caveman-review
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
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 a strong skill description that clearly communicates its unique value proposition: ultra-compressed, noise-free code review comments in a specific one-line format. It includes comprehensive trigger terms covering natural language variations and slash commands, and explicitly states both what it does and when to use it. The distinctive format and naming make it unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions: cuts noise from PR feedback, preserves actionable signal, formats each comment as one line with location/problem/fix. Describes a specific output format and methodology. | 3 / 3 |
Completeness | Clearly answers both what (ultra-compressed code review comments with location/problem/fix format) 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: 'review this PR', 'code review', 'review the diff', '/review', '/caveman-review', 'pull requests'. These are terms users would naturally say when requesting code reviews. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with its unique 'caveman-review' slash command and specific niche of ultra-compressed, one-line code review comments. The format constraint (location, problem, fix) clearly differentiates it from general code review 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 skill that exemplifies concise, actionable instruction design. The format specification is precise, the examples powerfully demonstrate the before/after transformation, and the edge cases (Auto-Clarity exceptions, Boundaries) are handled cleanly. The skill respects Claude's intelligence throughout—no concept explanations, no hedging, just the delta information needed to produce the desired output.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No explanation of what code review is, no padding. The examples are the longest part and they serve a clear purpose—showing the before/after transformation. The severity prefixes are compact tables. The 'Drop' and 'Keep' lists are tight and actionable. | 3 / 3 |
Actionability | The format template (`L<line>: <problem>. <fix>.`) is concrete and copy-paste ready. The before/after examples are specific and executable. The severity prefixes, drop/keep lists, and boundary conditions give Claude everything needed to produce correct output without ambiguity. | 3 / 3 |
Workflow Clarity | This is a single-task skill (produce terse review comments) with a clear, unambiguous output format. The Auto-Clarity section handles the one important branching condition (when to drop terse mode). The Boundaries section clearly scopes what the skill does and doesn't do. No multi-step destructive operations require validation checkpoints. | 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) with clear headers. No monolithic walls of text, no 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
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.