CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

76

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

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.

An exceptionally tight, actionable skill body that gives Claude exact formatting rules and concrete examples while assuming its competence. The only nit is that progressive disclosure sits just past the simple-skill line, though no external references are needed.

Suggestions

Consider trimming the body slightly or splitting the extended examples into a short Examples reference file to bring it within the simple-skill threshold and strengthen progressive disclosure.

The Auto-Clarity section overlaps somewhat with the Body rules; merging them could reduce redundancy and tighten the structure further.

DimensionReasoningScore

Conciseness

Lean and efficient throughout ('Write commit messages terse and exact. Conventional Commits format. No fluff. Why over what.'); assumes Claude's knowledge of git and diffs with every token earning its place.

5 / 5

Actionability

Fully executable guidance: concrete format spec ('<type>(<scope>): <imperative summary>'), enumerated types, char limits, body rules, and copy-paste-ready examples with ✅/❌ covering common cases.

5 / 5

Workflow Clarity

Single-purpose skill whose single action (output the message as a code block) is unambiguous; Boundaries section explicitly excludes destructive side effects ('does not run git commit, does not stage files'), so the destructive-cap does not apply.

5 / 5

Progressive Disclosure

Well-organized into clear sections (Rules, Examples, Auto-Clarity, Boundaries) with no need for external references, but the body slightly exceeds the 50-line simple-skill threshold, leaving minor organization gaps versus an ideal overview.

4 / 5

Total

19

/

20

Passed

Description

91%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, specific description that clearly states what the skill does and when to use it, with excellent trigger-term coverage. Only marginal overlap risk with generic commit helpers and slightly less-than-comprehensive action enumeration keep it from a perfect score.

DimensionReasoningScore

Specificity

Lists several specific actions and concrete constraints ('Cuts noise', 'preserving intent and reasoning', 'Conventional Commits format', 'Subject ≤50 chars', 'body only when "why" isn't obvious'), with only minor coverage gaps versus a fully comprehensive action list.

4 / 5

Completeness

Explicitly answers both what ('Ultra-compressed commit message generator...') and when ('Use when user says...', 'Auto-triggers when staging changes') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and invocation forms: 'write a commit', 'commit message', 'generate commit', '/commit', '/caveman-commit', and 'staging changes'.

5 / 5

Distinctiveness Conflict Risk

Clear niche (terse Conventional Commits generation) with distinct slash-command triggers; minor overlap risk remains with broader commit-helper skills.

4 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
juliusbrussee/caveman
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.