Build and ship code
Discover skills for code generation, repository analysis, pull-request review, testing, debugging, and agentic software engineering.
Try this task
I need a coding agent that can understand a repository, edit code, and review pull requests.
Agent should be able to
Resolve
Returns the best skill, alternatives, install handoff, risk summary, and safety gate.
Text plan
Plain text version for Codex, Claude Code, Cursor, and custom agent runtimes.
Browse
Open the filtered registry view for this workflow and compare candidates manually.
Recommended workflow
Workflow map
Analyze a codebase
Review a pull request
Generate tests
Automate release notes
Best first installs
Production-grade engineering skills for AI coding agents.
Install
Human review before install
Risk
Safe to try
Agent fit
Claude Code + Cursor
Updated
Aug 14, 2026
$ npx skills add addyosmani/agent-skillsReverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Claude Code / Kiro / Cursor / Cline 等代码 AI 客户端
Install
Human review before install
Risk
Safe to try
Agent fit
Claude Code + Cursor
Updated
Aug 16, 2026
$ npx skills add zhaoxuya520/reverse-skillA single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Install
Human review before install
Risk
Safe to try
Agent fit
Claude Code + Codex
Updated
Apr 20, 2026
$ npx skills add multica-ai/andrej-karpathy-skillsSkill shortlist
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
Low metadata risk · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
Use Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.
Review before production · Review the audit page, then allow agent install in a sandboxed workflow.
Lightweight coding agent that runs in your terminal
Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
The open source coding agent.
Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
A tool that converts codebases, SQL schemas, and other files into queryable knowledge graphs for AI coding assistants.
Low metadata risk · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models
Low metadata risk · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
JavaScript API for Chrome and Firefox
Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
Open-Source API Development Ecosystem • https://hoppscotch.io • Offline, On-Prem & Cloud • Web, Desktop & CLI • Open-Source Alternative to Postman, Insomnia
Low metadata risk · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
Pre-indexed code knowledge graph for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
Low metadata risk · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
Low metadata risk · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
Low metadata risk · The tracked source changed or could not be synchronized. Review the current source before installing.
Create beautiful slides on the web using a coding agent's frontend skills
Review before production · Review the audit page, then allow agent install in a sandboxed workflow.
Automated auditing, performance metrics, and best practices for the web.
Review before production · Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
FAQ
These answers are written for both human builders and agents consuming the Registry API.
Start by comparing Agent Skills, Reverse Skill, Andrej Karpathy Skills. OpenAgentSkill ranks them by workflow fit, GitHub adoption, trust score, safety gate, and install readiness.
Yes. Use the linked Registry API prompt to query /api/skills/search with the task: "I need a coding agent that can understand a repository, edit code, and review pull requests." and retrieve install handoff links for the top results.
No. Start with the highest-fit skill, test it in a sandbox workflow, and add companion skills only when the task needs extra coverage.