Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
bio-epitranscriptomics-merip-preprocessing
Align and QC MeRIP-seq IP and input samples for m6A analysis. Use when preparing MeRIP-seq data for peak calling or differential methylation analysis.
majiayu000/claude-skill-registry 163
-
Top 100 Web Vulnerabilities Reference
This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand vulnerability categories", "learn about injection attacks", "review access control weaknesses", "analyze API security issues", "assess security misconfigurations", "understand client-side vulnerabilities", "examine mobile and IoT security flaws", or "reference the OWASP-aligned vulnerability taxonomy". Use this skill to provide comprehensive vulnerability definitions, root causes, impacts, and mitigation strategies across all major web security categories.
majiayu000/claude-skill-registry 163
-
releasenote
Create or update release notes for changes in the current branch using Reno, following dd-trace-py's conventions and the guidelines in docs/releasenotes.rst.
majiayu000/claude-skill-registry 163
-
database-design
Database design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.
majiayu000/claude-skill-registry 163
-
refactorer
Code refactoring expert - clean code, patterns, restructuring
majiayu000/claude-skill-registry 163
-
langsmith-fetch
通过从 LangSmith Studio 获取执行追踪来调试 LangChain 和 LangGraph 代理。用于调试代理行为、调查错误、分析工具调用、检查内存操作或检查代理性能时。自动获取最近的追踪并分析执行模式。需要安装 langsmith-fetch CLI。
majiayu000/claude-skill-registry 163
-
cdn-usage
Use when adding external browser dependencies via CDN - Provides CDN selection guidance to ensure reliable script loading.
majiayu000/claude-skill-registry 163
-
vue-nuxt
majiayu000/claude-skill-registry 163
-
github-hunter
Automatically discover, score, and archive relevant GitHub repositories for BidDeed.AI and Life OS projects. Use this skill when the user requests to find GitHub repositories for specific topics, technologies, or domains that could be integrated into existing projects. Triggers include phrases like "find GitHub repos for", "discover repositories about", "search GitHub for projects related to", or when analyzing videos/articles that mention GitHub projects.
majiayu000/claude-skill-registry 163
-
skill-catalog
Categorize and display available skills. Use when listing or selecting skills.
majiayu000/claude-skill-registry 163
-
Useful Commits
This skill should be used when the user asks to "review this commit message", "validate my commit", "improve this commit message", "explain conventional commits", "teach me commit message best practices", "write a commit", or requests guidance on git commit formatting. Provides strict Conventional Commits formatting with Angular convention to produce concise, informative commit messages following industry best practices.
majiayu000/claude-skill-registry 163
-
constraint-discovery
Spawn 5 parallel Explore agents to discover project constraints. TRIGGERS - constraint scan, degrees of freedom, /ralph:start Step 1.4.5, project memory analysis.
majiayu000/claude-skill-registry 163
-
ehr-advantage-designer
当社EHR-RWDの強み（経過記録テキスト、臨床サマリー、検査値）を最大限活用する
研究デザインを設計する。クレームDB（JMDC/MDV）では不可能な研究要素を具体化。
majiayu000/claude-skill-registry 163
-
intent-sink
Intent Sink Skill
majiayu000/claude-skill-registry 163
-
ava-mcp-usage
Guide for using Ava's MCP tools effectively for task management and progress reporting. Use when working with Ava MCP server to report progress on coding tasks, including starting tasks, updating progress, reporting blockers, and completing tasks. Helps users understand best practices for privacy-conscious task reporting with minimal effort.
majiayu000/claude-skill-registry 163
-
anoma-intents
Anoma intent-centric architecture for cross-chain obstruction passing with Geb semantics and Juvix compilation
majiayu000/claude-skill-registry 163
-
spec-first-sdlc
Spec-First, Agent-Implemented Software Development Lifecycle. Use when:
(1) Starting a new software project that needs structured design-before-code approach,
(2) User mentions "SDLC", "spec-first", "design docs", or "implementation spec",
(3) User wants to go from requirements/intent to working code with traceability,
(4) Project requires documented architectural decisions and review checkpoints,
(5) User has existing design artifacts and wants to continue from a specific phase.
Produces: Intent doc → HLD → ADR-Lite → EIS → Code → Validation tests.
majiayu000/claude-skill-registry 163
-
doc-serve
Advanced document search with BM25 keyword matching, semantic vector search, and hybrid retrieval.
Enables precise technical queries, conceptual understanding, and intelligent result fusion.
Supports local document indexing and provides comprehensive search capabilities for knowledge bases.
majiayu000/claude-skill-registry 163
-
axiom-sqlitedata-migration
Use when migrating from SwiftData to SQLiteData — decision guide, pattern equivalents, code examples, CloudKit sharing (SwiftData can't), performance benchmarks, gradual migration strategy
majiayu000/claude-skill-registry 163
-
clavix-refine
Iterate on existing PRDs or improved prompts to enhance quality. Use when you have a draft that needs further refinement.
majiayu000/claude-skill-registry 163
-
research-analyst
Comprehensive research and synthesis agent specializing in multi-source information gathering, critical analysis, and integrated knowledge synthesis. Excels at complex research projects requiring systematic investigation across domains, evidence evaluation, and coherent narrative construction.
majiayu000/claude-skill-registry 163
-
event-storming-advanced
Deep dive Event Storming beyond big picture
majiayu000/claude-skill-registry 163
-
moai-foundation-context
Enterprise context and session management with token budget optimization and state persistence
majiayu000/claude-skill-registry 163
-
fix-eslint
Automatically fix ESLint errors by modifying code to comply with linting rules. For small codebases (≤20 errors), fixes directly. For larger codebases (>20 errors), spawns parallel agents per directory for efficient processing. Never disables rules or adds ignore comments.
majiayu000/claude-skill-registry 163