Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
30-00-refactor-index
Refactoring primer index. Read this first before any refactor — it points you to the right guide for your situation. Progressive exploration, not bulk loading.
majiayu000/claude-skill-registry 163
-
amap
使用高德地图Web服务API进行地点搜索、天气查询和路线规划。
majiayu000/claude-skill-registry 163
-
project-development
This skill covers the principles for identifying tasks suited to LLM processing, designing effective project architectures, and iterating rapidly using agent-assisted development.
majiayu000/claude-skill-registry 163
-
open-web-unlocker
Fetch web pages and search results as clean markdown, structured JSON, or raw HTML. Use this skill when the task involves fetching a URL, scraping web content, or querying search engines (examples include reading articles, extracting product data, getting search results from Brave/Bing/DuckDuckGo, or handling JS-rendered and anti-bot pages).
majiayu000/claude-skill-registry 163
-
oris-maintainer
Maintain the Oris Rust agent runtime with an issue-driven GitHub workflow. Use when Codex is working in the Oris repository and needs to pick up a GitHub issue, turn the issue into scoped code changes, run Rust validation such as cargo fmt and cargo test, publish the oris-runtime crate to crates.io, close the completed issue, and continue to the next iteration.
majiayu000/claude-skill-registry 163
-
create-workflow-dotnet
This skill creates a Dapr workflow application in .NET. Use this skill when the user asks to "create a workflow in .NET", "write a .NET workflow application" or "build a workflow app in C#".
majiayu000/claude-skill-registry 163
-
git-squash
This skill should be used when the user asks to "squash PR commits", "squash my branch", "flatten branch history", "combine all commits into one", "prepare a clean PR commit", or "squash commits relative to main/default branch". It rewrites the current branch into a single commit whose message semantically summarizes the surviving net changes relative to the default branch.
majiayu000/claude-skill-registry 163
-
clawsec-suite
ClawSec suite manager with embedded advisory-feed monitoring, cryptographic signature verification, approval-gated malicious-skill response, and guided setup for additional security skills.
majiayu000/claude-skill-registry 163
-
audit-frontend
Frontend audit — component architecture, accessibility, D3 visualization, search UX
majiayu000/claude-skill-registry 163
-
prompt-architect
Comprehensive framework for analyzing, creating, and refining prompts for AI systems. Use when creating prompts for Claude, ChatGPT, or other language models, improving existing prompts, or applying evidence-based prompt engineering techniques. Applies structural optimization, self-consistency patterns, and anti-pattern detection to transform prompts into highly effective versions.
majiayu000/claude-skill-registry 163
-
unity-developer
Build Unity games with optimized C# scripts, efficient rendering, and proper asset management. Masters Unity 6 LTS, URP/HDRP pipelines, and cross-platform deployment.
majiayu000/claude-skill-registry 163
-
coding-standards
Padrões de Codificação React TypeScript. Use when reviewing code style or formatting.
majiayu000/claude-skill-registry 163
-
mcp-builder
Guide for creating MCP (Model Context Protocol) servers. Use this when building integrations with external services, creating new MCP servers, or connecting Claude to APIs.
majiayu000/claude-skill-registry 163
-
project-audit
Security scan, dead code detection, and code quality audit for any project
majiayu000/claude-skill-registry 163
-
motherduck-partner-delivery
Deliver repeatable MotherDuck architectures across multiple clients. Use when standardizing isolation, provisioning, regional deployment, sharing boundaries, and client-specific exceptions for a consultancy or partner delivery model.
majiayu000/claude-skill-registry 163
-
seo-fundamentals
SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles.
majiayu000/claude-skill-registry 163
-
nodejs-backend-patterns
Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices. Use when creating Node.js servers, REST APIs, GraphQL backends, or microservices architectures.
majiayu000/claude-skill-registry 163
-
promql-generator
Generates PromQL queries with RED/USE/SLO patterns, native histograms, recording rules, and alerting expressions. Use when creating new queries from requirements; excludes validation (use promql-validator).
majiayu000/claude-skill-registry 163
-
Hooks Automation
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.
majiayu000/claude-skill-registry 163
-
react-patterns
Modern React patterns and principles. Hooks, composition, performance, TypeScript best practices.
majiayu000/claude-skill-registry 163
-
team-builder
Interactive agent picker for composing and dispatching parallel teams
majiayu000/claude-skill-registry 163
-
cobuilder-guardian
This skill should be used when the CoBuilder Guardian needs to act as an independent guardian angel — designing PRDs with CoBuilder RepoMap context injection, challenging designs via parallel solutioning, dispatching workers via AgentSDK pipelines, creating blind Gherkin acceptance tests and executable browser test scripts from PRDs, monitoring orchestrator progress, independently validating claims against acceptance criteria using gradient confidence scoring (0.0-1.0), autonomously accepting or rejecting implementations based on gradient confidence scoring thresholds (0.70+ for ACCEPT), autonomously closing validation gaps via Phase 4.5 gap closure protocol (creating fix-it codergen nodes), and setting session promises. Use when asked to "spawn and monitor an orchestrator", "create acceptance tests for a PRD", "validate orchestrator claims", "act as guardian angel", "independently verify implementation work", "autonomously close validation gaps", "create fix-it nodes", "design and challenge a PRD", "validation thresholds", "gradient scoring decision", or "bead creation for gaps".
majiayu000/claude-skill-registry 163
-
result-to-claim
Use when experiments complete to judge what claims the results support, what they do not, and what evidence is still missing. A secondary Codex agent evaluates results against intended claims and routes to the next action (pivot, supplement, or confirm). Use after experiments finish - before writing the paper or running ablations.
majiayu000/claude-skill-registry 163
-
csharp
Writes C# code following VanDaemon conventions and clean architecture patterns
Use when: Creating services, entities, controllers, or plugins in the VanDaemon codebase
majiayu000/claude-skill-registry 163