CtrlK
BlogDocsLog inGet started
Tessl Logo

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

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An efficient, highly actionable instruction skill: concrete format, severity taxonomy, worked examples, and explicit scope boundaries, all in a compact well-organized body. No bundle files are present or needed.

DimensionReasoningScore

Conciseness

Lean throughout: terse rules, a one-line format spec, and tight before/after examples with no explanation of concepts Claude already knows; every line earns its place.

3 / 3

Actionability

Provides a concrete copy-paste format `L<line>: <problem>. <fix>.`, specific severity prefixes, and worked before/after examples showing exact output — fully executable guidance.

3 / 3

Workflow Clarity

A simple single-task skill whose action is unambiguous: the Drop/Keep lists, examples, and Auto-Clarity exceptions give a clear decision path, and the non-destructive review task needs no validation checkpoint.

3 / 3

Progressive Disclosure

Under 50 lines with no bundle files, organized into clear labeled sections (Rules, Examples, Auto-Clarity, Boundaries); per the simple-skills note this scores 3 without external references.

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.

A tight, well-constructed description that states the concrete capability, the output format, and explicit natural-language triggers in third person. It satisfies the what-and-when requirement with no fluff.

DimensionReasoningScore

Specificity

Names concrete actions and a concrete output format: 'Ultra-compressed code review comments', 'Each comment is one line: location, problem, fix' — multiple specific actions, matching the top anchor.

3 / 3

Completeness

Explicitly answers both what (compressed one-line review comments) and when via an explicit 'Use when user says...' clause with concrete triggers.

3 / 3

Trigger Term Quality

Lists natural phrases a user would say — 'review this PR', 'code review', 'review the diff', '/review', plus the /caveman-review invocation — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (terse review-comment format) with distinct triggers unlikely to fire for unrelated skills; uses third-person voice throughout.

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.

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.