#411 · Primary category: AI Coding Assistants
claude-code-skills
Standalone engineering skills for Claude Code and Codex: review, audit, optimization, testing, product discovery, architecture, and safe publishing.
Project last updated:08/29/26
GitHub Stars
554
Forks
83
Contributors
1
License
MIT
Why we included this project
Claude Code and Codex users working on real codebases will find this a useful set of standalone skills, each one a self-contained prompt file for a specific job: reviewing an implementation plan, auditing code health and security, profiling performance, planning a test strategy, or documenting architecture. You install only the suites you need instead of wiring up a framework. The skills are deliberately concise, carrying just the domain knowledge, decision gates, and evidence checklists worth putting in context, which suits modern coding models that handle complex workflows without heavy orchestration. The same skills move between hosts thanks to support for the Agent Plugins v1 standard alongside native Claude Code and Codex distribution. If you want more disciplined, evidence-driven output from your coding agents rather than ad-hoc prompting, this is a solid starting point to adapt.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.