Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
chaos-engineering-altrupets-monorepo
majiayu000/claude-skill-registry 163
-
prompt
Use when optimizing prompts, skill descriptions, or agent instructions for clarity, specificity, and behavioral effectiveness.
majiayu000/claude-skill-registry 163
-
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
majiayu000/claude-skill-registry 163
-
prompt-optimization
Analyze and improve existing prompts for better performance
majiayu000/claude-skill-registry 163
-
ralph-specum-triage
This skill should be used only when the user explicitly asks to use `$ralph-specum-triage`, or explicitly asks Ralph Specum in Codex to triage a large effort into multiple specs.
majiayu000/claude-skill-registry 163
-
bilibili-analyzer
自动分析B站视频内容，下载视频并拆解成帧图片，使用AI分析并生成详细的专题文档或实操教程。
majiayu000/claude-skill-registry 163
-
Code Coverage with gcov
Add gcov code coverage instrumentation to C/C++ projects
majiayu000/claude-skill-registry 163
-
changelog-rules
Shared changelog conventions and formatting rules referenced by /create-changelog and /update-changelog. Not typically invoked directly.
majiayu000/claude-skill-registry 163
-
security-report
Generate a comprehensive security report for stakeholders
majiayu000/claude-skill-registry 163
-
c4-context
Expert C4 Context-level documentation specialist. Creates high-level system context diagrams, documents personas, user journeys, system features, and external dependencies. Synthesizes container and component documentation with system documentation to create comprehensive context-level architecture. Use when creating the highest-level C4 system context documentation.
majiayu000/claude-skill-registry 163
-
setup-harness
Copy Claude Code harness into a project directory for version control. Use when user wants to set up the harness or when they say "setup harness", "copy harness", "install harness", or provide a harness path.
majiayu000/claude-skill-registry 163
-
aspire-integration-testing
Write integration tests using .NET Aspire's testing facilities with xUnit. Covers test fixtures, distributed application setup, endpoint discovery, and patterns for testing ASP.NET Core apps with real dependencies.
majiayu000/claude-skill-registry 163
-
openclaw-relay
Real-time messaging across OpenClaw instances (channels, DMs, threads, reactions, search).
majiayu000/claude-skill-registry 163
-
review
Verify implementation conforms to planning artifacts. Checks API routes against OpenAPI spec, schema against ERD, domain model against classes, acceptance criteria coverage, security implementation, and documentation completeness.
majiayu000/claude-skill-registry 163
-
architect-review
Master software architect specializing in modern architecture
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-sandbox-files
List files in a sandbox directory. Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163
-
prototype-interaction
Define and document prototype interactions, transitions, and hotspots
majiayu000/claude-skill-registry 163
-
Performance Optimization
Optimize Next.js bundle size with code splitting, tree shaking, lazy loading, and build configuration. Apply when improving performance, reducing bundle size, analyzing dependencies, or optimizing load times.
majiayu000/claude-skill-registry 163
-
template-skill
Replace with description of the skill and when Claude should use it.
majiayu000/claude-skill-registry 163
-
code-review
当用户要求"审查代码"、"代码检查"、"检查bug"、"代码质量检查"、"发现问题"、"重构建议"，或者提到"代码审查"、"code review"、"审查"、"检查"时使用此技能。用于代码质量、潜在bug、性能问题、安全漏洞或改进机会的反馈。
majiayu000/claude-skill-registry 163
-
mobile-first-design
Designs responsive interfaces starting from mobile screens with progressive enhancement for larger devices. Use when building responsive websites, optimizing for mobile users, or implementing adaptive layouts.
majiayu000/claude-skill-registry 163
-
mathematical-proof-logic
The logical structure of mathematical proof -- how first-order logic, natural deduction, and semantic reasoning combine to produce rigorous mathematical arguments. Covers the logical skeleton of direct proof, contraposition, contradiction, cases, and induction; the role of definitions, lemmas, and theorems; how informal mathematical prose maps to formal deductive structure; and the difference between proof-as-object and proof-as-activity. Use when the question is "why is this a valid proof?" rather than "what proof technique applies?"
majiayu000/claude-skill-registry 163
-
red-team
Persona-based adversarial validation. Probes whether docs and skills actually work when someone with constraints tries to use them. Spawns context-restricted agents that attempt real tasks, then consolidates findings via council. Triggers: "red-team", "red team", "adversarial test", "persona test", "can someone use this", "usability test", "zero-context test".
majiayu000/claude-skill-registry 163
-
connect
Connect Claude to any app. Send emails, create issues, post messages, update databases - take real actions across Gmail, Slack, GitHub, Notion, and 1000+ services.
majiayu000/claude-skill-registry 163