
Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.
Deep multi-agent code review for local changes. Inspired by AmpCode's agentic review. Use when you want comprehensive analysis of staged changes, unstaged changes, specific commits, or branch differences. Spawns parallel specialized agents (security, performance, patterns, architecture) and synthesizes actionable findings with priority levels. Can implement fixes directly.
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.
Generate architecture diagrams as .excalidraw files from codebase analysis. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, or generate excalidraw files.
Google Drive CLI for listing, searching, uploading, downloading, and sharing files and folders.
Reverse engineer Grainrad (grainrad.com) and recreate its UI/UX, panels, effect list, presets, settings, and export options in a new web app. Also use this skill to apply Grainrad-style effects (ASCII, dithering, halftone, etc.) locally to images, GIFs, or videos without using the Grainrad website or browser UI.
Prepare for and conduct Jobs-to-be-Done interviews to understand tool/workflow adoption decisions. Use when planning JTBD interviews, creating interview guides, or conducting adoption research at DreamWorks Animation or similar organizations. Focuses on reconstructing real adoption episodes using the four forces framework.
Management coach channeling Julie Zhuo's philosophy from "The Making of a Manager". Use for self-coaching on management challenges, improving 1:1s, giving feedback, building trust, or navigating difficult conversations. Combines warmth with practical wisdom.
Auto-triggered when working with launchd agents, plist files, or background automation on macOS. Proactively checks for common pitfalls and applies learned patterns to prevent issues before they occur.
Search files using macOS Spotlight index via mdfind CLI. This skill should be used when searching for files by content, filename, or metadata across the filesystem. Faster than grep for broad content searches since Spotlight pre-indexes everything. Triggers include "find files containing", "search for documents", "locate files", "spotlight search", or any broad file search that would benefit from indexed search.
Convert JTBD insights and qualitative research into ODI (Outcome-Driven Innovation) desired outcome statements with proper syntax. Use when translating pain points, desires, or job steps into measurable, solution-agnostic outcome statements for prioritization and validation.
Generate a PRD with user clarification questions (interactive). Use when you want to ask the user clarifying questions before creating the PRD. Triggers on: /prd-ralph, create prd with questions.
Guide organizational transformation from feature factories to product-led companies. Use when helping teams adopt product-led practices, change management for product culture, or bridging executive strategy with product execution.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Convert a PRD markdown file to prd.json for execution. Triggers on: convert prd, create tasks, prd to json, generate tasks from prd.
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
Orchestrate high-quality visual asset creation by routing requests to the appropriate specialized skill (frontend-design, canvas-design, nano-banana-pro) and capturing output with screenshot when needed. Use when the user asks to create visual assets, image assets, mockups, posters, illustrations, diagrams, UI designs, or any visual deliverable. This skill routes to the best underlying tool rather than reimplementing capabilities.
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Web search and content extraction using Brave Search. Use when researching topics, finding documentation, extracting article content, or gathering information from the web. No browser required - works headlessly.
Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.
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.
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.
Best practices for Remotion - Video creation in React
Synthesize multiple research sources into strategic insights with value-risk prioritization framework. Use when planning product roadmaps, evaluating competing opportunities, or making high-stakes decisions with limited resources.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Manage Claude Code's ambient awareness system. Use when the user wants to add context events, check pending events, manage the filesystem watcher, troubleshoot the ambient system, or integrate external event sources. Triggers on "ambient", "event queue", "what happened while I was away", "context events", or "watcher status".
# Beautiful Mermaid Skill Render Mermaid diagrams as beautiful SVGs or ASCII art. Ultra-fast, fully themeable, zero DOM dependencies. ## Triggers Use this skill when: - Creating any diagram, flowchart, or visualization - Explaining architecture, workflows, or data flows visually - User asks to "draw", "diagram", "visualize", or "show me" a process - Documenting system designs, state machines, or entity relationships - Adding diagrams to documentation, PRDs, or technical specs - Need ASCII dia
Captures before/after screenshots of web pages or elements for visual comparison. Use when user says "take before and after", "screenshot comparison", "visual diff", "PR screenshots", "compare old and new", or needs to document UI changes. Accepts two URLs (file://, http://, https://) or two image paths.
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.
Transform verbose, lengthy documents into clear, concise, actionable communications using proven frameworks (BLUF, Minto Pyramid, SCR). Use when stakeholders aren't reading lengthy docs or when critical messages get lost in detail.
Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a new skill, or asks about skill structure, best practices, or SKILL.md format.
Create custom subagents for specialized AI tasks. Use when the user wants to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.
Expert product/data analyst for DWA's product suite (Lasso, Rico, Courier, Shoppe). This skill should be used when analyzing Datadog metrics, querying RUM data, generating analytics reports, or interpreting product performance. Triggers include "how is Lasso doing", "show me metrics for Courier", "analyze search latency", "generate weekly report", "are there any special variation signals", or any request involving Datadog data for DWA products.
Maintain project continuity by organizing research insights and generating structured documentation. Use proactively when organizing research findings, updating handoff documents, or creating comprehensive project documentation with consistent structure.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
Remove signs of AI-generated writing from text. Quick-pass tool for detecting and fixing AI patterns while adding authentic voice. For the full pattern catalog, see ~/.claude/skills/writing-editor/references/AI_TELLS.md
JTBD-first critique framework. Use when asked to "critique this UI", "review my interface", "what's wrong with this design", or "teardown this screen".
Design PDSA (Plan-Do-Study-Act) experiments to test JTBD/ODI hypotheses about adoption, measure outcome movement, and iterate based on results. Use when converting insights into testable interventions for Weekly Business Review (WBR) tracking.
Write high-converting landing page copy using proven frameworks like PAS (Problem-Agitate-Solution), AIDA, and StoryBrand. Creates headlines, value propositions, CTAs, and full page sections optimized for conversion. Use when users need landing page copy, sales page content, or marketing website text.
Control macOS through AppleScript and JavaScript for Automation (JXA) via the macos_automator MCP server. This skill should be used when the user asks to automate Mac applications, control system settings, interact with UI elements, get clipboard contents, manage windows, control media apps, or perform any macOS automation task. Triggers on requests like "open Safari", "get clipboard", "control Spotify", "take a screenshot", "list running apps", or "click that button".
Apple Human Interface Guidelines for Mac. Use when building macOS apps with SwiftUI or AppKit, implementing menu bars, toolbars, window management, or keyboard shortcuts. Triggers on tasks involving Mac UI, desktop apps, or Mac Catalyst.
Expert in macOS app development using AppKit, SwiftUI for Mac, and XPC. Specializes in system extensions, menu bar apps, and deep OS integration.
Apply Silicon Valley Product Group (SVPG) principles for building empowered product teams and strong products. Use for product leadership coaching, strategic product guidance, or transforming from feature factory to outcome-driven product organization.
Troubleshoot MCP server connection issues, re-authenticate Gmail MCP, and manage server configurations. This skill should be used when MCP tools fail, servers won't connect, Gmail MCP needs re-authentication, or managing MCP server settings. Triggers on "MCP not working", "Gmail MCP", "MCP error", "server won't connect", or "re-authenticate MCP".
Query and manage Claude's pattern memory store. Use when the user asks about patterns, wants to search memory, check what rules are active, add observations manually, check memory decay, or debug the memory system. Triggers on "memory", "patterns", "what have you learned", "rules", "claude-memory", "memory stats", or "decay".
Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when the user wants to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.
Create clean, technical ASCII-art diagrams in Monodraw-inspired style for system architectures, workflow processes, system maps, and service blueprints. Use when the user asks to visually explain something, create a diagram, visualize a system, or illustrate technical concepts. Produces monospaced, line-drawn diagrams with boxes, arrows, and dotted shading for clear technical documentation.
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
Execute Teresa Torres' systematic 7-step methodology to extract evidence-based opportunities from stakeholder interviews. Use when analyzing interview transcripts to identify product opportunities with proper source citations.
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.
Invoke Peekaboo-powered autonomous agents for visual GUI tasks. This skill should be used when the task requires visual understanding, GUI automation, design QA comparison, UI testing, or user research recording. Triggers on requests like "compare this design to the implementation", "test this UI flow", "automate clicking through this app", or "record this user session".
Contextual PM toolkit advisor that helps you pick the right product management tools for your current situation and customizes guidance to your specific scenario. Use when facing a PM challenge, starting a new phase, or unsure which framework to apply.
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
Coach product managers and leaders using Marty Cagan's frameworks from Empowered and Transformed. Use when helping someone develop product skills, reviewing discovery work, teaching evidence-based methods, or guiding organizational transformation from feature factory to product operating model.
Define product metrics frameworks (HEART, AARRR), create measurement plans, and quantify product improvements. Use when establishing success metrics, measuring feature impact, or building data-informed product culture.
Guide commercialization strategy, market positioning, competitive analysis, and go-to-market planning. Use when developing product strategy, entering new markets, or making strategic product decisions with business model implications.
Expert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts, review or improve existing prompts, optimize AI instructions, or create any form of written communication intended for AI consumption (Claude, GPT, or other LLMs).
Bi-directional AI writing assistant via MCP. This skill should be used when: - User wants to annotate a document with inline feedback - User says "annotate", "mark up", "review", or "add comments" to a document - User needs to revise a document based on Quill annotations - User wants to export annotations to ~/.quill/document.json - User mentions "quill" in relation to document editing - Agent receives quill_* MCP tool results Works with Quill macOS app, quill-tui (terminal), and quill-web via shared ~/.quill/ directory. MCP integration enables agents to read, respond to, and resolve annotations without API keys.
Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.
Best practices for Remotion - Video creation in React
Apply Teresa Torres' Continuous Discovery framework and user research methodologies. Design interview protocols, conduct discovery research, and synthesize insights to inform product decisions. Use when planning research studies or conducting stakeholder/user interviews.
Three-phase research interview system based on Anthropic Interviewer methodology. Conducts structured qualitative interviews with explicit planning, adaptive interviewing, and synthesis. Supports single interviews and multi-interview series with thematic analysis. Use when you need Claude to interview you (or guide an interview with someone else) to extract insights, stories, and knowledge on any topic.
Universal screenshot tool for capturing web pages, desktop apps, and images. Supports viewport presets (mobile/tablet/desktop), CSS selectors, batch capture, auto-upload to image hosts, and markdown output for PRs. Use when user says "take a screenshot", "screenshot this", "capture the page", "screenshot of [app/url]", "batch screenshots", "all viewports", or "upload screenshot".
Analyze stakeholder psychology, communication strategies, and influence tactics. Use when preparing for important stakeholder meetings, crafting strategic communications, or addressing resistance to change.
Expert in the Swift ecosystem, specializing in iOS/macOS/visionOS development, Swift 6 concurrency, and deep system integration.
Tailwind CSS utility-first framework for rapid UI development with responsive design and dark mode
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
TUI dashboard for monitoring tmux sessions, useful for long-running agent tasks. This skill should be used when monitoring background processes, viewing tmux session output, or managing multiple terminal sessions. Triggers on "tmux sessions", "monitor background", "session dashboard", or "tmuxwatch".
Expert coach for learning, mastering, and upskilling in any domain. Use when the user wants to learn, master, improve, upskill, get better at, or get coached on any topic. Helps build consistent practice habits, identify prerequisites, design efficient learning loops, avoid common pitfalls, maintain discipline, and measure progress. Based on evidence-based principles from "Advice on Upskilling" by Justin Skycak.
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture.
Fetch transcripts from YouTube videos for summarization and analysis.
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
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.
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).
Speech-to-text transcription using Groq Whisper API. Supports m4a, mp3, wav, ogg, flac, webm.
Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.
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.
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.
Add Agentation visual feedback toolbar to a Next.js project
Create and run autonomous agents using the Anthropic Agent SDK. Use when the user wants to build custom AI agents, automate workflows with Claude's capabilities, or execute complex multi-step tasks programmatically.
Guide for designing effective tools for AI agents. Use when creating tools for custom agent systems or any AI tool interfaces. Provides principles for tool naming, input/output design, error handling, and evaluation methodologies that maximize agent effectiveness.
Analyze Beads issue tracker graphs for planning, prioritization, and execution insights. Use when the user asks about tasks, priorities, what to work on next, project planning, or mentions Beads issues. Provides graph-theoretic analysis (PageRank, critical path, bottlenecks) for intelligent prioritization.
Manage calendar events via Apple Calendar (source of truth). Use when the user wants to check their calendar, schedule interviews, create events, find free time, or manage their schedule. Includes both DreamWorks and personal calendars.
Search across all agent conversation history (Claude Code, Codex, Cursor, Gemini, Aider, ChatGPT). This skill should be used when looking for previous solutions, checking if a problem was solved before, or searching agent history. Triggers on "search history", "have I solved this before", "previous conversations", or "agent history".
Self-improving product system that reads daily reports, identifies the #1 priority, creates PRD + tasks, and autonomously implements fixes. Runs directly in your current session (no subprocess spawning). Use when you have a report and want autonomous implementation, or for overnight automation. Triggers on: compound product, auto-compound, self-improving, autonomous improvement, report to PR, run compound on, compound loop.
Create Cursor rules for persistent AI guidance. Use when the user wants to create a rule, add coding standards, set up project conventions, configure file-specific patterns, create RULE.md files, or asks about .cursor/rules/ or AGENTS.md.
Comprehensive EA/PM for daily planning, weekly reviews, calendar/task/email management, and strategic life coordination. Use proactively for morning planning, evening reflection, weekly reviews, synthesis checks, and cross-domain integration.
Rigorously verify claims, cross-reference sources, and investigate discrepancies in documents. Use before publishing research reports, when conflicting information exists, or when stakes are high and accuracy is critical.
Analyze user feedback from multiple sources (reviews, support tickets, interviews), identify patterns, and synthesize actionable insights for product prioritization. Use when customer feedback is scattered across channels and needs systematic analysis.
Framer Motion performance optimization guidelines. This skill should be used when writing, reviewing, or refactoring React animations with Framer Motion to ensure optimal performance patterns. Triggers on tasks involving motion components, animations, gestures, layout transitions, scroll-linked effects, and SVG animations.
Google Calendar CLI (BACKUP). Primary calendar access is via Apple Calendar (osascript). Use gccli only for direct Google API operations not available through Apple Calendar.
Gmail CLI for searching emails, reading threads, sending messages, managing drafts, and handling labels/attachments.
Comprehensive career strategist for finding, vetting, and landing opportunities. Implements CMF scoring, goHunt research methodology, Lane→Story→Spearfishing framework, and VALUE-FIRST cover letters.
Analyze JTBD interview transcripts to extract four forces, identify patterns, and synthesize insights. Use when processing interview recordings, transcripts, or notes to understand adoption causality and prepare actionable findings.
Manage Linear issues, projects, and teams. Use when the user mentions Linear, wants to create/view/update issues, check project status, or manage their Linear workflow. Provides comprehensive Linear API access through the @linear/sdk.
Discover, inspect, and call MCP servers directly from CLI without needing Claude. This skill should be used when listing available MCP tools, calling MCP tools directly, viewing tool schemas, or generating standalone CLIs from MCP servers. Triggers on "list MCP", "call MCP tool", "MCP schema", or "generate CLI from MCP".
Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.
Control the user own Chrome browser via Playwriter extension with Playwright code snippets in a stateful local js sandbox via playwriter cli. Automate web interactions, take screenshots, inspect accessibility trees, debug & profile web applications. Run `playwriter skill` command to read the complete up to date skill
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
Autonomous coding using Ralph Wiggum loops - a method for running fresh Claude instances per iteration to avoid context rot. Use when the user wants to implement features autonomously, mentions 'ralph', 'autonomous coding', 'run overnight', or wants to build something without supervision. Triggers on: use ralph, ralph loop, autonomous coding, implement this overnight, build X with ralph, help me create a spec for ralph.
For any task, read this skill first. Multi-AI gateway for fullstack apps. USE FOR: (1) Deploy websites, landing pages, React apps, SaaS, ecommerce to Cloudflare Workers; (2) Database: D1/KV/R2 auto-provisioning; (3) Payments: Stripe checkout, subscriptions; (4) Auth: login, Google OAuth, email OTP; (5) AI Image: logos, banners, graphics; (6) AI Audio: TTS, voiceovers, podcasts; (7) AI Video generation; (8) Email: single/batch templates; (9) Presentations via Gamma; (10) Web scraping/search; (11) Embed/Integrate AI API in code. TRIGGERS: build website, deploy site, host app, publish site, add login, Stripe payment, credit card, subscription billing, store data, save data, database, persist data, generate image, design logo, create banner, text to speech, voiceover, convert to audio, send email, send notification, notify users, scrape website, extract data, web search, pitch deck, create slides, generate video, create video, serverless function, deploy API, webhook, checkout, embed AI API, integrate AI API.
Build agent-grade CLI tools using Peter Steinberger's proven patterns. Covers CLI-first architecture, MCP integration, crash-resilient wrappers, multi-provider AI, session management, and distribution. Use when creating CLI tools, MCP servers, or AI-integrated automation tools.
Craft compelling product narratives using Andy Raskin's 5-act strategic narrative and Nancy Duarte's presentation frameworks. Use when creating stakeholder buy-in pitches, executive presentations, product positioning, or persuasive proposals. Triggers on "pitch", "presentation", "narrative", "stakeholder buy-in", "executive deck", or "tell the story of".
Apply systems thinking frameworks to understand complex problems, identify leverage points, and design sustainable interventions. Use when facing recurring issues, unintended consequences, or problems where obvious solutions keep failing.
Extract frames, audio, and transcripts from video files and generate a manifest for AI analysis. Use when the user mentions video analysis, mp4/mov files, screen recordings, interview recordings, transcription, or needs to make large videos manageable for Claude/Gemini.
Modify Cursor/VSCode user settings in settings.json. Use when the user wants to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.
Cognitive engagement coach based on "Think First, AI Second" principles. This skill should be used when the user asks strategic, architectural, or high-stakes questions, OR when they explicitly request challenge/critique (e.g., "poke holes", "devil's advocate", "challenge this"). Promotes active thinking over passive AI consumption.
Design UX validation methodologies, research protocols, and test planning to validate assumptions before building. Use when planning validation studies, designing experiments, or testing risky product assumptions.
This skill should be used when reviewing or editing written drafts to ensure they match Sam's personal style guide. It prioritizes voice preservation and anti-beige detection while catching structural gaps. Triggers on requests to review, edit, or improve written content.
Deploy applications and websites to Vercel using the bundled `scripts/deploy.sh` claimable-preview flow. Use when the user asks to deploy to Vercel, wants a preview URL, or says to push a project live on Vercel.
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.
Creates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually through controls, see a live preview, and copy out a prompt. Use when the user asks to make a playground, explorer, or interactive tool for a topic.
Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) using Python (`openpyxl`, `pandas`), especially when formulas, references, and formatting need to be preserved and verified.