Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
gitwhat
Concise git workspace snapshot for the current directory. Use when asked to show current branch, cwd, repo root, whether the current directory is a worktree, local dirty status, or whether other worktrees have uncommitted changes.
majiayu000/claude-skill-registry 163
-
conversation-archaeologist
Mine ALL past Claude conversations to build a living 'User Manual About You'. Extract writing style, business context, goals, preferences, and patterns. Make all other skills smarter with context.
majiayu000/claude-skill-registry 163
-
jhack
Expert assistant for Juju charm development using jhack utilities. Use when debugging charms, inspecting relations, syncing code, replaying events, testing scenarios, or performing rapid development iterations. Keywords include jhack, Juju debugging, charm testing, relation inspection, event replay, sync, tail, fire, show-relation, show-stored.
majiayu000/claude-skill-registry 163
-
vercel-debug
Investigate Vercel deployment errors using Vercel CLI. Use when user shares a Vercel deployment error, build failure, or deployment URL that needs debugging.
majiayu000/claude-skill-registry 163
-
TypeScript SDK Reference
Comprehensive reference for the TypeScript Agent SDK with functions, types, and interfaces for programmatic Claude Code interactions
majiayu000/claude-skill-registry 163
-
api-credentials
Securely manages API credentials for multiple providers (Anthropic Claude, Google Gemini, GitHub). Use when skills need to access stored API keys for external service invocations.
majiayu000/claude-skill-registry 163
-
system-init
Initialize or hydrate the agent's memory system and verify configuration.
majiayu000/claude-skill-registry 163
-
antlr4-dev
ANTLR4前端开发专家，专注于词法/语法分析、AST构建、访问者模式实现。
majiayu000/claude-skill-registry 163
-
ios-build-workflow
iOS/Swift/Xcodeのビルド・テスト・実行ワークフロー。「iOSビルド」「Xcodeエラー」「コンパイル」「シミュレーター」「swift build」「xcodebuild」などのキーワードで自動適用。
majiayu000/claude-skill-registry 163
-
modern-rationalism-empiricism
Master Early Modern philosophy from Descartes through Kant. Use for: rationalism, empiricism, the epistemological turn, mind-body problem, substance metaphysics. Triggers: 'Cartesian', 'cogito', 'Descartes', 'Spinoza', 'Leibniz', 'Locke', 'Berkeley', 'Hume', 'tabula rasa', 'innate ideas', 'impressions ideas', 'monads', 'substance', 'causation', 'personal identity', 'transcendental', 'synthetic a priori', 'Kant', 'categories', 'thing-in-itself', 'noumenon', 'phenomenon'.
majiayu000/claude-skill-registry 163
-
mini-app-review
デプロイ済みアプリの作成者レビューを実施する。「レビュー」「改善」「ブラッシュアップ」を依頼されたときに使用する。
majiayu000/claude-skill-registry 163
-
executive-briefing-kit
Framework for packaging competitive updates into executive-ready narratives and action plans.
majiayu000/claude-skill-registry 163
-
Git Workflow Patterns
Conventional commits, PR practices, branching strategies
majiayu000/claude-skill-registry 163
-
python-analyzer
Format and analyze Python code using ruff (formatting/linting) and ty (static type checking). Use when the user asks to format Python code, run linting, check types, fix code style issues, or analyze Python code quality.
majiayu000/claude-skill-registry 163
-
backtracking-patterns
Master backtracking technique with permutations, combinations, and puzzle solving patterns with production-ready implementations.
majiayu000/claude-skill-registry 163
-
detecting-suspicious-assert
Detects suspicious use of assertions for security checks that can be disabled in production builds. Use when analyzing assertion usage, security checks, or investigating assert-related vulnerabilities.
majiayu000/claude-skill-registry 163
-
looper-live-test
Run a live Looper smoke test by creating a temporary project (PROJECT.md + to-do.json), executing looper for one iteration, observing output, and reporting results. Use when verifying looper behavior or demonstrating a live run.
majiayu000/claude-skill-registry 163
-
cli-helper
Use this skill when the user asks about CLI tool options, parameters, or flags. Activate when queries mention command-line tools, --help output, CLI documentation, or organizing tool parameters into levels. Helps parse and structure CLI help documentation into Basic, Medium, and Advanced complexity levels.
majiayu000/claude-skill-registry 163
-
unified-search-discover
Progressive search and discovery with structured refinement workflows for file finding, content searching, and safe refactoring operations using fd/find, rg/grep, and ast-grep tools. Use when searching, discovering, or refactoring code with progressive refinement patterns.
majiayu000/claude-skill-registry 163
-
story-coach
Act as an assistive writing coach who guides but never writes for the user. Use when helping someone develop their own writing through questions, diagnosis, and frameworks. Critical constraint - never generate story prose, dialogue, or narrative content. Instead ask questions, identify issues, suggest approaches, and let the writer write.
majiayu000/claude-skill-registry 163
-
golang-style
Use this skill BEFORE writing or editing any Go (.go) files. Triggers when about to create, modify, or add code to .go files. Enforces happy path coding, error wrapping, sentinel errors, and godoc-style comments.
majiayu000/claude-skill-registry 163
-
react-component
Create React components with TypeScript, following best practices for hooks, state management, accessibility, and testing. Use when building new UI components or refactoring existing ones.
majiayu000/claude-skill-registry 163
-
market-sizing-analysis
This skill should be used when the user asks to "calculate TAM", "determine SAM", "estimate SOM", "size the market", "calculate market opportunity", "what's the total addressable market", or requests market sizing analysis for a startup or business opportunity.
majiayu000/claude-skill-registry 163
-
maintain-environment
Maintain the repo devcontainer environment and related workflow files. Use when changing .devcontainer or environment setup scripts.
majiayu000/claude-skill-registry 163