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.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that hits all the marks. It provides specific capabilities (compressed commit messages, Conventional Commits format, character limits), explicit trigger terms covering natural user phrases, and a clear 'Use when' clause. The distinctive 'caveman-commit' branding and precise formatting constraints make it easily distinguishable from other potential commit-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: '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'. These are highly specific and actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (compressed commit message generator with Conventional Commits format, subject ≤50 chars, body only when why isn't obvious) and 'when' (explicit 'Use when...' clause with multiple trigger phrases plus auto-trigger condition). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'write a commit', 'commit message', 'generate commit', '/commit', '/caveman-commit', 'staging changes'. These are exactly the phrases users would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: commit message generation with a specific style (ultra-compressed, caveman). The unique '/caveman-commit' command and specific formatting constraints (≤50 chars) make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent, tightly written skill that exemplifies what a good SKILL.md should be. It's concise without sacrificing clarity, provides concrete examples with anti-patterns, and clearly bounds its scope. The rules are specific and actionable, and the structure makes it easy to reference any particular aspect quickly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line earns its place. No explanation of what commits are or how git works. Rules are terse bullet points. The 'What NEVER goes in' section is particularly efficient—it teaches by anti-pattern without belaboring the point. | 3 / 3 |
Actionability | Provides concrete examples with both ❌ and ✅ patterns, specific format rules (≤50 chars, 72 hard cap, imperative mood), exact type list, and copy-paste-ready commit message examples. The boundaries section clearly defines what the skill does and doesn't do. | 3 / 3 |
Workflow Clarity | This is a single-task skill (generate a commit message), and the workflow is unambiguous: read the diff, apply the rules, output a code block. The 'Auto-Clarity' section acts as a validation checkpoint for when body is mandatory. The 'Boundaries' section clearly scopes the operation. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is well-organized into logical sections (Rules, Examples, Auto-Clarity, Boundaries) that are easy to scan and navigate. No monolithic walls of text or unnecessary nesting. | 3 / 3 |
Total | 12 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- JuliusBrussee/caveman
- Commit
8bab5c7
- 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.