Production-grade engineering skills for AI coding agents.
$ npx skills add addyosmani/agent-skillsInstallation guide
A practical installation workflow for Claude Code users: choose one skill, copy the install command, run a sandbox task, and review permissions before adopting it.
Decision prompt
I want to install one Agent Skill in Claude Code and validate it safely before using it in my default workflow.
Recommended shortlist
Production-grade engineering skills for AI coding agents.
$ npx skills add addyosmani/agent-skillsaccess to david ondrej's personal agent skills
$ npx skills add davidondrej/skillsReview a branch or diff against repository standards and the originating spec in two independent analysis passes.
$ npx skills add mattpocock/skills --skill code-reviewUse Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.
$ npx skills add anthropics/skills --skill webapp-testingHow to use this guide
Choose a concrete Claude Code workflow such as PR review, bug triage, or browser verification.
Use the readiness score, risks, proof points, and install command before copying anything.
Ask the agent to complete one real task, then inspect diffs and logs manually.
Evaluation notes
The safest installation path is narrow: pick one skill, run one task, inspect the output, and only then add it to your normal agent workflow.
A skill with a clear install path is easier to evaluate. Missing install commands are not automatic dealbreakers, but they add review work.
FAQ
You can, but it is harder to debug. For production workflows, install and validate one skill at a time.
Treat it as a manual-review candidate. Open the repository, inspect the instructions, and avoid production use until the install path is clear.
More candidates
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.
Automate a real browser from the terminal for navigation, form filling, snapshots, screenshots, extraction, and UI-flow debugging.
🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Claude Code / OpenClaw / Codex / Cursor / OpenCode / Qwen / Copilot / Hermes / Kimi & 17+ CLIs.
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
A curated list of awesome skills, hooks, slash-commands, agent orchestrators, applications, and plugins for Claude Code by Anthropic
Next guides
Platform shortlist
A practical shortlist of skills for Claude Code users who want stronger repository analysis, repeatable coding workflows, browser checks, and agent-ready implementation plans.
Platform shortlist
A focused guide for builders using Codex-style coding agents: repository inspection, issue triage, implementation planning, testing, and browser verification skills.
Installation guide
A step-by-step workflow for adding install-ready skills to a Codex-style agent setup while keeping validation, permissions, and rollback in mind.
Installation guide
A practical installation workflow for Claude Code users: choose one skill, copy the install command, run a sandbox task, and review permissions before adopting it.
Decision prompt
I want to install one Agent Skill in Claude Code and validate it safely before using it in my default workflow.
Recommended shortlist
Production-grade engineering skills for AI coding agents.
$ npx skills add addyosmani/agent-skillsaccess to david ondrej's personal agent skills
$ npx skills add davidondrej/skillsReview a branch or diff against repository standards and the originating spec in two independent analysis passes.
$ npx skills add mattpocock/skills --skill code-reviewUse Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.
$ npx skills add anthropics/skills --skill webapp-testingHow to use this guide
Choose a concrete Claude Code workflow such as PR review, bug triage, or browser verification.
Use the readiness score, risks, proof points, and install command before copying anything.
Ask the agent to complete one real task, then inspect diffs and logs manually.
Evaluation notes
The safest installation path is narrow: pick one skill, run one task, inspect the output, and only then add it to your normal agent workflow.
A skill with a clear install path is easier to evaluate. Missing install commands are not automatic dealbreakers, but they add review work.
FAQ
You can, but it is harder to debug. For production workflows, install and validate one skill at a time.
Treat it as a manual-review candidate. Open the repository, inspect the instructions, and avoid production use until the install path is clear.
More candidates
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.
Automate a real browser from the terminal for navigation, form filling, snapshots, screenshots, extraction, and UI-flow debugging.
🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Claude Code / OpenClaw / Codex / Cursor / OpenCode / Qwen / Copilot / Hermes / Kimi & 17+ CLIs.
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
A curated list of awesome skills, hooks, slash-commands, agent orchestrators, applications, and plugins for Claude Code by Anthropic
Next guides
Platform shortlist
A practical shortlist of skills for Claude Code users who want stronger repository analysis, repeatable coding workflows, browser checks, and agent-ready implementation plans.
Platform shortlist
A focused guide for builders using Codex-style coding agents: repository inspection, issue triage, implementation planning, testing, and browser verification skills.
Installation guide
A step-by-step workflow for adding install-ready skills to a Codex-style agent setup while keeping validation, permissions, and rollback in mind.