasoning, and technical communication patterns. Triggers on technical writing, architecture documentation, ADR creation, or analytical essay requests.
Write effective tests across the stack—unit, integration, E2E, and visual regression. Covers testing philosophy, framework selection, mocking strategies, and CI integration. Triggers on testing, test coverage, TDD, or quality assurance requests.
Scaffold and build interactive 3D visualizations using Three.js with emphasis on algorithmic art, sacred geometry, temporal animations, and modular architecture. Use when creating WebGL visualizations, generative art pieces, interactive 3D experiences, particle systems, flow fields, or projects like gravitational spirals, temporal perspective pieces, or illuminated visual narratives. Triggers on requests for Three.js projects, 3D web graphics, algorithmic visualizations, or sacred geometry renders.
Use when substantive inline content delivered during a session lives only in the JSONL transcript and needs promotion to a durable, surface-discoverable, remote-backed artifact. Triggers on "persist this", "promote to a plan", "make this survive context exit", "engine log N", or when closeout flags a deliverable as "inline only — not file-persisted". Provides the four-phase extract → frontmatter → propagate → register protocol. Sibling to artifact-resurfacing (which reconciles citations pointing at nothing); this one rescues content that exists without citation.
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
Analyzes time-series data for patterns, trends, seasonality, and anomalies, with forecasting using statistical and machine learning methods.
Implement vector similarity search with embedding generation, index selection, and hybrid retrieval strategies. Covers ChromaDB, pgvector, FAISS, and RAG pipeline design. Triggers on vector search, embeddings, semantic search, or RAG architecture requests.
Enforce the Orchestrator Voice Constitution during text generation. Provides voice constraints, anti-pattern awareness, and scoring guidance. Use when writing or reviewing prose-heavy documents (READMEs, design docs, essays, manifestos).
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Design engaging workshops, conference talks, and educational presentations. Covers learning objectives, activity design, slide craft, and facilitation techniques. Triggers on workshop design, presentation prep, talk structure, or training session requests.
Conducts a full automated autopsy of the current workspace directory to map files, identifies structural issues, proposes a restructuring plan (the signal), and establishes unified governance using templates. Use this skill when a user asks to map, restructure, reorganize, or apply new governance to an existing messy repository.
Transform any data, document, deck, README, manifest, config, report, or compilation by (1) extracting every piece of dynamic information — names, links, statistics, costs, identifiers, dates, thresholds, contact details — into configurable environment variables instead of hard-coding, and (2) enforcing that every factual assertion carries at least two independent citations. Use this skill whenever the user provides compiled data and asks to debrand, parametrize, sanitize, generalize, abstract, anonymize, make reusable, harden against drift, or remove hard-coded values. Also use whenever reviewing or refactoring content that mixes brand-specific particulars with reusable structure, or that makes claims without verifiable sources. Triggers on phrases like "remove branding," "make this reusable," "transmute this," "parametrize," "no hard-coded values," "configurable," "needs citations," "verify these claims," or any request to convert a one-off artifact into a parameterized template.
Verify claims in a session/PR/transcript against on-disk reality. Produce a verification report (verified / false-positive / false-negative / partial) with explicit owners. STOP at verification — do not execute remediation without explicit approval.
Dry-run audit + targeted cleanup for shell command history. Currently wraps atuin (stats today, prune, dedup with dated preview artifacts); extensible to zsh/bash/mcfly backends. Always previews before applying — apply commands are echoed for the human to run, never auto-executed. Triggers on "/shell-history-hygiene", "audit atuin", "audit shell history", "clean shell history", "atuin prune", "atuin dedup", "shell history hygiene", "history cleanup". Replaces ad-hoc one-liners (e.g. `... | tee cmd > file.txt` which wrote two files, swallowed dedup output, and left a junk `cmd` file).
Verify claims in a session/PR/transcript against on-disk reality. Produce a verification report (verified / false-positive / false-negative / partial) with explicit owners. STOP at verification — do not execute remediation without explicit approval.
Transform any data, document, deck, README, manifest, config, report, or compilation by (1) extracting every piece of dynamic information — names, links, statistics, costs, identifiers, dates, thresholds, contact details — into configurable environment variables instead of hard-coding, and (2) enforcing that every factual assertion carries at least two independent citations. Use this skill whenever the user provides compiled data and asks to debrand, parametrize, sanitize, generalize, abstract, anonymize, make reusable, harden against drift, or remove hard-coded values. Also use whenever reviewing or refactoring content that mixes brand-specific particulars with reusable structure, or that makes claims without verifiable sources. Triggers on phrases like "remove branding," "make this reusable," "transmute this," "parametrize," "no hard-coded values," "configurable," "needs citations," "verify these claims," or any request to convert a one-off artifact into a parameterized template.
Designs reliable webhook systems with proper delivery guarantees, retry logic, signature verification, and idempotent processing for event-driven integrations.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Build dynamic web interfaces with htmx using hypermedia-driven patterns for partial page updates, lazy loading, infinite scroll, and server-sent events without writing JavaScript. Triggers on htmx usage, hypermedia architecture, or progressive enhancement requests.
Create compelling pitch decks for startups, projects, and internal proposals. Covers narrative structure, slide design principles, data visualization, and audience-specific adaptation. Triggers on pitch deck creation, presentation design, or fundraising deck requests.
Implement POSSE (Publish on Own Site, Syndicate Elsewhere) content distribution with canonical URLs, cross-platform syndication, backfeed collection, and resilient delivery. Covers multi-platform publishing automation and IndieWeb patterns. Triggers on POSSE implementation, content syndication architecture, or IndieWeb publishing requests.
Assess repository readiness for promotion through governance states (LOCAL, CANDIDATE, PUBLIC_PROCESS, GRADUATED) with structured checklists, quality gates, and evidence requirements. Triggers on promotion assessment, readiness review, or governance state transition requests.
Build interactive 3D experiences in React using react-three-fiber (R3F), drei helpers, and shader integration. Covers scene composition, performance optimization, and animation patterns. Triggers on R3F development, React + Three.js, or declarative 3D scene requests.
Use Redis effectively for caching, pub/sub messaging, rate limiting, distributed locks, and session storage. Covers data structure selection, expiration strategies, and cluster patterns. Triggers on Redis usage, caching architecture, or pub/sub messaging requests.
Build inclusive web experiences following WCAG guidelines. Covers semantic HTML, ARIA, keyboard navigation, color contrast, and testing strategies. Triggers on accessibility, a11y, WCAG, screen readers, or inclusive design requests.
Designs multi-agent systems with coordinated agent swarms, task distribution, inter-agent communication, and emergent collective behavior.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Production-ready backend API implementation patterns including REST, GraphQL, authentication, error handling, and data validation
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Audio production concepts, DSP fundamentals, mixing/mastering techniques, and DAW workflows. Bridges modular synthesis philosophy with practical audio engineering. Triggers on audio production, mixing, sound design, DSP, or music technology requests.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
End-to-end protocol for when outbound open-source contributions generate inbound relationship opportunities. Covers contact verification, company research, architectural comparison, conversation preparation with multi-register talking points (technical/humanities/ELI5), response drafting, and honest boundary mapping. Triggers on inbound emails from contribution targets, cold outreach from people who found your PRs, or any signal that an open-source contribution attracted strategic attention.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Distill artist/theorist narrative principles into formal, implementable algorithmic frameworks. Use when asked to extract, formalize, or systematize narrative techniques from any storytelling source—filmmakers, writers, theorists, game designers, showrunners. Triggers on requests involving narrative principle extraction, story structure analysis, craft methodology formalization, or creating implementable storytelling protocols.
Curate and present creative/technical work for maximum impact. Structure case studies, craft project narratives, optimize for different audiences (hiring managers, clients, collaborators). Supports portfolio websites, PDF decks, and presentation formats. Triggers on portfolio review, case study writing, project showcase, or work presentation requests.
A strategic guide for managing complex creative portfolios as a system of "organs" (Art, Commerce, Tools), diagnosing lifecycle stages (Nigredo, Albedo, Rubedo), and balancing the "Four Fields" of creative labor.
Personal multi-project coordination for creative practitioners managing many concurrent initiatives. Not PM methodology—practical systems for tracking progress, managing energy, and moving projects forward. Triggers on project management, multi-project coordination, progress tracking, or overwhelm with concurrent work.
Analyze narrative structures, character arcs, and genre conventions in reality television for academic research and content analysis. Use when studying reality TV editing patterns, mapping contestant storylines, analyzing producer manipulation techniques, comparing show formats, or writing about unscripted television. Triggers on reality TV analysis, unscripted television research, character arc mapping, or genre convention studies.
Helps users organize knowledge, categorize notes, and discover connections within their personal knowledge management systems (e.g., Obsidian, Notion).
Conducts systematic security analyses using methodologies like STRIDE to identify vulnerabilities in software architectures and propose mitigations.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Craft compelling fiction and creative nonfiction with attention to structure, voice, prose style, and revision. Supports short stories, novel chapters, essays, and hybrid forms. Triggers on creative writing, fiction writing, story craft, prose style, or literary technique requests.
Optimize resumes and CVs for impact, ATS compatibility, and audience targeting. Supports multiple formats (chronological, functional, hybrid), accomplishment framing (STAR/XYZ), and tailoring for specific roles. Triggers on resume review, CV update, job application prep, or career document requests.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Session-end ritual that walks back through plans authored and atoms touched in this session, assigning each a closure status (DONE-NNN, IRF-XXX-NNN, or `~/.Codex/plans/abandoned/`). Verifies git state. Produces CLOSEOUT_SUMMARY.md. Triggers on "/closeout", "close out the session", "end of session", "wrap up", "session close", or before any planned `git push`. Addresses the 90.4% plan-orphan rate documented in docs/evaluation/self-review-2026-05-05/stale-plans-and-orphan-commits.md.
Systematic approach to refactoring code for improved maintainability, performance, and clarity while preserving functionality
Automated code style enforcement with linters, formatters, and pre-commit hooks for consistent codebases
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Reflective pass over your memory files — merge duplicates, fix stale facts, prune the index.
Promote creative and technical work through strategic content distribution. Covers platform selection, audience building, content repurposing, and engagement strategies without becoming a full-time marketer. Triggers on promotion, audience building, social media strategy, or content marketing requests.
Analyzes freelance contracts and Statements of Work (SOW) to identify potential risks, scope creep, and unfavorable terms, providing plain-language explanations.
Designs ETL/ELT data pipelines with proper extraction, transformation, and loading patterns, including orchestration, error handling, and data quality validation.
Transforms raw data into compelling visual narratives using Python or R, focusing on clarity, insight, and aesthetic presentation.
Designs DeFi trading systems for perpetual futures, liquidity provision, and automated strategies with risk management and MEV protection.
Deploy applications with confidence using CI/CD pipelines, containerization, and infrastructure as code. Covers GitHub Actions, Docker, Vercel, and cloud deployment patterns. Triggers on deployment, CI/CD, Docker, GitHub Actions, or DevOps requests.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Session-end ritual that walks back through plans authored and atoms touched in this session, assigning each a closure status (DONE-NNN, IRF-XXX-NNN, or `~/.Codex/plans/abandoned/`). Verifies git state. Produces CLOSEOUT_SUMMARY.md. Triggers on "/closeout", "close out the session", "end of session", "wrap up", "session close", or before any planned `git push`. Addresses the 90.4% plan-orphan rate documented in docs/evaluation/self-review-2026-05-05/stale-plans-and-orphan-commits.md.
Manage application configuration across environments with layered config loading, environment variables, secrets management, and validation. Covers 12-factor app patterns and config file formats. Triggers on configuration management, environment variables, or settings architecture requests.
Manage database schema changes safely with migration tools, zero-downtime strategies, and rollback procedures. Covers Alembic, SQL migrations, data migrations, and testing strategies. Triggers on database migration, schema changes, or Alembic configuration requests.
Design command-line interfaces with clear argument parsing, subcommands, help text, output formatting, and exit codes. Covers Click, Typer, argparse, and shell completion. Triggers on CLI tool development, argument parsing, or terminal UX design requests.
Transform AI conversations and chat transcripts into publishable content including blog posts, documentation, tutorials, and knowledge base entries. Covers extraction, restructuring, and editorial refinement. Triggers on conversation-to-content, transcript processing, or chat-to-doc requests.
Implement reliable data backup and recovery strategies with automated scheduling, encryption, rotation policies, and disaster recovery testing. Covers database backups, file system snapshots, and cloud storage patterns. Triggers on backup strategy, disaster recovery, or data protection requests.
Build community platforms with user profiles, discussion forums, event management, and moderation tools. Covers real-time features, content moderation, and community engagement patterns. Triggers on community platform development, forum design, or social feature requests.
Audit document collections to extract features, identify patterns, assess quality, and build structured inventories. Covers metadata extraction, content classification, gap analysis, and coverage mapping. Triggers on document audit, content inventory, or document feature extraction requests.
Containerize applications with multi-stage Dockerfiles, Docker Compose orchestration, image optimization, and container security. Covers Python, Node.js, and multi-service architectures. Triggers on Docker, containerization, or container orchestration requests.
Transfer context between AI agent sessions with structured handoff protocols, state serialization, and decision log preservation. Covers multi-agent coordination, context compression, and continuity patterns. Triggers on agent handoff, session transfer, or multi-agent continuity requests.
Build data ingestion pipelines for batch and streaming data from multiple sources. Covers extraction strategies, format normalization, deduplication, validation gates, and staging patterns. Triggers on data ingestion, ETL pipeline, or data import architecture requests.
Analyze market positioning, identify underserved segments, and map competitive gaps using systematic frameworks. Covers SWOT analysis, competitive landscape mapping, opportunity scoring, and positioning strategy. Triggers on market analysis, competitive research, or gap identification requests.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Conductor skill that formalizes any domain-tied product through a 5-phase protocol (identify-map-encode-express-deploy) expressed through four rhetorical modes (logos-ethos-pathos-kairos). Orchestrates seven existing skills.
Analyze your SpecStory AI coding sessions in .specstory/history for yak shaving - when your initial goal got derailed into rabbit holes. Run when user says "analyze my yak shaving", "check for rabbit holes", "how distracted was I", or "yak shave score".
Build browser extensions with Manifest V3 for Chrome, Firefox, and cross-browser compatibility. Covers content scripts, background workers, popup UI, storage APIs, and extension messaging. Triggers on browser extension development, Manifest V3, or Chrome extension requests.
Creates annotated bibliography-style manifests for Claude projects, tracking files, conversation threads, and relationships with unique IDs and annotations. Use when documenting project contents, creating file inventories, tracking conversation history, or building navigable knowledge maps.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Design and implement blockchain integrations across chains and frameworks with emphasis on patterns over specific technologies. Use when building Web3 applications, smart contract systems, token mechanics, decentralized identity, or blockchain-verified data. Triggers on blockchain architecture, smart contract design, Web3 integration, token systems, or decentralized application development. Framework-agnostic—applies to Ethereum, Solana, or emerging chains.
Architects cross-platform and native mobile applications, providing guidance on state management, navigation, and platform-specific best practices for React Native, Flutter, iOS, and Android.
Designs systems for encoding, scoring, and generating choreographic movement using Laban notation, computational geometry, and procedural animation principles.
Implements OAuth 2.0 and OpenID Connect authentication flows with proper security, token management, and common provider integrations.
Renames projects and content with dense, meaningful ontological titles that describe essence and function. Combines 3-4 words using separator conventions (- for compound/close words, -- for distant concepts). Provides translations to Latin and Greek. Use when naming projects, repositories, systems, or concepts.
Onboard new repositories into a managed ecosystem with seed.yaml contracts, CI/CD setup, documentation standards, and governance integration. Covers the full lifecycle from repo creation through promotion readiness. Triggers on new repository setup, repo onboarding, or ecosystem integration requests.
Systematic methodology for gathering, analyzing, and synthesizing research from multiple sources into coherent insights and actionable knowledge.
Provides expert guidance on Rust programming, focusing on memory safety, concurrency patterns, and idiomatic architectural choices for systems software.
Curated bundle of essential security skills for building secure applications. Includes threat modeling, hardening guides, audit checklists, compliance frameworks, and contract analysis. Use when establishing security practices for a project.
Manage AI agent session lifecycles with structured phases (FRAME, SHAPE, BUILD, PROVE), context preservation across sessions, handoff protocols, and session metadata tracking. Triggers on session management, agent lifecycle, or multi-session workflow requests.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Build inclusive web experiences following WCAG guidelines. Covers semantic HTML, ARIA, keyboard navigation, color contrast, and testing strategies. Triggers on accessibility, a11y, WCAG, screen readers, or inclusive design requests.
Curated bundle for building, testing, and coordinating AI agent systems. Includes multi-agent orchestration, agent testing, cross-agent handoff, MCP server building, and prompt engineering. Use when developing AI agent workflows or multi-agent systems.
Designs multi-agent systems with coordinated agent swarms, task distribution, inter-agent communication, and emergent collective behavior.
Test AI agent systems including tool use, multi-turn conversations, error recovery, and non-deterministic outputs. Covers mock strategies, evaluation metrics, and regression testing for agent workflows. Triggers on AI agent testing, LLM evaluation, or agent quality assurance requests.
Design robust APIs with RESTful patterns, GraphQL schemas, versioning strategies, and error handling conventions. Supports OpenAPI/Swagger documentation and SDK generation patterns. Triggers on API design, schema definition, endpoint architecture, or developer experience requests.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Audio production concepts, DSP fundamentals, mixing/mastering techniques, and DAW workflows. Bridges modular synthesis philosophy with practical audio engineering. Triggers on audio production, mixing, sound design, DSP, or music technology requests.
Production-ready backend API implementation patterns including REST, GraphQL, authentication, error handling, and data validation
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Design and implement blockchain integrations across chains and frameworks with emphasis on patterns over specific technologies. Use when building Web3 applications, smart contract systems, token mechanics, decentralized identity, or blockchain-verified data. Triggers on blockchain architecture, smart contract design, Web3 integration, token systems, or decentralized application development. Framework-agnostic—applies to Ethereum, Solana, or emerging chains.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Manage application configuration across environments with layered config loading, environment variables, secrets management, and validation. Covers 12-factor app patterns and config file formats. Triggers on configuration management, environment variables, or settings architecture requests.
Build community platforms with user profiles, discussion forums, event management, and moderation tools. Covers real-time features, content moderation, and community engagement patterns. Triggers on community platform development, forum design, or social feature requests.
Design command-line interfaces with clear argument parsing, subcommands, help text, output formatting, and exit codes. Covers Click, Typer, argparse, and shell completion. Triggers on CLI tool development, argument parsing, or terminal UX design requests.
Manage database schema changes safely with migration tools, zero-downtime strategies, and rollback procedures. Covers Alembic, SQL migrations, data migrations, and testing strategies. Triggers on database migration, schema changes, or Alembic configuration requests.
Containerize applications with multi-stage Dockerfiles, Docker Compose orchestration, image optimization, and container security. Covers Python, Node.js, and multi-service architectures. Triggers on Docker, containerization, or container orchestration requests.
Implement reliable data backup and recovery strategies with automated scheduling, encryption, rotation policies, and disaster recovery testing. Covers database backups, file system snapshots, and cloud storage patterns. Triggers on backup strategy, disaster recovery, or data protection requests.
Build data ingestion pipelines for batch and streaming data from multiple sources. Covers extraction strategies, format normalization, deduplication, validation gates, and staging patterns. Triggers on data ingestion, ETL pipeline, or data import architecture requests.
Curated bundle for the full essay lifecycle from writing through multi-platform distribution. Includes publishing pipeline, creative writing craft, content distribution strategy, and POSSE architecture. Use when building an end-to-end content publishing workflow.
Audit document collections to extract features, identify patterns, assess quality, and build structured inventories. Covers metadata extraction, content classification, gap analysis, and coverage mapping. Triggers on document audit, content inventory, or document feature extraction requests.
Design effective prompts for LLM agents with structured input/output formats, chain-of-thought reasoning, few-shot examples, and system prompt architecture. Covers Claude-specific patterns and multi-turn conversation design. Triggers on prompt design, LLM interaction patterns, or system prompt architecture requests.
Transfer context between AI agent sessions with structured handoff protocols, state serialization, and decision log preservation. Covers multi-agent coordination, context compression, and continuity patterns. Triggers on agent handoff, session transfer, or multi-agent continuity requests.
Deploy generative art projects for exhibition, web galleries, and print production. Covers rendering pipelines, resolution management, gallery hosting, and archival strategies for algorithmic artworks. Triggers on generative art deployment, art exhibition setup, or digital art publishing requests.
Implement structured logging, error hierarchies, and observability patterns for production systems. Covers structured JSON logging, error classification, correlation IDs, and alerting integration. Triggers on logging architecture, error handling strategy, or observability requests.
Guides the creation of a "Minimal Root" home directory using the XDG Base Directory specification and a Bare Git Repository. Manages config separation, secrets, and cross-platform syncing.
Foundational layer beneath PDE. Governs eight-strata substrate (ontology, lineage, constellation, gap-map, agent-fleet, production-stack, internal-magnet, external-contribution) plus four operators (selfish-altruistic loop, magnetic membrane, portfolio operator, reflexive operator) for any domain a flag pierces — chess, fitness, voodoo, education, design, taxidermy. Pre-instantiates engine reuse via Phase 0 portfolio audit and stretching-rack gap diagnosis.
Design and generate curriculum materials for college composition courses (ENC1101 and similar). Use when creating syllabi, assignment prompts, rubrics, lesson plans, scaffolded writing sequences, peer review guides, or D2L/LMS-formatted content. Triggers on requests for composition pedagogy, writing assignment design, grading criteria, or freshman writing course materials.
Multi-perspective collaborative inquiry. Decomposes a topic into six cognitive lenses (Scope, Logic, Mythos, Bridge, Meta, Pattern) that operate as a chorus rather than a single voice, then synthesizes meta-patterns no single lens could find alone. MANDATORY TRIGGERS: 'expansive inquiry', 'multi-perspective inquiry', 'explore this from every angle', 'six-lens analysis', 'run a chorus on this'. STRONG TRIGGERS: 'help me think through X deeply', 'mythopoetic AND logical analysis'. Do NOT trigger on simple Q&A or failure-focused inquiries — use premortem for those.
End-to-end feature development orchestration from planning through deployment with quality gates
Systematic content evaluation framework progressing through Critique → Reinforcement → Risk Analysis → Growth. Use when reviewing writing, arguments, proposals, code documentation, or any content requiring rigorous multi-dimensional assessment. Supports interactive guided mode or autonomous full-report mode, with output as markdown report, structured checklist, or inline revision suggestions. Triggers on requests to evaluate, critique, improve, strengthen, or review content quality.
Give effective feedback that promotes learning and growth. Covers written feedback on student work, rubric design, peer review facilitation, and constructive critique techniques. Triggers on grading, feedback, rubrics, peer review, or critique requests.
Manage freelance and client work professionally—proposals, contracts, scope management, invoicing, and client communication. Covers the business side of creative work. Triggers on freelance, client work, proposals, contracts, pricing, or project scope requests.
Systematic approach to building consistent, maintainable frontend UI components with design systems and component libraries
Designs engaging gameplay loops, economies, and progression systems, balancing challenge and reward for interactive experiences.
Optimize Google Cloud Platform resource allocation and manage cloud credits efficiently. Use when planning GCP deployments, analyzing cloud spend, maximizing value from expiring credits, right-sizing instances, or designing cost-effective architectures. Triggers on GCP cost optimization, credit management, resource allocation planning, or cloud budget concerns.
Audits web applications and architectures for compliance with GDPR, CCPA, and other privacy regulations, focusing on consent, data minimization, and user rights.
Create algorithmic and generative art using mathematical patterns, noise functions, particle systems, and procedural generation. Covers flow fields, L-systems, fractals, and creative coding foundations. Triggers on generative art, algorithmic art, creative coding, procedural generation, or mathematical visualization requests.
Creates algorithmic music composition systems using procedural generation, Markov chains, L-systems, and neural approaches for ambient, adaptive, and experimental music.
Architects high-impact GitHub Profile READMEs using the "Special Repository" mechanism. optimizing for recruitment signaling, visual semiotics, and dynamic automation (Actions, WakaTime).
Organize GitHub repositories for professional presentation and maintainability. README templates, documentation standards, repo organization patterns, and profile optimization. Triggers on GitHub cleanup, repo organization, README writing, or open source presentation requests.
Enforces the "Minimal Root" philosophy for repository organization and implements "World-Class README" standards. Moves config clutter to `.config/` and creates high-conversion documentation.
operationalizes GitHub Projects (V2) as a dynamic roadmap system. Defines field taxonomy, "Triage" protocols, and synchronizes Strategy (Roadmap) with Execution (Issues).
Build dynamic web interfaces with htmx using hypermedia-driven patterns for partial page updates, lazy loading, infinite scroll, and server-sent events without writing JavaScript. Triggers on htmx usage, hypermedia architecture, or progressive enhancement requests.
Write compelling grant proposals for academic research, creative projects, and nonprofit initiatives. Covers federal (NSF, NEA, NEH), foundation, and institutional grants with attention to narrative, budget justification, and review criteria. Triggers on grant writing, funding proposals, research funding, or fellowship applications.
End-to-end protocol for when outbound open-source contributions generate inbound relationship opportunities. Covers contact verification, company research, architectural comparison, conversation preparation with multi-register talking points (technical/humanities/ELI5), response drafting, and honest boundary mapping. Triggers on inbound emails from contribution targets, cold outreach from people who found your PRs, or any signal that an open-source contribution attracted strategic attention.
Guides teams through IT outages and security incidents, providing structured workflows for detection, containment, eradication, and post-mortem analysis.
Designs interactive theatrical experiences with branching narratives, audience participation systems, and immersive environmental storytelling.
Generate sacred geometry patterns with interfaith symbolism for spiritual visualizations and art. Use when creating visual representations that honor multiple religious traditions, designing meditation aids, building soul journey visualizations, or producing art that bridges sacred traditions through geometric harmony. Triggers on sacred geometry requests, interfaith symbol design, spiritual visualization projects, or multi-tradition sacred art.
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Prepare for job interviews across formats—behavioral, technical, portfolio reviews, and negotiations. STAR/CAR frameworks for stories, common question patterns, research strategies, and follow-up templates. Triggers on interview prep, job interviews, behavioral questions, or salary negotiation requests.
Progressive context retrieval pattern for understanding unfamiliar codebases through iterative refinement
Design knowledge systems using ontological principles—organizing by what things ARE rather than arbitrary hierarchies. Use when structuring personal knowledge bases, designing documentation systems, creating cross-domain linking patterns, building the {OS.me} ecosystem, or architecting information that reveals rather than obscures essential nature. Triggers on knowledge management, documentation architecture, information ontology, or systematic organization of complex domains.