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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

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: concrete, executable guidance with worked examples, clear conditional rules, and explicit boundaries — all within a tight, well-structured layout that assumes Claude's competence.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — terse rules, no explanation of concepts Claude already knows (Conventional Commits, git), every line earns its place. Not the level-2 case with unnecessary padding.	3 / 3
Actionability	Gives the exact format '<type>(<scope>): <imperative summary>', a concrete type list, char caps, and fully worked before/after examples that are copy-paste ready.	3 / 3
Workflow Clarity	Single-purpose skill whose one action (produce the message) is unambiguous, with conditional 'Auto-Clarity' guidance for high-stakes cases; it deliberately does not run destructive git operations, so no validation loop is required.	3 / 3
Progressive Disclosure	Well-organized into clear sections (Rules, Examples, Auto-Clarity, Boundaries) with no nested references; the single task needs no external bundle, and no references/ scripts/ assets/ files exist to verify.	3 / 3
	Total	12 / 12 Passed

Description

100%

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 lean and high-quality: concrete capabilities, explicit natural-language triggers, third-person voice, and a clearly bounded niche. It answers both 'what' and 'when' without fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Cuts noise from commit messages while preserving intent', 'Conventional Commits format', 'Subject ≤50 chars', 'body only when "why" isn't obvious' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly states what the skill does and includes an explicit 'Use when...' clause with concrete triggers plus auto-trigger conditions; not the level-2 case that lacks the when.	3 / 3
Trigger Term Quality	Strong coverage of natural phrasings a user would actually say — 'write a commit', 'commit message', 'generate commit', '/commit', '/caveman-commit', 'staging changes'.	3 / 3
Distinctiveness Conflict Risk	Clear niche (terse commit-message generation) with distinct, commit-specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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
Commit: 0d95a81

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.