code-review

Perform a pedantic, multi-perspective code review on the current diff or git changes against the styleguide and software engineering best practices.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/code-review/SKILL.md

Quality

Content

75%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 body is a well-structured, actionable instruction skill with concrete commands, a clear severity taxonomy, and a sensible multi-pass workflow. It is concise and assumes Claude's competence, with only minor trimming and validation-loop opportunities.

Suggestions

Tighten the Step 1 sub-agent delegation logic and the IMPORTANT blockquote to lift conciseness toward 5.

Add a short worked example of the expected review output (tagged comments with file/line references) to make actionability copy-paste ready.

Add an explicit final validation step (e.g., confirm comments cite file/line and use a valid tag) to give the workflow a clear feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is efficient and avoids explaining concepts Claude already knows (no 'what is a git diff' padding), but the sub-agent delegation logic in Step 1 and the IMPORTANT blockquote add some length that could be trimmed; not a 5 because of those minor over-explanation instances.	4 / 5
Actionability	Provides concrete, executable guidance such as `git diff`, regex `^[0-9]+$`, and specific bash parameter-expansion examples (`${var##*/}`, `$(< file)`, `grep -F`), plus concrete severity tags; not a 5 because it lacks a worked example of the actual review output format.	4 / 5
Workflow Clarity	A clear numbered Step-by-Step Execution sequence (pre-flight, context-gathering, analysis) with a branching checkpoint for the sub-agent decision; not a 5 because there is no explicit validation/feedback loop confirming the review output before delivery.	4 / 5
Progressive Disclosure	Well-organized with clear section headers (Context, Review Protocol, Multi-Perspective Review Checklist with three passes, Step-by-Step Execution) and a clearly signaled reference to `.gemini/styleguide.md`; not a 5 because no bundle files exist and content is self-contained, placing it just below the cleanly-split ideal.	4 / 5
	Total	16 / 20 Passed

Description

66%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 clearly states what the skill does and uses natural, specific terms, but it omits any explicit 'Use when...' trigger guidance, which caps completeness. It is distinct and largely free of fluff.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to review uncommitted changes, a git diff, or a pull request for defects, security issues, or style violations.'

Enumerate the concrete defect categories the review covers (logic bugs, security vulnerabilities, resource leaks, style violations) to lift specificity from 4 to 5.

Include common trigger synonyms like 'pull request', 'PR', or 'review my code' to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'pedantic, multi-perspective code review on the current diff or git changes against the styleguide and software engineering best practices' name the domain plus several concrete actions (multi-perspective review, diff/git changes, styleguide, best practices), with minor gaps in not enumerating specific defect types; not a 5 because coverage is broad rather than enumerated.	4 / 5
Completeness	Has a clear 'what' but no explicit 'Use when...' trigger clause, so per the boundary guidance a missing trigger clause caps completeness at 3; 'when' is only weakly implied by the actions.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('code review', 'diff', 'git changes', 'styleguide') but misses common synonyms like 'pull request', 'PR', or 'review my code'; good coverage with a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (code review of the current diff against a styleguide) with distinct triggers and minimal conflict risk; not a 5 only because the lack of explicit trigger phrases leaves minor overlap risk with general review skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: flutter/flutter-intellij
Path: .agents/skills/code-review/SKILL.md
Commit: 01f1775

Reviewed: about 14 hours 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.