CtrlK
BlogDocsLog inGet started
Tessl Logo

caveman-review

Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 content is an exemplar of terse, high-signal skill writing: a concrete format, exact examples, and clear scope boundaries with no padding. It scores near the top on conciseness, actionability, and disclosure, with only a slight workflow-clarity gap from lacking explicit validation checkpoints.

DimensionReasoningScore

Conciseness

The body is lean throughout — terse rules, minimal prose, no re-explanation of concepts Claude already knows, and every line earns its place (e.g. 'No throat-clearing.'), matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

It gives a concrete copy-paste format ('L<line>: <problem>. <fix>.'), exact severity prefixes, and three full before/after examples with concrete fixes like 'Add guard before .email' and 'Wrap in withBackoff(3)', fully executable guidance covering common cases.

5 / 5

Workflow Clarity

The single task is unambiguous and the Auto-Clarity and Boundaries sections sequence when to drop terse mode, but there are no explicit validation checkpoints for the review output itself; this is a minor gap rather than the explicit feedback-loop structure of the 5 anchor.

4 / 5

Progressive Disclosure

This is a short single-purpose skill under 50 lines with no external bundle files (references/scripts/assets are absent), and it is organized into clearly labeled sections (Rules, Examples, Auto-Clarity, Boundaries), so the simple-skill exception gives it a 5.

5 / 5

Total

19

/

20

Passed

Description

83%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.

The description is concise, third-person, and cleanly answers both what the skill does and when to use it with natural trigger phrases. It is mostly specific and distinct, with only minor gaps in trigger synonym coverage and a slight overlap risk with generic review requests.

DimensionReasoningScore

Specificity

The phrase 'Compressed code review - one line per finding with location, problem and fix' names a clear domain (code review) and three concrete actions (location, problem, fix), matching the 'several specific actions; minor gaps' anchor rather than the comprehensive 5 anchor which requires more enumerated actions.

4 / 5

Completeness

It explicitly answers 'what' (compressed one-line code review comments) and 'when' ("Use for /caveman-review, \"review this PR\", or \"review the diff\"") with concrete trigger phrases, matching the anchor that clearly answers both what and when.

5 / 5

Trigger Term Quality

Natural trigger phrases like '"review this PR"' and '"review the diff"' are included alongside the /caveman-review command, giving good keyword coverage, but it misses common variations like 'code review' as a bare phrase or 'look at these changes', keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The terse one-line-per-finding format and /caveman-review trigger carve a distinct niche, but 'review this PR'/'review the diff' overlap with general review skills, so minor overlap risk remains rather than the minimal-conflict 5 anchor.

4 / 5

Total

17

/

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.

Validation16 / 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.