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

89%

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

100%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 an exemplary terse instruction skill: dense rule specification, concrete executable examples including a counter-example and a breaking-change case, explicit body-inclusion conditions, and clear non-execution boundaries. Every dimension lands on the top anchor.

DimensionReasoningScore

Conciseness

The body is lean and imperative ('No fluff. Why over what.'), assumes Claude already knows Conventional Commits and never explains it, and every rule earns its place. The only date ('before 2026-06-01') is illustrative content inside an example commit body rather than rotting instructional guidance, so it does not warrant a penalty — anchor 5 applies.

5 / 5

Actionability

Gives an exact subject template ('<type>(<scope>): <imperative summary>'), the full type list, character limits, and a wrong/right example pair plus a complete breaking-change example with BREAKING CHANGE trailer. The guidance is copy-paste ready and covers the common cases, matching anchor 5; as an instruction-only skill, absence of code is not penalized per the scoring notes.

5 / 5

Workflow Clarity

This is a simple single-purpose skill and the single action is unambiguous: generate the message and 'Output the message as a code block ready to paste.' The Auto-Clarity section gives explicit conditions for when a body is mandatory and the Boundaries section excludes execution, staging, and amending, so the simple-skill exception to anchor 5 applies. No destructive or batch operation exists, so the validation cap does not.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed for a ~57-line skill; the body is organized into clear one-level sections (Rules, Examples, Auto-Clarity, Boundaries) with nothing that should be split into a separate file. Navigation is trivial, matching the well-organized-sections condition for anchor 5.

5 / 5

Total

20

/

20

Passed

Description

78%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 that clearly and explicitly states both what the skill does and when to use it, with natural trigger phrases and third-person voice. The main weaknesses are limited enumeration of concrete capabilities and trigger terms that overlap with generic commit-message helpers.

Suggestions

Add one or two more concrete capability phrases to the 'what' clause (e.g., 'subject, body, and breaking-change trailers') to raise specificity beyond a single action.

Include additional natural trigger variants such as 'git commit' or 'make a commit' so keyword coverage reaches users who phrase the request differently.

DimensionReasoningScore

Specificity

The description names the domain ('Conventional Commits message') and one concrete action ('Write... compressed to intent only') but does not enumerate the skill's capabilities such as subject/body structure, breaking-change handling, or the terse-style constraint. It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than anchor 4, which expects several specific actions listed.

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. This directly matches the anchor-5 example structure; the when-clause is present and specific, so it is not capped at 3.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('write a commit', 'commit message') plus slash-command triggers (/commit, /caveman-commit), which is good coverage. It falls short of anchor 5 because common variations like 'git commit', 'make a commit', or 'commit this' are missing.

4 / 5

Distinctiveness Conflict Risk

The Conventional-Commits-with-intent-compression framing is a clear niche with dedicated slash-command triggers, but generic triggers like 'write a commit' overlap with any general commit-message skill. It fits anchor 4 (mostly distinct, minor overlap risk with closely related skills) rather than anchor 5's minimal conflict risk.

4 / 5

Total

16

/

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
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.