Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
claude-typescript-sdk
Build AI applications with the Anthropic TypeScript SDK. Use when creating Claude integrations, building agents, implementing tool use, streaming responses, or working with the @anthropic-ai/sdk package.
majiayu000/claude-skill-registry 163
-
guide-yamadashy-repomix
majiayu000/claude-skill-registry 163
-
verify-before-committing
Use when about to create a git commit in this project
majiayu000/claude-skill-registry 163
-
claude-skillkit
Professional skill creation with research-driven workflow and automated validation.
USE WHEN: Creating new skills, validating existing skills, deciding between Skills vs Subagents, migrating documents to skills, or running individual validation tools.
PRIMARY TRIGGERS: "create skill" = Full creation (12 steps with research + execution planning) "validate skill" = Validation workflow (steps 3-8) "Skills vs Subagents" = Decision workflow (step 0) "convert doc to skill" = Migration workflow "estimate tokens" = Token optimization "security scan" = Security audit
WORKFLOW COMPLIANCE: Structured workflows with validation checkpoints. Research phase (Step 1c-1d) ensures skills based on proven approaches.
DIFFERENTIATOR: Research-driven creation. Web search (3-5 queries) before building. Multi-proposal generation. 9 automation scripts. Quality 9.0+/10.
REUSED: Anthropic's init_skill.py and package_skill.py (production-tested).
majiayu000/claude-skill-registry 163
-
ecto-query-analysis
Analyzes Ecto queries for N+1 problems, missing preloads, and performance issues.
majiayu000/claude-skill-registry 163
-
pagerunner-skill
Real Chrome automation for AI agents — authenticated sessions, PII anonymization, snapshots, and multi-agent coordination via KV store.
majiayu000/claude-skill-registry 163
-
Spec-Kit Claude Code Workflow
A conceptual skill for guiding the Spec-Kit + Claude Code development workflow
majiayu000/claude-skill-registry 163
-
cto-audit
Perform deep, expert-level codebase and architecture audits to identify technical strengths, weaknesses, risks, and opportunities. Use when a user asks for an assessment of a codebase's structure, quality, or readiness for scale. Deliver detailed, actionable, and prioritized recommendations grounded in engineering best practices.
majiayu000/claude-skill-registry 163
-
write-comments
Writes explanatory comments to code to improve readability for developers and AI systems. Use when documenting code or improving code comprehension.
majiayu000/claude-skill-registry 163
-
agent-builder
Design and build AI agents for any domain. Use when users:
(1) ask to "create an agent", "build an assistant", or "design an AI system"
(2) want to understand agent architecture, agentic patterns, or autonomous AI
(3) need help with capabilities, subagents, planning, or skill mechanisms
(4) ask about Claude Code, Cursor, or similar agent internals
(5) want to build agents for business, research, creative, or operational tasks
Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration
majiayu000/claude-skill-registry 163
-
develop-backend
Spring Boot/MyBatisによるバックエンド実装スキル - RESTful API設計、データベース設計（Flywayマイグレーション）、Controller/Service/Mapper層の実装、単体テスト作成を行います。DRY原則を徹底し、product.utilパッケージの既存実装やAOPによる自動ログ出力を活用します。未使用コード削除をIDE警告で確認し、./gradlew checkでLint/テスト/カバレッジ80%以上を保証します。サーバー起動による動作確認も必須です。
majiayu000/claude-skill-registry 163
-
jutsu-react-native:react-native-native-modules
Use when building or integrating native modules in React Native. Covers creating native modules, Turbo Modules, bridging native code, and accessing platform-specific APIs.
majiayu000/claude-skill-registry 163
-
modal
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
majiayu000/claude-skill-registry 163
-
kindle-capture
Kindle Web Reader/Kindle macOSアプリからスクリーンショットをキャプチャしてPDF生成。書籍名やASIN指定でKindle本を自動PDF化。Kindleライブラリ検索、Playwrightでページ自動取得、PNG画像からPDF変換、レイアウト設定（single/double）、範囲指定、品質調整、リサイズに対応。タイトル取得に失敗した場合は表紙キャプチャをAIで視認して命名する。
majiayu000/claude-skill-registry 163
-
juicebox-migration-deep-dive
Advanced Juicebox data migration strategies.
Use when migrating from other recruiting platforms, performing bulk data imports,
or implementing complex data transformation pipelines.
Trigger with phrases like "juicebox data migration", "migrate to juicebox",
"juicebox import", "juicebox bulk migration".
majiayu000/claude-skill-registry 163
-
manage-contact
Manage contacts in Sinch Conversation API. Use when the user wants to create a contact, update contact information, list contacts, find a contact, get contact details, add channels to a contact, or manage contact channels. Handles contact creation, updates, and channel associations.
majiayu000/claude-skill-registry 163
-
worktree-manager
Create, manage, and cleanup git worktrees with Claude Code agents across all projects. USE THIS SKILL when user says "create worktree", "spin up worktrees", "new worktree for X", "worktree status", "cleanup worktrees", or wants parallel development branches. Handles worktree creation, dependency installation, validation, agent launching in Ghostty, and global registry management.
majiayu000/claude-skill-registry 163
-
FastLED
FastLED library for controlling addressable LEDs (WS2812B, etc). Covers color spaces, effects, and performance optimization.
majiayu000/claude-skill-registry 163
-
Competitive Analyzer
Gemini DeepSearch MCPを活用した競合分析専門エージェント。直接・間接競合の徹底調査と差別化軸の特定。競合調査、市場分析、ポジショニング分析の際に積極的に使用。MUST BE USED for competitive analysis.
majiayu000/claude-skill-registry 163
-
justfile-maturity-model
Five-level maturity progression - assessment criteria, upgrade paths, YAGNI enforcement
majiayu000/claude-skill-registry 163
-
radar-chart
Configure radar (spider) charts in drizzle-cube dashboards for multi-dimensional comparison. Use when creating radar charts, spider charts, or comparing multiple metrics across categories.
majiayu000/claude-skill-registry 163
-
playwright-visual-testing
Browser automation, visual testing, and screenshot validation using Playwright MCP server for accelerated web development. Master visual regression testing, automated UI testing, and cross-browser validation.
majiayu000/claude-skill-registry 163
-
refactor_gate
Ask whether to proceed with refactoring after architecture mapping.
majiayu000/claude-skill-registry 163
-
matchms
Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization, compound ID, for metabolomics and MS data processing.
majiayu000/claude-skill-registry 163