amhuppert
113 verified skills207 total stars
claude/ai-resources-plugin/skills/jog-users-memory
--- name: jog-users-memory description: Jog the user's memory after they've been away: a brief, scannable summary of progress, next steps, and open questions. disable-model-invocation: true allowed-tools: Read, Bash(git log:*), Bash(git status:*), Bash(git diff:*) --- # Context Refresh Quick memory jog for returning to work after being away. ## Instructions ### 1. Gather Context (parallel where possible) **From git:** - Run `git log --oneline -15` to see recent commits - Run `git status --
tools2
latex
Generate LaTeX documents (or convert markdown to LaTeX) with professional typography. Optionally compile to PDF.
development2
hotkey-helper
Use when picking or vetting a keyboard shortcut on macOS. Triggers include "what hotkey should I use for X", "is this combo available", "does this shortcut conflict", "recommend a keybinding", "check this combo against my setup", or any mention of choosing, binding, or changing a shortcut in WezTerm, tmux, Zed, Chrome, Claude Code, or macOS. Determines whether a proposed combo collides with OS-reserved bindings, app defaults, or the user's customizations, and recommends ergonomic alternatives when needed.
tools2
knip
Detect and remove dead code with knip. Use when the user asks to "run knip", "find unused files", "find unused exports", "find unused dependencies", "clean up dead code", "remove dead code", "set up knip", "configure knip", "knip.json", "knip false positive", "knip CI", or mentions a `knip` config, dependency bloat, bundle bloat from unused imports, or tree-shaking unused exports. Covers the configuration-first workflow, confidence-gated deletion, framework-specific gotchas (Next.js 15+, Tailwind, Storybook, Jest, Bun's test runner and `bun build --compile`), monorepos, CI integration, and performance tuning.
development2
nano-banana-prompt
Create a high-quality image generation prompt for Google's Nano Banana 2 (NB2) model on Gemini.
development2
optimize-tsconfig
Optimize tsconfig.json for build speed, watch mode, and tsc memory. Use for slow tsc, too many file watchers, or TypeScript performance audits.
development2
shama-init-config
Initialize Shama voice-to-text config for the project — create voice.json, voice-vocabulary.md, voice-context.md, and register the project in Shama's registry.toml.
data-ai2
transcript-path
Locate the on-disk Claude Code transcript file (.jsonl under ~/.claude/projects/) for the current or a specified conversation.
development2
investigate-web-perf
Trace-based triage of web performance issues via chrome-devtools-mcp: LCP/INP regressions, slow page loads and interactions, ForcedReflow/layout thrashing, CLS, bundle bloat, memory leaks. Captures Chrome performance traces and analyzes them with performance insights. Requires setup-perf-stack. For installing react-scan, component-level React render attribution (unnecessary re-renders, unstable props), or automated render checks with Playwright, use react-scan instead.
tools2
react-scan
Install and use react-scan tooling for component-level React render attribution: "set up react-scan", "diagnose React re-renders", "find unnecessary renders", "find unstable props", "measure component renders programmatically", or automated render checks with Playwright (react-scan + playwright, lite headless API for CI). Covers install across Next.js/Vite/Remix/script-tag/browser-extension and the render-attribution → fix → validate loop. For trace-based triage of LCP/INP regressions, ForcedReflow, bundle bloat, or memory leaks, use investigate-web-perf instead.
tools2
web-debugger
Debug a running web app via the web-debugger SDK: app logs, application state, runtime snapshots, React state, query cache.
development2
reflection
Reflect on the conversation and propose improvements to durable AI-agent instruction files such as CLAUDE.md and AGENTS.md.
data-ai2
understand-objective
Thoroughly understand a software development objective before implementation: research, identify ambiguities, ask clarifying questions. Use before starting implementation of a non-trivial or ambiguously specified feature, or when requirements leave open design decisions.
development2
save-current-context
Save current session context to a handoff file so a future AI agent can continue with no prior context.
data-ai2
steer
Reflect on codebase navigation effectiveness at end of conversation. Surfaces dead ends, inefficiencies, missing context. Does not write files — pair with /kiro:steering-custom to persist.
development2
shama-add-context
Add terms, context, or instructions to Shama voice-to-text files for clipboard mode (Ctrl+Opt+Space) or shell-command mode (Ctrl+Opt+S), at project or global level.
tools2
add-design-agent
Create a research or review agent for the /design workflow.
data-ai2
assess-project-context
Assess / rate the default project context (CLAUDE.md, onboarding). Scores how well it conveys the project to AI across six dimensions, with improvement recommendations.
data-ai2
setup-perf-stack
Bootstrap web performance debugging tooling: install chrome-devtools-mcp and related MCP servers/skills.
tools2
model-price-compare
Compare AI model prices across Anthropic, OpenAI, and Google. Generates pages-per-dollar / cost-per-token visualizations.
development2
hotkey-helper
Use when picking or vetting a keyboard shortcut on macOS. Triggers include "what hotkey should I use for X", "is this combo available", "does this shortcut conflict", "recommend a keybinding", "check this combo against my setup", or any mention of choosing, binding, or changing a shortcut in WezTerm, tmux, Zed, Chrome, Claude Code, or macOS. Determines whether a proposed combo collides with OS-reserved bindings, app defaults, or the user's customizations, and recommends ergonomic alternatives when needed.
tools2
agent-offloading
Covers the agent-offloading principle for AI-assisted development — offload everything deterministic (git operations, validation commands, iteration accounting, output parsing, message routing) from the agent onto code, and reserve the agent for judgment, language understanding, and code synthesis. Includes the division-of-labor table, decision heuristics, orchestrator-owned fields, and typed side channels for agent-produced artifacts. Use when designing an agent workflow or orchestration loop, deciding whether a check belongs in a script or a prompt, tempted to ask an agent to track its own iterations or decide when to halt, or when parsing structured data out of agent response text.
development2
cli-tools-for-agents
Design a purpose-built project CLI as the primary tool surface for AI coding agents, instead of in-process tool or MCP servers. Covers the exit-code taxonomy, structured errors, file-based payloads with a validate verb, job-shaped long operations, identity resolution, a doctor self-check, and build-parity stamps. Use when building a CLI for agents, migrating away from in-process tool servers, designing tool output and error contracts, or deciding how agents should invoke project actions.
tools2
earned-guidance-docs
Applies an evidence-earned discipline to agent-facing documentation — a durable rule is written down only after it has bitten, and historical rationale lives in a dated lessons log rather than in code comments. Also covers instruction architecture: a small tool-agnostic root contract plus read-on-demand reference docs treated as persistent project memory with a drift-sync lifecycle. Use when setting up AGENTS.md or CLAUDE.md, when an instruction file keeps growing, when starting a lessons file such as PERFORMANCE.md, when deciding whether a rule has earned a place in agent guidance, or when agents appear to ignore instructions because the document is full of speculative advice.
tools2
changes-tour-guide
Walk through recent code changes pedagogically: a two-phase markdown guide (overview, then detailed explanations) in dependency order.
development2
cheat-sheet
Create a 1-2 page cheat sheet / quick reference for a tool, language, or framework.
tools2
progressive-disclosure-tooling
Structure a CLI or tool surface as a progressive-disclosure graph where every subcommand's --help is a self-contained mini-skill, and derive every guidance surface from one typed registry so documentation drift becomes structurally impossible. Use when writing --help text, designing tool help systems, organizing command documentation for agents, or fighting drift between help text, parsers, and skill docs.
tools2
browser-automation
Automate browser interaction with Playwright: open pages, take screenshots, verify UI, test flows, debug pages, inspect elements.
tools2
create-plan
Create a decision-complete implementation plan that can be executed mechanically without further design decisions.
testing2
save-current-context
Save current session context to a handoff file so a future AI agent can continue with no prior context.
data-ai2
investigate-web-perf
Trace-based triage of web performance issues via chrome-devtools-mcp: LCP/INP regressions, slow page loads and interactions, ForcedReflow/layout thrashing, CLS, bundle bloat, memory leaks. Captures Chrome performance traces and analyzes them with performance insights. Requires setup-perf-stack. For installing react-scan, component-level React render attribution (unnecessary re-renders, unstable props), or automated render checks with Playwright, use react-scan instead.
tools2
cheat-sheet
Create a 1-2 page cheat sheet / quick reference for a tool, language, or framework.
tools2
knip
Detect and remove dead code with knip. Use when the user asks to "run knip", "find unused files", "find unused exports", "find unused dependencies", "clean up dead code", "remove dead code", "set up knip", "configure knip", "knip.json", "knip false positive", "knip CI", or mentions a `knip` config, dependency bloat, bundle bloat from unused imports, or tree-shaking unused exports. Covers the configuration-first workflow, confidence-gated deletion, framework-specific gotchas (Next.js 15+, Tailwind, Storybook, Jest, Bun's test runner and `bun build --compile`), monorepos, CI integration, and performance tuning.
development2
understand-objective
Thoroughly understand a software development objective before implementation: research, identify ambiguities, ask clarifying questions. Use before starting implementation of a non-trivial or ambiguously specified feature, or when requirements leave open design decisions.
development2
changes-tour-guide
Walk through recent code changes pedagogically: a two-phase markdown guide (overview, then detailed explanations) in dependency order.
development2
ai-validation-output
Configure AI-optimal validation: pre-commit hooks, CommandCenter.json, and low-noise linter/test/typecheck output for AI agents.
development2
browser-automation
Automate browser interaction with Playwright: open pages, take screenshots, verify UI, test flows, debug pages, inspect elements.
tools2
compress
Compress and optimize AI instructions to be clearer, more concise, and more efficient.
testing2
create-requirements
Create a PRD / product requirements document with app summary, design principles, and detailed requirements.
testing2
explainer-document
Write a concise explainer / learning document / beginner guide that teaches a topic to someone unfamiliar with it.
testing2
init-design-config
Initialize DESIGN-AGENTS.md config for the /design workflow, populated from project context.
data-ai2
ai-readable-tool-output
Covers configuring development tooling — linters, type checkers, test runners, formatters — so AI agents can consume their output efficiently: suppress success output, preserve every failure detail, strip colors, bail early, and truncate huge diffs. Includes tool-by-tool flags and config for ESLint, TypeScript, Vitest, Jest, and Prettier, the `:ai` package script convention, and a backend-neutral `AI_OUTPUT=1` switch. Use when an agent burns context on passing-test noise, when setting up pre-commit hooks or agent-invoked check commands, when asked to "make the test output quieter for the agent", or when configuring a project's lint/typecheck/test scripts for agent use.
tools2
logging-for-agent-debugging
Design structured logging that AI agents can actually debug from — a stable documented event vocabulary, ambient trace context, scoped routing with a global timeline, documented query gotchas, a bounded log-analysis CLI, and forensic per-run logs for long agent executions. Use when designing logging for a project agents will debug, when an agent cannot find what it needs in the logs, when building an agent-friendly log query or performance-analysis tool, or when adding observability to multi-step agent runs.
tools2
agent-feedback-tiers
Define a three-tier feedback vocabulary — hint, reminders, instruction — for steering agents from tool output, with strict tier contracts and an evidence-gated admission rule for reminders. Use when designing tool output that guides agents, adding hints or reminders to a CLI or tool, deciding where mid-flow guidance belongs, or reviewing whether guidance text is in the right tier.
tools2
agent-retrospectives
Run structured retrospectives on any agent setup — instructions (AGENTS.md, CLAUDE.md, system prompts), skills, slash commands, workflows, processes, and tooling — after real use, mining finished runs for durable improvements. Covers the quality → cost → speed review order, deterministic extraction before judgment, spot-checking agent self-reports, and routing every finding to a concrete owner. Use when asked for a "retrospective on how the agent did", "post-mortem on this run", "improve my CLAUDE.md from this session", "audit how the workflow performed", or after rolling out new instructions, skills, or tooling and wanting to know what to change.
tools2
mechanical-guardrails
Converts recurring "please don't" guidance into structural enforcement agents cannot drift past — deleting the foot-gun API, making illegal states unrepresentable in types, shrink-only ratchets, coverage assertions, checked-in budgets, declare-or-fail registries, derived artifacts, and round-trip contract tests. Use when agents keep reintroducing a pattern you documented against, when asking how to make a convention stick, when planning a migration off a legacy API, when a wrapping or registration convention has silently drifted, or when code review is the only thing standing between the codebase and a defect class.
development2
agent-structured-output
Covers how to get reliable machine-readable output from AI agents — separate the thinking turn from the formatting turn, keep schemas flat and bounded, offload substantive content to files and return a small manifest, inject orchestrator-owned fields after parsing, and validate the manifest and the referenced files at the boundary. Includes schema design do/don't lists, prompting rules, the failure model, layered extraction, and one bounded repair turn. Use when an agent's JSON response drives workflow state, when designing a response schema or JSON Schema/Zod contract for an agent, when structured output keeps failing validation, or when deciding what belongs in JSON versus in a generated file.
development2
live-system-verification
Verify features against the live running system — real user flows, real API and model calls, and durable backend state — before calling them done. Covers scratch-datastore isolation, evidence engineering with greppable markers, round-trip persistence checks, and the change classes that only break live. Use when asked to "verify it actually works", "test end to end", "confirm this works in the real app", or before declaring a feature complete on the strength of a green test suite.
development2
compress
Compress and optimize AI instructions to be clearer, more concise, and more efficient.
testing2
code-standards-review
Review a codebase for adherence to code standards. Uses specialized agents with progressive disclosure to determine which standards apply.
development2
compare-reports
Compare two reports written by different AI agents from the same prompt — score both across accuracy, prompt adherence, organization, readability, and usefulness, then produce a polished self-contained HTML comparison report that declares a winner. Use whenever the user wants to compare, judge, grade, rank, or pick between two AI-generated reports, answers, research outputs, or documents ("which of these is better?", "evaluate these two responses", "A/B test these reports", "grade these two drafts"), even if they don't mention HTML, scoring, or the word "report".
development2
design
Create or iterate on a software design via a multi-agent workflow with parallel research and review phases. Stores artifacts in memory-bank/planning/{name}/.
data-ai2
ai-validation-output
Configure AI-optimal validation: pre-commit hooks, CommandCenter.json, and low-noise linter/test/typecheck output for AI agents.
development2
configure-editor-schema
Wire an existing JSON Schema into VS Code, Cursor, and/or Zed so it provides validation and IntelliSense for matching JSON or YAML files.
development2
create-requirements
Create a PRD / product requirements document with app summary, design principles, and detailed requirements.
testing2
create-reference
Create or update an AI-optimized reference document for a tool, library, framework, or API via thorough research.
tools2
optimize-tsconfig
Optimize tsconfig.json for build speed, watch mode, and tsc memory. Use for slow tsc, too many file watchers, or TypeScript performance audits.
development2
assess-project-context
Assess / rate the default project context (CLAUDE.md, onboarding). Scores how well it conveys the project to AI across six dimensions, with improvement recommendations.
data-ai2
nano-banana-prompt
Create a high-quality image generation prompt for Google's Nano Banana 2 (NB2) model on Gemini.
development2
model-price-compare
Compare AI model prices across Anthropic, OpenAI, and Google. Generates pages-per-dollar / cost-per-token visualizations.
development2
latex
Generate LaTeX documents (or convert markdown to LaTeX) with professional typography. Optionally compile to PDF.
development2
changelog-review
Review the Claude Code changelog and summarize recent changes and their significance.
development2
shama-init-config
Initialize Shama voice-to-text config for the project — create voice.json, voice-vocabulary.md, voice-context.md, and register the project in Shama's registry.toml.
data-ai2
transcript-path
Locate the on-disk Claude Code transcript file (.jsonl under ~/.claude/projects/) for the current or a specified conversation.
development2
setup-perf-stack
Bootstrap web performance debugging tooling: install chrome-devtools-mcp and related MCP servers/skills.
tools2
shama-add-context
Add terms, context, or instructions to Shama voice-to-text files for clipboard mode (Ctrl+Opt+Space) or shell-command mode (Ctrl+Opt+S), at project or global level.
tools2
react-scan
Install and use react-scan tooling for component-level React render attribution: "set up react-scan", "diagnose React re-renders", "find unnecessary renders", "find unstable props", "measure component renders programmatically", or automated render checks with Playwright (react-scan + playwright, lite headless API for CI). Covers install across Next.js/Vite/Remix/script-tag/browser-extension and the render-attribution → fix → validate loop. For trace-based triage of LCP/INP regressions, ForcedReflow, bundle bloat, or memory leaks, use investigate-web-perf instead.
tools2
explainer-document
Write a concise explainer / learning document / beginner guide that teaches a topic to someone unfamiliar with it.
testing2
agent-offloading
Covers the agent-offloading principle for AI-assisted development — offload everything deterministic (git operations, validation commands, iteration accounting, output parsing, message routing) from the agent onto code, and reserve the agent for judgment, language understanding, and code synthesis. Includes the division-of-labor table, decision heuristics, orchestrator-owned fields, and typed side channels for agent-produced artifacts. Use when designing an agent workflow or orchestration loop, deciding whether a check belongs in a script or a prompt, tempted to ask an agent to track its own iterations or decide when to halt, or when parsing structured data out of agent response text.
development2
init-design-config
Initialize DESIGN-AGENTS.md config for the /design workflow, populated from project context.
data-ai2
logging-for-agent-debugging
Design structured logging that AI agents can actually debug from — a stable documented event vocabulary, ambient trace context, scoped routing with a global timeline, documented query gotchas, a bounded log-analysis CLI, and forensic per-run logs for long agent executions. Use when designing logging for a project agents will debug, when an agent cannot find what it needs in the logs, when building an agent-friendly log query or performance-analysis tool, or when adding observability to multi-step agent runs.
tools2
steer
Reflect on codebase navigation effectiveness at end of conversation. Surfaces dead ends, inefficiencies, missing context. Does not write files — pair with /kiro:steering-custom to persist.
development2
write-tests
Write automated tests. Guides test selection, mocking strategy, and writing tests that verify behavior over implementation.
testing2
agent-retrospectives
Run structured retrospectives on any agent setup — instructions (AGENTS.md, CLAUDE.md, system prompts), skills, slash commands, workflows, processes, and tooling — after real use, mining finished runs for durable improvements. Covers the quality → cost → speed review order, deterministic extraction before judgment, spot-checking agent self-reports, and routing every finding to a concrete owner. Use when asked for a "retrospective on how the agent did", "post-mortem on this run", "improve my CLAUDE.md from this session", "audit how the workflow performed", or after rolling out new instructions, skills, or tooling and wanting to know what to change.
tools2
agent-structured-output
Covers how to get reliable machine-readable output from AI agents — separate the thinking turn from the formatting turn, keep schemas flat and bounded, offload substantive content to files and return a small manifest, inject orchestrator-owned fields after parsing, and validate the manifest and the referenced files at the boundary. Includes schema design do/don't lists, prompting rules, the failure model, layered extraction, and one bounded repair turn. Use when an agent's JSON response drives workflow state, when designing a response schema or JSON Schema/Zod contract for an agent, when structured output keeps failing validation, or when deciding what belongs in JSON versus in a generated file.
development2
reflection
Reflect on the conversation and propose improvements to durable AI-agent instruction files such as CLAUDE.md and AGENTS.md.
data-ai2
live-system-verification
Verify features against the live running system — real user flows, real API and model calls, and durable backend state — before calling them done. Covers scratch-datastore isolation, evidence engineering with greppable markers, round-trip persistence checks, and the change classes that only break live. Use when asked to "verify it actually works", "test end to end", "confirm this works in the real app", or before declaring a feature complete on the strength of a green test suite.
development2
add-design-agent
Create a research or review agent for the /design workflow.
data-ai2
earned-guidance-docs
Applies an evidence-earned discipline to agent-facing documentation — a durable rule is written down only after it has bitten, and historical rationale lives in a dated lessons log rather than in code comments. Also covers instruction architecture: a small tool-agnostic root contract plus read-on-demand reference docs treated as persistent project memory with a drift-sync lifecycle. Use when setting up AGENTS.md or CLAUDE.md, when an instruction file keeps growing, when starting a lessons file such as PERFORMANCE.md, when deciding whether a rule has earned a place in agent guidance, or when agents appear to ignore instructions because the document is full of speculative advice.
tools2
web-debugger
Debug a running web app via the web-debugger SDK: app logs, application state, runtime snapshots, React state, query cache.
development2
cli-tools-for-agents
Design a purpose-built project CLI as the primary tool surface for AI coding agents, instead of in-process tool or MCP servers. Covers the exit-code taxonomy, structured errors, file-based payloads with a validate verb, job-shaped long operations, identity resolution, a doctor self-check, and build-parity stamps. Use when building a CLI for agents, migrating away from in-process tool servers, designing tool output and error contracts, or deciding how agents should invoke project actions.
tools2
create-plan
Create a decision-complete implementation plan that can be executed mechanically without further design decisions.
testing2
progressive-disclosure-tooling
Structure a CLI or tool surface as a progressive-disclosure graph where every subcommand's --help is a self-contained mini-skill, and derive every guidance surface from one typed registry so documentation drift becomes structurally impossible. Use when writing --help text, designing tool help systems, organizing command documentation for agents, or fighting drift between help text, parsers, and skill docs.
tools2
agent-feedback-tiers
Define a three-tier feedback vocabulary — hint, reminders, instruction — for steering agents from tool output, with strict tier contracts and an evidence-gated admission rule for reminders. Use when designing tool output that guides agents, adding hints or reminders to a CLI or tool, deciding where mid-flow guidance belongs, or reviewing whether guidance text is in the right tier.
tools2
ai-readable-tool-output
Covers configuring development tooling — linters, type checkers, test runners, formatters — so AI agents can consume their output efficiently: suppress success output, preserve every failure detail, strip colors, bail early, and truncate huge diffs. Includes tool-by-tool flags and config for ESLint, TypeScript, Vitest, Jest, and Prettier, the `:ai` package script convention, and a backend-neutral `AI_OUTPUT=1` switch. Use when an agent burns context on passing-test noise, when setting up pre-commit hooks or agent-invoked check commands, when asked to "make the test output quieter for the agent", or when configuring a project's lint/typecheck/test scripts for agent use.
tools2
configure-editor-schema
Wire an existing JSON Schema into VS Code, Cursor, and/or Zed so it provides validation and IntelliSense for matching JSON or YAML files.
development2
compare-reports
Compare two reports written by different AI agents from the same prompt — score both across accuracy, prompt adherence, organization, readability, and usefulness, then produce a polished self-contained HTML comparison report that declares a winner. Use whenever the user wants to compare, judge, grade, rank, or pick between two AI-generated reports, answers, research outputs, or documents ("which of these is better?", "evaluate these two responses", "A/B test these reports", "grade these two drafts"), even if they don't mention HTML, scoring, or the word "report".
development2
mechanical-guardrails
Converts recurring "please don't" guidance into structural enforcement agents cannot drift past — deleting the foot-gun API, making illegal states unrepresentable in types, shrink-only ratchets, coverage assertions, checked-in budgets, declare-or-fail registries, derived artifacts, and round-trip contract tests. Use when agents keep reintroducing a pattern you documented against, when asking how to make a convention stick, when planning a migration off a legacy API, when a wrapping or registration convention has silently drifted, or when code review is the only thing standing between the codebase and a defect class.
development2
code-standards-review
Review a codebase for adherence to code standards. Uses specialized agents with progressive disclosure to determine which standards apply.
development2
fix-merge-conflicts
Resolve git merge conflicts. Use when git status shows unmerged paths or files contain standard Git conflict markers.
data-ai2
changelog-review
Review the Claude Code changelog and summarize recent changes and their significance.
development2
design
Create or iterate on a software design via a multi-agent workflow with parallel research and review phases. Stores artifacts in memory-bank/planning/{name}/.
data-ai2
create-reference
Create or update an AI-optimized reference document for a tool, library, framework, or API via thorough research.
tools2
fix-merge-conflicts
Resolve git merge conflicts. Use when git status shows unmerged paths or files contain standard Git conflict markers.
data-ai2
cursor-rules-synchronizer
Synchronizes Cursor Rules (.mdc files in .cursor/rules/) to CLAUDE.md by generating a Rules section with context-efficient descriptions and usage instructions. Use when setting up Cursor Rules for the first time, after adding or modifying rules, or when the Rules section in CLAUDE.md is missing or outdated.
testing1
config-audit
This skill should be used when auditing or comparing Claude Code and Cursor IDE configurations to identify feature gaps, equivalencies, and migration opportunities. Useful when managing AI development tooling across both platforms or deciding how to structure AI workflows.
tools1
knowledge-base-ingest
This skill should be used when integrating source material into a knowledge base, including when the user asks to "integrate this document into the knowledge base", "add this transcript to the memory bank", "ingest this document", "update the knowledge base", "analyze a new source document", or "sync current-state docs with this source".
documentation1
analyze-ralph-logs
This skill should be used when analyzing Ralph Loop workflow executions to diagnose failures, understand execution flow, or review what happened during the most recent run. Use when the user says "analyze ralph logs", "what happened with ralph", "ralph stopped", "ralph failed", "debug ralph", or wants to understand why a Ralph Loop execution ended unexpectedly.
development1
benchmark-chicken-svg
Model comparison benchmark for generating an SVG image.
data-ai1
configure-ralph
This skill should be used when the user wants to configure ralph-claude-code for a new objective. It updates .ralph/PROMPT.md and .ralph/fix_plan.md files in projects that already have Ralph enabled. Use when the user says "configure ralph", "set up ralph for", "update ralph for a new objective", or wants to start a new development objective with Ralph.
development1
local-commit
This skill should be used when the user wants to commit changes to the local private repository using lgit. It manages versioning of private AI configuration files.
data-ai1
local-init
This skill should be used when the user wants to initialize a new local private repository in the current directory. This sets up the .local directory for versioning private AI configuration files separately from the main repository.
data-ai1
sdd-to-ralph
This skill should be used when the user wants to convert completed CCSDD specs into Ralph execution artifacts. Use when user says "bridge spec to ralph", "convert sdd to ralph", "sdd to ralph", "generate ralph from spec", "prepare spec for ralph", or wants to take a cc-sdd feature spec and run it through Ralph for autonomous implementation.
tools1
break-into-subtasks
Break frontend feature requirements into parallelizable subtasks (API, UI, integration) with dependencies and a Mermaid diagram.
development1
commit
Commit staged git changes after generating and approving a message.
tools1
approve
Approve and execute a previously created implementation plan with no deviation.
development1
create-plan-anthropic
Create a decision-complete implementation plan that can be executed mechanically without further design decisions.
testing1
claude/ai-resources-plugin/skills/understand-objective-anthropic
--- name: understand-objective-anthropic description: Thoroughly understand a software development objective before implementation: research, identify ambiguities, ask clarifying questions. --- # Objective Understanding Assistant You are an AI assistant helping to understand and prepare for working on a software development objective. Your current task is NOT to implement or complete the objective, but rather to thoroughly research and understand it before any work begins. You will be provide
tools1
worktree
Create a git worktree for parallel Claude Code sessions.
development1
claude/ai-resources-plugin/skills/kb-ingest
--- name: kb-ingest description: Delegate knowledge-base ingestion to the `knowledge-base-ingester` sub-agent so the source document, primary/current trees, and ingest workflow stay out of the main conversation's context window. Run this when the user explicitly invokes `/ai-resources:kb-ingest`; do not auto-trigger from natural-language ingestion requests (those should use the `knowledge-base-ingest` skill directly). disable-agent disable-model-invocation: true --- # kb-ingest Run a knowledge
tools1
cursor-rules
This skill should be used when creating or editing Cursor rules files (.mdc format) in the .cursor/rules directory. Provides guidance on rule types, frontmatter configuration, effective rule writing patterns, and best practices for structuring AI instructions for Cursor IDE.
development1
claude/ai-resources-plugin/skills/init-voice-config
--- name: init-voice-config description: Initialize voice-to-text config for the project: voice.json, voice-vocabulary.md, voice-context.md. disable-model-invocation: true allowed-tools: Read, Glob, Grep, Write(voice.json), Write(voice-context.md), Write(voice-vocabulary.md), Agent --- # Initialize Voice-to-Text Project Config Create a local `voice.json` config, a `voice-vocabulary.md` vocabulary file, and a `voice-context.md` context file in the current directory. These cover the **clipboard
tools1
add-voice-context
Add terms, context, or instructions to voice-to-text files for clipboard/file mode (F9/F10) or shell-command mode (F8), at project or global level.
tools1