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.

78

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary terse instruction skill: every section earns its tokens, the output format and severity scheme are concrete and copy-pasteable, and the Auto-Clarity and Boundaries sections crisply scope exceptions without bloat. As a simple single-purpose skill under 50 lines with no bundle files, it satisfies the simple-skill exceptions for workflow clarity and progressive disclosure.

DimensionReasoningScore

Conciseness

Lean imperative prose with no explanation of concepts Claude already knows ('Write code review comments terse and actionable. One line per finding.'); even the verbose ❌ examples earn their place by demonstrating what to drop.

5 / 5

Actionability

Copy-paste-ready output template (`L<line>: <problem>. <fix.>`), defined severity prefixes, explicit drop/keep lists, and three before/after example pairs covering bug, risk, and nit cases.

5 / 5

Workflow Clarity

A simple single-purpose skill whose single action (produce terse one-line review comments) is unambiguous; per the simple-skill exception this scores 5, and the Auto-Clarity section cleanly scopes the exception.

5 / 5

Progressive Disclosure

Under 50 lines with no external references needed and well-organized sections (Rules, Examples, Auto-Clarity, Boundaries); per the simple-skill exception this scores 5.

5 / 5

Total

20

/

20

Passed

Description

95%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.

A tight, well-constructed description that crisply states what the skill produces, when it should trigger, and includes both natural phrases and a named slash command. The only minor gap is that the 'what' describes one capability in detail rather than enumerating multiple distinct actions.

Suggestions

To lift specificity, name one or two additional concrete capabilities (e.g., 'classifies severity as bug/risk/nit', 'switches to verbose mode for security findings') so the 'what' reads as multiple distinct actions.

DimensionReasoningScore

Specificity

Names the domain ('Ultra-compressed code review comments') and concrete facets ('Cuts noise from PR feedback', 'preserving the actionable signal', 'one line: location, problem, fix'), but these are aspects of a single capability rather than multiple distinct actions, so it sits just below the comprehensive multi-action anchor.

4 / 5

Completeness

Explicitly answers both what (ultra-compressed one-line comments with location/problem/fix) and when, with concrete quoted trigger phrases and an auto-trigger statement.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including synonyms and variations — 'review this PR', 'code review', 'review the diff', '/review', '/caveman-review', and 'reviewing pull requests'.

5 / 5

Distinctiveness Conflict Risk

Clear niche (ultra-compressed/terse PR review) with a unique named slash command (/caveman-review) and specific triggers, giving minimal conflict risk with general review skills.

5 / 5

Total

19

/

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.