juliusbrussee/caveman-commit

Write commit messages terse and exact. Conventional Commits format. No fluff. Why over what.

Rules

Subject line:

<type>(<scope>): <imperative summary> — <scope> optional
Types: feat, fix, refactor, perf, docs, test, chore, build, ci, style, revert
Imperative mood: "add", "fix", "remove" — not "added", "adds", "adding"
≤50 chars when possible, hard cap 72
No trailing period
Match project convention for capitalization after the colon

Body (only if needed):

Skip entirely when subject is self-explanatory
Add body only for: non-obvious why, breaking changes, migration notes, linked issues
Wrap at 72 chars
Bullets - not *
Reference issues/PRs at end: Closes #42, Refs #17

What NEVER goes in:

"This commit does X", "I", "we", "now", "currently" — the diff says what
"As requested by..." — use Co-authored-by trailer
"Generated with Claude Code" or any AI attribution — unless the user's own rule requires an Assisted-by/AI-attribution trailer, then add it as a trailer
Emoji (unless project convention requires)
Restating the file name when scope already says it

Examples

Diff: new endpoint for user profile with body explaining the why

❌ "feat: add a new endpoint to get user profile information from the database"

✅

feat(api): add GET /users/:id/profile

Mobile client needs profile data without the full user payload
to reduce LTE bandwidth on cold-launch screens.

Closes #128

Diff: breaking API change

✅

feat(api)!: rename /v1/orders to /v1/checkout

BREAKING CHANGE: clients on /v1/orders must migrate to /v1/checkout
before 2026-06-01. Old route returns 410 after that date.

Auto-Clarity

Always include body for: breaking changes, security fixes, data migrations, anything reverting a prior commit. Never compress these into subject-only — future debuggers need the context.

Boundaries

Only generates the commit message. Does not run git commit, does not stage files, does not amend. Output the message as a code block ready to paste. "stop caveman-commit" or "normal mode": revert to verbose commit style.

Files2

2 files · 2.6 KB

Select a file to preview

Overall Score

89/100

Grade

A

Excellent

Safety

98

Quality

88

Clarity

89

Completeness

82

Summary

This skill generates terse Conventional Commits messages with an emphasis on clarity and reasoning. It enforces strict formatting rules (subject ≤50–72 chars, imperative mood, body only when necessary) and guides the agent to produce context-aware messages that explain the "why" rather than restating diffs. The skill explicitly prevents AI attribution, emoji, and verbose patterns, and mandates body text for breaking changes, security fixes, migrations, and reverts.

Detected Capabilities

text generationcommit message formattingrule enforcement

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

write commit messageconventional commitscommit with whyterse commitgenerate commit body

Use Cases

Generate concise commit messages in Conventional Commits format
Create breaking change commit messages with mandatory context
Write security fix commits with explanation of impact
Document data migrations with schema change rationale
Enforce terse messaging that avoids redundancy with diffs
Auto-generate commit bodies for non-obvious reasoning

Quality Notes

Skill is purely generative — zero file I/O, no shell execution, no side effects. Very low surface area risk.
Clear, enforceable rules with concrete examples demonstrating both anti-patterns and correct output.
Explicit scope boundaries: skill generates message text only, does not invoke git, does not stage, does not amend.
Coverage of edge cases: breaking changes, security fixes, migrations, reverts all have mandatory body guidance.
Body conditions are well-defined (non-obvious why, breaking changes, migrations, issues/PRs).
Subject line rules are mathematically precise (≤50 typical, hard cap 72 chars).
Anti-patterns section clearly documents what never goes in (AI attribution, emoji unless convention, restated file names).
Example outputs in both README and SKILL.md validate the rules with real diff → message walkthrough.
Minor: README duplicates content from SKILL.md but adds practical invocation reference, improving accessibility.
Documentation is self-contained — no external dependencies or missing configuration.

Model: claude-haiku-4-5-20251001Analyzed: Aug 17, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

caveman-commit