OpenRaiser

Sit — Testing skill for Claude Code

Testing community

⚙️ [Skill] A Git-native semantic safety layer for AI agents editing Skill packages — validates, diffs, reviews, and gates prompt/schema/test changes before they ship.

How to install Sit

This entry records only its repository, not the path inside it, so there is no exact command to give. Open OpenRaiser/Sit and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Sit does

⚙️ [Skill] A Git-native semantic safety layer for AI agents editing Skill packages — validates, diffs, reviews, and gates prompt/schema/test changes before they ship.

Alternatives in Testing

  • Debug — You are tasked with helping debug issues during manual testing or implementation 10k ★
  • Playwright Automation — git clone Browser automation skill for end-to-end testing and web interaction 2.3k ★
  • Spec Kitty — Spec-Driven Development for serious software developers 1.6k ★

README

sit semantic safety for AI skills

English | 中文

Quick Start | Why sit? | Real Case | Agent Loop | PyPI | Releases

Real case: see how paper-webpage-builder uses Skill-style prompts, schemas, scripts, and golden behavior checks.

**A Git-native safety layer for AI agents that edit prompts, schemas, scripts, and Skill packages.**

Git can tell you that a prompt changed. `sit` tells you whether that change is a typo fix, a behavior change, a schema contract change, a test update, or a release risk.

pip install sit-toolkit
sit diff HEAD..WORKTREE
sit review HEAD..WORKTREE

Use `sit` when humans or AI agents evolve reusable skills and you need semantic diffs, golden tests, version gates, PR reviews, and reproducible releases without replacing Git.

![sit turns raw Git diffs into semantic Skill review signals](https://raw.githubusercontent.com/OpenRaiser/Sit/main/.github/assets/brand/sit-readme-hero-flat.png)

Why sit?

AI Skill packages are not just