Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
extern-researcher
Research external open-source repositories to learn patterns and implementations.
This skill should be used when agents need to study external codebases, check for
existing research before cloning, manage temporary workspaces, and persist findings
to the global thoughts system. Triggers include: studying external repos, learning
from open source, cloning for pattern research, or checking what has been researched.
majiayu000/claude-skill-registry 163
-
skills-index-updater
Regenerate skill indexes for IDEs without native skill support (Kiro, Gemini, etc.). ONLY use when the user EXPLICITLY asks to "update skill index", "sync agents", "regenerate index", or "update AGENTS.md". Do NOT auto-invoke after creating/modifying skills - Claude Code has native skill support and does not need this.
majiayu000/claude-skill-registry 163
-
with-reference
Demonstrates loading an external note during execution.
majiayu000/claude-skill-registry 163
-
ace-pattern-learning
Search ACE playbook before implementing, building, fixing, debugging, or refactoring code. Capture patterns after completing substantial coding work.
majiayu000/claude-skill-registry 163
-
production-readiness
Harden code and pipelines for production. Use when the user asks for production-ready code, hardening, release readiness, performance, monitoring, or reliability.
majiayu000/claude-skill-registry 163
-
setting-up-distributed-tracing
Execute this skill automates the setup of distributed tracing for microservices. it helps developers implement end-to-end request visibility by configuring context propagation, span creation, trace collection, and analysis. use this skill when the user re... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
majiayu000/claude-skill-registry 163
-
history-analyzer
Analyze git history for hotspots, coupling, and knowledge distribution. Use when user asks "who knows this code", "what files change most", "hotspots", "bus factor", "knowledge silos", or needs to understand code evolution.
majiayu000/claude-skill-registry 163
-
Time Awareness
Provides current date/time information for temporal queries and calculations
majiayu000/claude-skill-registry 163
-
quality-metrics
Measure quality effectively with actionable metrics. Use when establishing quality dashboards, defining KPIs, or evaluating test effectiveness.
majiayu000/claude-skill-registry 163
-
swift-case-paths
A library for working with enum cases as first-class values, enabling key path-like access to enum cases
majiayu000/claude-skill-registry 163
-
ci-images
Work with this repo’s GitHub Actions CI and GHCR Docker image publishing workflow. Use when changing generation checks, tests, formatting, or when preparing a release and validating image tags.
majiayu000/claude-skill-registry 163
-
sitrep-coordinator
Military-style Situation Report (SITREP) generation for multi-agent coordination. Creates structured status updates with completed/in-progress/blocked sections, authorization codes, handoff protocols, and clear next actions. Optimized for complex project management across multiple AI agents and human operators.
majiayu000/claude-skill-registry 163
-
typescript-best-practices
Provides TypeScript patterns for type-first development, making illegal states unrepresentable, exhaustive handling, and runtime validation. Must use when reading or writing TypeScript/JavaScript files.
majiayu000/claude-skill-registry 163
-
webhook-push
Unified webhook messaging for WeCom, DingTalk, and Feishu platforms. Send notifications to enterprise communication platforms with a single interface.
majiayu000/claude-skill-registry 163
-
code-comment-guidelines
Code comment guidelines based on industry best practices. Use when reviewing code, writing new code, or when asked about comment quality. Applies to all languages but specializes in TypeScript/JavaScript. Enforces "JSDoc for public APIs only, no redundant comments" principle. Automatically suggests comment additions, removals, or refactoring alternatives.
majiayu000/claude-skill-registry 163
-
elm-development
Comprehensive Elm functional programming for web development including The Elm Architecture, type system, JavaScript interop, and production-ready patterns
majiayu000/claude-skill-registry 163
-
claude-code-patterns
Use when deciding whether to create a skill, command, or agent. Provides decision framework, templates, and best practices for Claude Code abstractions.
majiayu000/claude-skill-registry 163
-
git-workflow-strategy
Master Git workflows including GitFlow, GitHub Flow, Trunk-Based Development. Configure branches, merge strategies, and collaboration patterns for team environments.
majiayu000/claude-skill-registry 163
-
reduce-relie-basics
Run REDUCE in Docker for this repo (using lunacamp/reduce-algebra), load the vendored ReLie file from resources/relie-src/relie.red, and perform a tiny smoke test. Use when you need the canonical docker run command or a minimal ReLie bootstrap.
majiayu000/claude-skill-registry 163
-
woocommerce-backend-dev
Add or modify WooCommerce backend PHP code following project conventions. Use when creating new classes, methods, hooks, or modifying existing backend code. **MUST be invoked before writing any PHP unit tests.**
majiayu000/claude-skill-registry 163
-
app-store-deployment
Deploy iOS and Android apps to App Store and Google Play. Covers signing, versioning, build configuration, submission process, and release management.
majiayu000/claude-skill-registry 163
-
persona-pipeline
Generate AI agent personas with authentic backstories, demographics, and personality traits for TraitorSim. Use when creating new characters, generating personas, building character libraries, or when asked about persona generation, backstory creation, or character development. Orchestrates Deep Research + Claude synthesis pipeline.
majiayu000/claude-skill-registry 163
-
tm-definition-of-done
Enforce Tavern Master definition of done (lint + tests + formatting + plan updates).
majiayu000/claude-skill-registry 163
-
analyzer-architecture-review
analyzerアプリケーションのアーキテクチャレビュー。Port&Adapterアーキテクチャ（ヘキサゴナルアーキテクチャ）のルールに従っているかをチェックします。新しいPort/Adapter/Usecase/Model追加時、PRレビュー時、またはアーキテクチャ違反の検出が必要な時に使用します。Port層の関数型定義、依存関係の方向、New*関数パターン、レイヤー分離などを検証します。
majiayu000/claude-skill-registry 163