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.
80
100%
Does it follow best practices?
Impact
—
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 clearly communicates what the skill does (generates ultra-compressed commit messages in Conventional Commits format with specific constraints) and when to use it (with explicit trigger phrases and auto-trigger conditions). It uses third-person voice, is concise without being vague, and has strong distinctiveness through its specific style and unique command triggers.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: generates commit messages, cuts noise while preserving intent/reasoning, uses Conventional Commits format, enforces subject ≤50 chars constraint, includes body only when 'why' isn't obvious. | 3 / 3 |
Completeness | Clearly answers both 'what' (ultra-compressed commit message generator with Conventional Commits format, subject ≤50 chars, body only when needed) 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', and 'staging changes'. These are 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, Conventional Commits). The unique '/caveman-commit' command and specific formatting constraints make it 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 token efficiency while remaining fully actionable. The rules are precise, the examples demonstrate both good and bad patterns with realistic commit messages, and the boundaries section clearly constrains Claude's behavior. The only minor note is the time-sensitive date in the breaking change example (2026-06-01), but it serves as a realistic example rather than actual guidance, so it doesn't detract.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line earns its place. No explanation of what Conventional Commits is or how git works. The rules are terse, the examples show don't tell, and anti-patterns are listed as compact bullet points rather than paragraphs. | 3 / 3 |
Actionability | Provides exact format templates, concrete type lists, specific examples with good/bad comparisons, and clear output expectations (code block ready to paste). The examples are copy-paste ready commit messages with realistic diffs. | 3 / 3 |
Workflow Clarity | This is a single-task skill (generate a commit message) with an unambiguous workflow: read diff → apply rules → output code block. The decision tree for when to include a body is explicit, and the 'Auto-Clarity' section provides clear mandatory-body triggers. No destructive operations are involved, so no validation checkpoints are needed. | 3 / 3 |
Progressive Disclosure | For a standalone 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. No bundle files are needed and none are referenced incorrectly. | 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
63a91ec
- 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.