Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
cc-linear
majiayu000/claude-skill-registry 163
-
moai-design-systems
Design system patterns with DTCG tokens, WCAG 2.2, and Figma integration
majiayu000/claude-skill-registry 163
-
ralph
持久化执行-验证-修复循环，直到任务完成
majiayu000/claude-skill-registry 163
-
responsive-design
Implement mobile-first responsive design with Tailwind CSS breakpoints for mobile, tablet, and desktop. Use when building responsive layouts or fixing layout issues.
majiayu000/claude-skill-registry 163
-
content-ideas
Generate 20 content ideas from 1 topic, each pushed through a different lens — story, observation, contrarian take, listicle, past vs present, present vs future, analysis, teardown, lesson, data/research. Each idea = title + one-sentence hook. Use when user wants "content ideas", "what should I write about", "brainstorm topics", or needs to fill a content calendar.
majiayu000/claude-skill-registry 163
-
writing-data
Use this skill when you need to structure data in `srs/data` for the Next.js app
majiayu000/claude-skill-registry 163
-
copilot-cli-quickstart
Use this skill when someone wants to learn GitHub Copilot CLI from scratch. Offers interactive step-by-step tutorials with separate Developer and Non-Developer tracks, plus on-demand Q&A. Just say "start tutorial" or ask a question! Note: This skill targets GitHub Copilot CLI specifically and uses CLI-specific tools (ask_user, sql, fetch_copilot_cli_documentation).
majiayu000/claude-skill-registry 163
-
map-codebase
Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map the codebase", "map codebase", "architecture report", "codebase overview", "architecture overview", "what am I looking at", or "explain this codebase".
majiayu000/claude-skill-registry 163
-
testing-patterns
Testing patterns and principles. Unit, integration, mocking strategies.
majiayu000/claude-skill-registry 163
-
pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
majiayu000/claude-skill-registry 163
-
gstack
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with
elements, verify page state, diff before/after actions, take annotated screenshots, check
responsive layouts, test forms and uploads, handle dialogs, and assert element states.
~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a
user flow, or file a bug with evidence.
gstack also includes development workflow skills. When you notice the user is at
these stages, suggest the appropriate skill:
- Brainstorming a new idea → suggest /office-hours
- Reviewing a plan (strategy) → suggest /plan-ceo-review
- Reviewing a plan (architecture) → suggest /plan-eng-review
- Reviewing a plan (design) → suggest /plan-design-review
- Creating a design system → suggest /design-consultation
- Debugging errors → suggest /investigate
- Testing the app → suggest /qa
- Code review before merge → suggest /review
- Visual design audit → suggest /design-review
- Ready to deploy / create PR → suggest /ship
- Post-ship doc updates → suggest /document-release
- Weekly retrospective → suggest /retro
- Wanting a second opinion or adversarial code review → suggest /codex
- Working with production or live systems → suggest /careful
- Want to scope edits to one module/directory → suggest /freeze
- Maximum safety mode (destructive warnings + edit restrictions) → suggest /guard
- Removing edit restrictions → suggest /unfreeze
- Upgrading gstack to latest version → suggest /gstack-upgrade
If the user pushes back on skill suggestions ("stop suggesting things",
"I don't need suggestions", "too aggressive"):
1. Stop suggesting for the rest of this session
2. Run: gstack-config set proactive false
3. Say: "Got it — I'll stop suggesting skills. Just tell me to be proactive
again if you change your mind."
If the user says "be proactive again" or "turn on suggestions":
1. Run: gstack-config set proactive true
2. Say: "Proactive suggestions are back on."
majiayu000/claude-skill-registry 163
-
Codebase Interrogator (Business Analyst)
Scans the codebase to extract intended features, business logic, and data models.
majiayu000/claude-skill-registry 163
-
shared-tooling-biome
Biome v2 unified linter, formatter, and import organizer — single Rust-powered tool replacing ESLint + Prettier with 97% Prettier compatibility and 20x faster performance
majiayu000/claude-skill-registry 163
-
final-release-review
Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions, improvement opportunities, and risks before releasing openai-agents-python.
majiayu000/claude-skill-registry 163
-
automation
Eliminate repetitive tasks, build CI/CD pipelines, and create self-maintaining systems
majiayu000/claude-skill-registry 163
-
database-admin
Expert database administrator specializing in modern cloud databases, automation, and reliability engineering. Masters AWS/Azure/GCP database services, Infrastructure as Code, high availability, disaster recovery, performance optimization, and compliance. Handles multi-cloud strategies, container databases, and cost optimization. Use PROACTIVELY for database architecture, operations, or reliability engineering.
majiayu000/claude-skill-registry 163
-
agents-v2-py
Build container-based Foundry Agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition.
Use when creating hosted agents that run custom code in Azure AI Foundry with your own container images.
Triggers: "ImageBasedHostedAgentDefinition", "hosted agent", "container agent", "Foundry Agent",
"create_version", "ProtocolVersionRecord", "AgentProtocol.RESPONSES", "custom agent image".
majiayu000/claude-skill-registry 163
-
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows
majiayu000/claude-skill-registry 163
-
frontend-design-pro
Creates jaw-dropping, production-ready frontend interfaces AND delivers perfectly matched real photos (Unsplash/Pexels direct links) OR flawless custom image-generation prompts for hero images, backgrounds, and illustrations. Zero AI slop, zero fake URLs.
majiayu000/claude-skill-registry 163
-
vibe-agents
Generate AGENTS.md and AI configuration files for your project. Use when the user wants to create agent instructions, set up AI configs, or says "create AGENTS.md", "configure my AI assistant", or "generate agent files".
majiayu000/claude-skill-registry 163
-
agent-dev-backend-api
Agent skill for dev-backend-api - invoke with $agent-dev-backend-api
majiayu000/claude-skill-registry 163
-
logging-observability
Implement structured logging, tracing, and metrics for debugging
majiayu000/claude-skill-registry 163
-
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
majiayu000/claude-skill-registry 163
-
vaultkeeper
Credential rotation reminders and API key hygiene monitoring. Tracks when credentials were last rotated, reminds you to update them, and scans for leaked keys. Use when: managing API keys, maintaining security hygiene, or rotating credentials regularly. NOT for: password management (use 1Password, Bitwarden), secrets management at scale (use Vault, AWS Secrets Manager), or compliance auditing.
majiayu000/claude-skill-registry 163