CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

caveman-commit

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

74

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is caveman-commit in JuliusBrussee/caveman

SKILL.md
Quality
Evals
Security

Quality

Content

96%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Excellent instruction-only content: terse, concrete, and matching the skill's own compression philosophy, with complete examples and clear boundaries. The only weakness is minor internal redundancy between the Body rules and the Auto-Clarity section.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence ('Write commit messages terse and exact. No fluff. Why over what.') with zero padding and no explanation of git or Conventional Commits basics; every token earns its place.

5 / 5

Actionability

Fully concrete guidance: exact subject format, enumerated types, char limits, an explicit never-includes list, and two complete copy-paste-ready example messages covering the common cases (feature with body, breaking change).

5 / 5

Workflow Clarity

A simple single-purpose skill whose single action is unambiguous: inspect the change, output the message as a paste-ready code block. The skill explicitly excludes destructive actions (no commit, no stage, no amend), so no validation cap applies.

5 / 5

Progressive Disclosure

A simple, well-sectioned skill (Rules, Examples, Auto-Clarity, Boundaries) with all content appropriately inline and no external files needed. Held at 4 rather than 5 because the body slightly exceeds the simple-skill line and the Auto-Clarity section partially duplicates the Body rules, a minor organization gap.

4 / 5

Total

19

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with a clear niche, explicit what/when structure, and third-person voice. Trigger coverage is good but misses a few natural phrasings, and capability coverage centers on one action.

Suggestions

Add natural trigger variations users commonly say, e.g. 'make a commit', 'git commit', or 'commit these changes'.

Mention a second concrete capability explicitly (e.g. 'analyzes the staged diff to draft the message') to round out capability coverage.

DimensionReasoningScore

Specificity

The description names concrete, parameterized capabilities ('Ultra-compressed commit message generator', 'Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious'), but describes a single core action with format constraints rather than several distinct actions, which is the anchor-5 pattern.

4 / 5

Completeness

It explicitly answers both what it does (generate ultra-compressed Conventional Commits messages with subject ≤50 chars) and when to use it, with a 'Use when...' clause listing concrete trigger phrases plus auto-trigger guidance.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('write a commit', 'commit message', 'generate commit', '/commit', 'staging changes'), but common variations users actually say such as 'make a commit' or 'git commit' are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (commit-message generation) with distinct, domain-specific triggers closely matching the rubric's own good example ('Generate descriptive commit messages by analyzing git diffs'); minimal overlap with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

masweb/waxp-vuebo

Path

.agents/skills/caveman-commit/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.