CtrlK
BlogDocsLog inGet started
Tessl Logo

caveman-commit

Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.

72

Quality

88%

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

93%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.

The body is a tight, highly actionable commit-message spec with concrete templates, real-diff examples, and explicit inclusion/exclusion checklists, all without padding. Its only weak spot is that guidance is rule-list rather than sequenced-workflow, leaving a minor validation-checkpoint gap.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence ("Write commit messages terse and exact. Conventional Commits format. No fluff. Why over what.") with no padding or explanations of concepts Claude already knows, matching the anchor for 5.

5 / 5

Actionability

Provides a concrete subject-line template, an enumerated type list, hard char limits, copy-paste-ready example blocks tied to real diffs, and explicit inclusion/exclusion rules — fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

Rules and the Auto-Clarity always-include checklist give a clear, unambiguous single-purpose process, but it is presented as a rule list rather than a sequenced workflow with an explicit verify/checkpoint feedback loop, fitting 4 more than 5.

4 / 5

Progressive Disclosure

The skill is short, single-purpose, and has no need for external bundle files (none exist); its well-organized sections (Rules, Examples, Auto-Clarity, Boundaries) satisfy the simple-skill exception for a top progressive-disclosure score.

5 / 5

Total

19

/

20

Passed

Description

82%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.

The description is concise, third-person imperative, and explicitly pairs a clear 'what' with concrete 'when' triggers including custom slash commands. It is strong on completeness and distinctiveness, with only minor gaps in trigger synonym coverage and the single-action specificity.

DimensionReasoningScore

Specificity

Names the domain (Conventional Commits) and one concrete action ("Write a Conventional Commits message compressed to intent only"), but coverage is a single action rather than multiple, fitting the anchor for 3 rather than the several-actions anchor for 4.

3 / 5

Completeness

Explicitly answers both what ("Write a Conventional Commits message compressed to intent only") and when ("Use for 'write a commit', 'commit message', /commit or /caveman-commit") with concrete trigger phrases, matching the anchor for 5.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ("write a commit", "commit message") plus slash-command triggers (/commit, /caveman-commit), giving good keyword coverage, though a few synonyms like "git commit" are absent.

4 / 5

Distinctiveness Conflict Risk

The niche (Conventional Commits compressed to intent only) with its own slash commands is a clear, distinct trigger surface with minimal overlap risk against generic git or documentation skills.

5 / 5

Total

17

/

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.