kentoshimizu/sw-agent-skills/git-commit-hygiene

Claude Code and agent skill by kentoshimizu/sw-agent-skills

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Enforce atomic commits, clear commit messages, and auditable change intent before push or review. Use when commit granularity, message clarity, and traceability must be improved; do not use for CI workflow design or application behavior implementation.

Install

npx vskill@latest install kentoshimizu/sw-agent-skills/git-commit-hygiene

SKILL.md

The same SKILL.md was published earlier as kentoshimizu/sw-agent-skills/git-commit-hygiene.

Git Commit Hygiene

Overview

Use this skill to create commit history that reviewers can reason about and operators can bisect safely.

Scope Boundaries

  • Use this skill when the task matches the trigger condition described in description.
  • Do not use this skill when the primary task falls outside this skill's domain.

Shared References

  • Commit message quality rules:
  • references/commit-message-quality-rules.md

Templates And Assets

  • Commit slicing checklist:
  • assets/commit-slicing-checklist.md
  • Commit message template:
  • assets/commit-message-template.txt

Inputs To Gather

  • Changed files and logical change boundaries.
  • Team commit message conventions and compliance constraints.
  • Risk profile of the change set (critical path vs local refactor).
  • Required verification scope before push.

Deliverables

  • Logical commit slicing plan.
  • Commit messages with explicit intent/rationale.
  • Verification notes per commit (tests/checks run).
  • Traceability-ready history for review and rollback.

Workflow

  1. Separate unrelated changes using assets/commit-slicing-checklist.md.
  2. Write commit messages from assets/commit-message-template.txt and references/commit-message-quality-rules.md.
  3. Ensure each commit is independently reviewable and reversible.
  4. Run required tests/checks before push.
  5. Re-check history for mixed intent, hidden generated noise, and sensitive content.

Quality Standard

  • Each commit has one primary behavioral intent.
  • Messages explain why and risk, not only file changes.
  • Commit sequence is bisect-friendly for regression analysis.
  • Sensitive data never appears in staged history.

Failure Conditions

  • Stop when a commit mixes unrelated behavior changes.
  • Stop when a commit cannot be validated independently.
  • Escalate when traceability/compliance requirements cannot be met with current history.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
8
7-day trend score
9

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 9 May 2026, 6 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/kentoshimizu/sw-agent-skills/git-commit-hygiene/badge)](https://verified-skill.com/skills/kentoshimizu/sw-agent-skills/git-commit-hygiene)

Something wrong with this skill or its page? Tell us.