commit-message-writer

Draft conventional commit messages that explain why a change exists instead of listing what changed. Use when trying to write a git commit message.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "commit-message-writer" with this command: npx skills add stefafafan/skills/stefafafan-skills-commit-message-writer

Commit Message Writer

Overview

Draft commit messages from intent. Explain why the change exists, not just what changed.

Workflow

  1. Gather the rationale from the user-agent conversation, project docs, explored implementation, or recent git history.
  2. Infer the most defensible reason when the diff does not state it explicitly.
  3. Choose the narrowest conventional commit type that fits the change.
  4. Write a why-first subject line.
  5. Add a body only when extra context helps.

Subject

Use the form type(scope): why.

Prefer these conventional commit types:

  • feat: introduce user-facing capability

  • fix: correct broken or risky behavior

  • refactor: improve structure without intended behavior change

  • perf: improve performance characteristics

  • test: add or fix tests

  • docs: change documentation only

  • build, ci, chore: repository or tooling maintenance

  • Stay at 50 characters or fewer.

  • Focus on intent or effect, not implementation steps or file edits.

  • Use a scope only when it adds meaning.

  • Avoid vague summaries such as update, change, modify or move.

Examples:

  • fix(auth): block expired token reuse
  • refactor(api): simplify pagination flow
  • feat(billing): support invoice retry recovery

Body

When needed, leave the second line blank and start the body on the third line.

  • Wrap every body line at 72 characters.
  • Use the body for motivation, constraints, tradeoffs, or follow-up context.
  • Do not repeat the diff unless that detail is needed to explain why.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

OpenClaw Skill Growth

Make OpenClaw Skills observable, diagnosable, and safely improvable over time. Use this when the user wants to maintain many SKILL.md files, inspect repeated...

Registry SourceRecently Updated
211Profile unavailable
General

Find Skills for ClawHub

Search for and discover OpenClaw skills from ClawHub (the official skill registry). Activate when user asks about finding skills, installing skills, or wants...

Registry SourceRecently Updated
2921Profile unavailable
General

Skill Listing Polisher

Improve a skill's public listing before publish. Use when tightening title, description, tags, changelog, and scan-friendly packaging so the listing looks cl...

Registry SourceRecently Updated
1150Profile unavailable
General

Skill Priority Setup

Scans installed skills, suggests L0-L3 priority tiers, and auto-configures skill injection policy. Use when: setting up skill priorities, optimizing token bu...

Registry SourceRecently Updated
2520Profile unavailable