Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
ecto-query-analysis
Analyzes Ecto queries for N+1 problems, missing preloads, and performance issues.
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
-
core-principles
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
-
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
-
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
-
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
majiayu000/claude-skill-registry 163
-
critical-bug-detector
Automatically performs critical pre-release checks when building installers, creating releases, or packaging VoiceLite. Prevents missing files, version mismatches, and configuration errors that have caused release failures.
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
-
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
-
run-ios-simulator
Build and run an iPlug2 iOS app in the iOS Simulator
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
-
assets-split-quadrants
Split a 2x2 sprite sheet into four PNGs.
majiayu000/claude-skill-registry 163
-
e2e-playwright
Playwright E2E workflow for this extension. Use when E2E fails or is flaky, or mentions Playwright/e2e/fixtures/spec/trace/PWDEBUG.
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
-
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
-
JSharpener
JavaScript/TypeScript static analysis tool for call graphs, unused code detection (tree shaking), dependency analysis, and circular dependency detection
majiayu000/claude-skill-registry 163
-
plans-yankeeinlondon-adaptive-shell
majiayu000/claude-skill-registry 163
-
ms-rust
ALWAYS invoke this skill BEFORE writing or modifying ANY Rust code (.rs files) even for simple Hello World programs. Enforces Microsoft-style Rust development discipline and requires consulting the appropriate guideline files before any coding activity. This skill is MANDATORY for all Rust development.
majiayu000/claude-skill-registry 163
-
Architecture Graph
This skill should be used when the user asks about "entities", "relations", "architecture graph", "spec-driven development", "code annotations", "@graph anchors", mentions ".graph/" directory, asks to "add entity", "create relation", "verify sync", "check drift", discusses "code_refs", "architecture specification", or is working with YAML entity files in .graph/entities/. Provides guidance for maintaining architecture-as-code consistency.
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
-
Implement Dynamic Dilation
Create interactive dilation animations using p5.js where students explore dilations with adjustable scale factors.
majiayu000/claude-skill-registry 163
-
multi-agent-orchestrator
Orchestrate parallel CLI agents (Claude Code, Codex, Gemini) for competitive evaluation. Use when user says "run multi-agent", "compare agents", "launch competitive evaluation", "use parallel agents", or complex tasks (>7/10) where multiple approaches exist and best solution matters.
majiayu000/claude-skill-registry 163
-
file-name-wizard
Audit all filename and naming conventions in the codebase against CLAUDE.md standards and common patterns. Use when user asks to check naming conventions, audit filenames, find naming inconsistencies, or validate file naming patterns.
majiayu000/claude-skill-registry 163