Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
complexity-gate
Estimate issue complexity before implementation to prevent timeouts. Uses cheap estimation to save expensive implementation tokens.
majiayu000/claude-skill-registry 163
-
phenotype-lab-spec
研究対象集団・アウトカムのフェノタイプ定義と検査値活用仕様を作成する。
コンピューター実行可能なアルゴリズム形式で記述し、バリデーション計画を含める。
majiayu000/claude-skill-registry 163
-
coderabbit-review
Use this skill when working with CodeRabbit, such as running CodeRabbit reviews, generating and processing automated CodeRabbit comments, or evaluating CodeRabbit suggestions.
majiayu000/claude-skill-registry 163
-
bitbucket
Manage repositories, check pipelines, review PRs, and collaborate on Bitbucket
majiayu000/claude-skill-registry 163
-
Backward Compatibility Rules
Comprehensive guide to backward compatibility rules for APIs, databases, and data contracts with migration strategies and testing approaches
majiayu000/claude-skill-registry 163
-
docs-update
Verify and update derived documentation
majiayu000/claude-skill-registry 163
-
video-hook-generator
Generate attention-grabbing hooks for the first 3 seconds of videos. The hook determines if viewers stay or scroll. Creates multiple hook variations for A/B testing. Use when crafting video openings, improving retention, or creating scroll-stopping content for YouTube, TikTok, or Reels.
majiayu000/claude-skill-registry 163
-
generate-subsystem-skills
Generate specialized skills for each subsystem in the monorepo. Creates shared language skills and subsystem-specific checklists for high-quality AI code generation.
majiayu000/claude-skill-registry 163
-
saddle-node
Bifurcation creating/destroying equilibrium pair
majiayu000/claude-skill-registry 163
-
link-verification
Use during content verification - validates all URLs are accessible and quoted text exists verbatim in sources
majiayu000/claude-skill-registry 163
-
cc-control-flow-quality
Review control flow quality using 87-item checklist. Use when code has deep nesting (3+ levels), complex conditionals, loop design questions, high cyclomatic complexity (McCabe >10), or callback hell. Symptoms: arrow-shaped code, repeated conditions, confusing loop exits, lengthy if-else chains. Provide refactoring patterns (guard clauses, named booleans, table-driven methods) and modern guidance (async/await, pattern matching, functional pipelines). Produce verified code with pass/fail assessment.
majiayu000/claude-skill-registry 163
-
ai-tools
Google AI tools integration. Modules: Gemini API (multimodal: audio/image/video/PDF, 2M context), Gemini CLI (second opinions, Google Search, code review), NotebookLM (source-grounded Q&A). Capabilities: transcription, OCR, video analysis, image generation, web search, document queries. Actions: transcribe, analyze, extract, generate, query, search with Google AI. Keywords: Gemini, Gemini API, Gemini CLI, NotebookLM, audio transcription, image captioning, video analysis, PDF extraction, Google Search, second opinion, source-grounded, multimodal, web research. Use when: processing media files, needing second AI opinion, searching current web info, querying uploaded documents, generating images.
majiayu000/claude-skill-registry 163
-
lc-list
List LeetCode problems by difficulty level (easy/medium/hard)
majiayu000/claude-skill-registry 163
-
dma-attack-techniques
Guide for Direct Memory Access (DMA) attack techniques using FPGA hardware. Use this skill when researching PCIe DMA attacks, pcileech, FPGA firmware development, or hardware-based memory access for game security research.
majiayu000/claude-skill-registry 163
-
project-setup-expert
Multi-module 구조 설계, Gradle 설정, Version Catalog, 의존성 관리.
헥사고날 아키텍처 모듈 분리. Domain 외부 의존성 금지, 순환 의존성 금지.
QA 도구 (Checkstyle, SpotBugs, PMD, JaCoCo) 설정.
majiayu000/claude-skill-registry 163
-
trust-credibility
Principios de BJ Fogg sobre credibilidad en web. Use cuando diseñe para conversión, e-commerce, o cualquier contexto donde la confianza es crítica.
majiayu000/claude-skill-registry 163
-
npm-search
Search npm packages. Use for finding Node.js/JavaScript packages, libraries, and tools.
majiayu000/claude-skill-registry 163
-
dogfooding
Help users implement effective dogfooding practices. Use when someone is trying to get their team to use their own product, designing internal usage programs, or building user empathy through personal product use.
majiayu000/claude-skill-registry 163
-
workflow-compliance-auditor
Validates workflow files for logical integrity, termination guarantees, and skill existence.
majiayu000/claude-skill-registry 163
-
api-fetch-with-auth
Create authenticated API fetch function in Next.js. Use for frontend API calls.
majiayu000/claude-skill-registry 163
-
anti-cheat-systems
Guide for understanding anti-cheat systems and bypass techniques. Use this skill when researching game protection systems (EAC, BattlEye, Vanguard), anti-cheat architecture, detection methods, or bypass strategies.
majiayu000/claude-skill-registry 163
-
PromptInjection
Prompt injection testing. USE WHEN prompt injection, jailbreak, LLM security, AI security assessment, pentest AI application, test chatbot vulnerabilities.
majiayu000/claude-skill-registry 163
-
qa-testing
QA engineer with expertise in software testing methodologies, test design, and quality assurance practices. Use this skill when planning tests, writing test cases, or improving test coverage and quality.
majiayu000/claude-skill-registry 163
-
quicksave
Cross-model context handoff via Japanese semantic compression with negentropic coherence validation. Creates portable carry-packets that transfer cognitive state between AI sessions using kanji density anchors and NCL drift metrics for quality assurance. Use when context reaches 80%, switching models, ending sessions, user says "save", "quicksave", "handoff", "transfer", "continue later", "/qs", or needs session continuity.
majiayu000/claude-skill-registry 163