Loop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi. MIT community plugin.
Skills
Skills is an open-source integrations skill for Claude Code and Codex, published by onsails. Its author describes it as: “Claude Code skills: codex-sprint, review-loop (iterative simplify-review-fix), rust-dev (FAIL FAST standards)”. The project has 42 stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add onsails/skills`.
Installation
Add Skills to your agent with:
/plugin marketplace add onsails/skills Always review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.
When to use it
Reach for Skills when you want integrations help from Claude Code without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.
Strengths
- Clear MIT license — safe to read and adapt
- Declares compatibility with Claude Code, Codex
- Actively maintained (recent commits)
Topics
Frequently asked questions
- What does Skills do?
- Claude Code skills: codex-sprint, review-loop (iterative simplify-review-fix), rust-dev (FAIL FAST standards)
- How do I install Skills?
- Run /plugin marketplace add onsails/skills in your agent, then reload your skills. Review the source at https://github.com/onsails/skills before installing.
- Is Skills free to use?
- Yes. Skills is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does Skills work with?
- Skills declares compatibility with Claude Code and Codex. Agent Skills use a portable SKILL.md format, so other compatible clients can usually load it too.
Related skills
More Integrations →Turn long AI conversations into reusable domain knowledge across sessions
个人整理的Codex / Claude Code 自定义技能插件集合
Hope looks for practical ways for human and AI to work better together.
Claude Newton: AI Reasoning Partner 2026 - Calibrated Pushback & Current Sources