review-guidelines

Repository-specific Cerebro review invariants and triage guidance for Droid code and security reviews.

0.98x

Quality

—

Does it follow best practices?

Impact

90%

0.98x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

87%

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

The content is a lean, highly actionable set of review invariants and triage rules with concrete commands and a sequenced pass workflow. The only gap is implicit per-pass validation checkpoints rather than explicit gates.

Dimension	Reasoning	Score
Conciseness	The body is dense with repo-specific facts and assumes Claude's competence, with no padding or explanation of concepts Claude already knows; every bullet carries actionable signal.	3 / 3
Actionability	It gives copy-paste-ready commands ('make droid-review-preflight', 'make droid-review-sast', 'make droid-ci-context', 'scripts/droid_review_context.py') plus concrete file locations and a named set of review passes, which is fully executable guidance for an instruction-only skill.	3 / 3
Workflow Clarity	Passes are sequenced ('execute passes in order') with a general validation rule ('validate every claim against changed code'), but per-pass validation checkpoints are implicit and there is no explicit validate-fix-retry feedback loop between passes.	2 / 3
Progressive Disclosure	The under-50-line body is cleanly split into 'Known Invariants' and 'Review Triage' sections with one-level-deep pointers to runtime files, satisfying the simple-skill allowance for well-organized content.	3 / 3
	Total	11 / 12 Passed

Description

57%

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 well-scoped to a distinct internal niche but reads as a noun-phrase label rather than a triggered capability statement. It lacks an explicit 'Use when...' clause and leans on jargon over natural user terms.

Suggestions

Add an explicit trigger clause, e.g. 'Use when running Droid code or security reviews on this repository.'

Replace some jargon with natural phrasings a user would say (e.g. 'code review', 'security review', 'triage findings') to improve trigger term coverage.

Name concrete actions the skill performs (e.g. 'enforces review invariants, triages findings by pass, and cites the local command that catches each bug') to lift specificity.

Dimension	Reasoning	Score
Specificity	It names the domain ('Droid code and security reviews') and two functions ('review invariants and triage guidance'), but does not list multiple concrete actions like the score-3 anchor; it stops at naming domain plus a couple of activities.	2 / 3
Completeness	It states what the skill provides ('invariants and triage guidance'), but the 'when' is only implied by 'for Droid code and security reviews' with no explicit 'Use when...' trigger clause, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Natural terms like 'review', 'code', 'security reviews', and 'triage' are present, but the description is dominated by internal jargon ('Cerebro', 'Droid', 'invariants') and misses common user phrasings.	2 / 3
Distinctiveness Conflict Risk	The 'Repository-specific Cerebro' and 'Droid' scoping carves out a clear niche tied to a named internal system, making it unlikely to trigger for unrelated review skills.	3 / 3
	Total	9 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: writer/cerebro
Commit: f4c73ab

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.