Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
vibe-safe-deploy
Performs deployment with pre-flight checks, atomic replacement, post-deploy verification, and automatic rollback. Use before any deployment to staging or production.
majiayu000/claude-skill-registry 163
-
interview-framework
This skill should be used when running an interactive interview before a spec phase, gathering requirements through dialogue, asking the user clarifying questions before delegating to a subagent, or when any Ralph phase command (research, requirements, design, tasks) needs adaptive brainstorming dialogue. Covers the 3-phase algorithm (Understand, Propose Approaches, Confirm and Store).
majiayu000/claude-skill-registry 163
-
redis
Implements caching layer with Redis or memory fallback using aiocache.
Use when: Adding cache operations, modifying TTLs, implementing cache invalidation patterns, or debugging cache behavior.
majiayu000/claude-skill-registry 163
-
seo-technical
Audit technical SEO across crawlability, indexability, security, URLs, mobile, Core Web Vitals, structured data, JavaScript rendering, and related platform signals like robots.txt and AI crawler access.
majiayu000/claude-skill-registry 163
-
uv-expert
Master complex Python project management with uv - an extremely fast Python package and project manager. Handle projects, scripts, tools, Python versions, workspaces, Docker integration, CI/CD, pip interface, dependency resolution, and advanced workflows. Use when working with uv, migrating from pip/poetry/pipenv, managing Python projects, or when users mention uv, uvx, pyproject.toml, uv.lock, virtual environments, or complex dependency management.
majiayu000/claude-skill-registry 163
-
community-building
Help users build and grow product communities. Use when someone is starting a community, scaling an ambassador program, driving community-led growth, or choosing between user, developer, or partner communities.
majiayu000/claude-skill-registry 163
-
rules-distill
Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files
majiayu000/claude-skill-registry 163
-
studio-list-pattern
Provides patterns for implementing infinite scroll lists with sticky toolbars in Erify Studios. This skill should be used when building studio-scoped list pages with card-based layouts, debounced search, and cursor-based pagination.
majiayu000/claude-skill-registry 163
-
using-pendle-adapter
majiayu000/claude-skill-registry 163
-
add-rate-limiting
Configure rate limiting policies for API endpoints with sliding window limits
majiayu000/claude-skill-registry 163
-
redux-slice-generator
Generate redux slice generator operations. Auto-activating skill for Frontend Development.
Triggers on: redux slice generator, redux slice generator
Part of the Frontend Development skill category. Use when working with redux slice generator functionality. Trigger with phrases like "redux slice generator", "redux generator", "redux".
majiayu000/claude-skill-registry 163
-
discovery
Full discovery phase orchestrator. Brainstorm + ao search + research + plan + pre-mortem gate. Produces epic-id and execution-packet for /crank. Triggers: "discovery", "discover", "explore and plan", "research and plan", "discovery phase".
majiayu000/claude-skill-registry 163
-
libmemory
libmemory - Memory management for LLM context windows. WindowBuilder constructs token-limited context from conversation history and tools. createWindow factory simplifies window creation. MemoryIndex stores conversation identifiers. Use for managing chat history, building LLM prompts, and context window optimization.
majiayu000/claude-skill-registry 163
-
wechat-automation
当用户要求"微信监听"、"消息提取"、"Agent 开发"、"wxauto"、"Accessibility API"、"UI 自动化"、"输入框控制"、"Platform Agent"，或者提到"微信自动化"、"消息监控"、"WeChat monitoring"时使用此技能。用于开发 WeReply 的 Platform Agent（Windows wxauto 或 macOS Accessibility API）、实现微信消息监听、消息提取、输入框控制和 Agent 错误处理。
majiayu000/claude-skill-registry 163
-
template-skill
Template for creating new skills in gptme-contrib. Use this as a starting point when creating your own skills.
majiayu000/claude-skill-registry 163
-
advance-directive
Drafts attorney-supervised, state-compliant U.S. Advance Health Care Directives that appoint health care agents, resolve the HIPAA access gap, and record clinically usable treatment preferences. Enforces state-law verification for execution formalities, statutory forms, and special limitations. Addresses adversarial risks from family disputes and institutional challenges. Use when drafting advance directives, health care proxies, living wills, health care powers of attorney, HIPAA medical authorizations, or end-of-life planning documents.
majiayu000/claude-skill-registry 163
-
mailcoach-automation
Automate Mailcoach tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
building-threat-feed-aggregation
majiayu000/claude-skill-registry 163
-
testing-business-logic-flaws
majiayu000/claude-skill-registry 163
-
agent-issue-tracker
Agent skill for issue-tracker - invoke with $agent-issue-tracker
majiayu000/claude-skill-registry 163
-
verification-before-completion
verification-before-completion
majiayu000/claude-skill-registry 163
-
phpunit
PHPUnit test structure, naming, assertions, and factory conventions for Laravel feature and unit tests.
majiayu000/claude-skill-registry 163
-
nw-command-design-patterns
Best practices for command definition files - size targets, declarative template, anti-patterns, and canonical examples based on research evidence
majiayu000/claude-skill-registry 163
-
run
One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.
majiayu000/claude-skill-registry 163