review

Use when asked to review code, review a branch, or do a code review. Spawns Breaker (correctness) and API Analyst (compatibility/conventions) sub-agents while the orchestrator reviews architecture, tests, performance, and security.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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.

A well-structured, highly actionable multi-step review workflow with strong validation checkpoints and concrete commands. Its main weakness is progressive disclosure: the content is largely inline and references an api-conventions.md file that is absent from the bundle.

Suggestions

Add the referenced api-conventions.md to the skill's references/ directory (or remove the 'cat .claude/skills/review/api-conventions.md' instruction) so the bundle is self-contained and the reference is not dangling.

Extract the large report template and the Breaker/API Analyst persona blocks into a references/ file, keeping SKILL.md as a lean overview that links to them one level deep.

Tighten the persona quotes (Breaker/API Analyst) to a few bullet-pointed mindset prompts to reduce token weight while preserving the behavioral framing.

Dimension	Reasoning	Score
Conciseness	Dense, operational guidance that assumes Claude's competence (no explanations of git/diff basics), though the multi-line persona quotes for Breaker and API Analyst could be trimmed without losing intent.	4 / 5
Actionability	Fully executable: copy-paste bash commands ('git diff --stat', 'git ls-files --others --exclude-standard'), a concrete report template, explicit severity/promotion tables, and a fixed output format cover the common cases.	5 / 5
Workflow Clarity	Steps 1–9 are clearly sequenced with explicit validation gates (empty-diff, size, no-code, high-confidence checklist), verdict rules, and an Edge Cases section providing error-recovery guidance.	5 / 5
Progressive Disclosure	The body has clear section headers and signals referenced files by name, but the procedure is a monolithic ~330-line inline block and the referenced api-conventions.md is not present in the skill's bundle, leaving a dangling reference.	3 / 5
	Total	17 / 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.

A strong, concrete description that clearly states both what the skill does and when to invoke it, with natural trigger phrasing and a distinctive multi-agent design. Minor improvements could add synonyms like 'PR review' and mention report output.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Spawns Breaker (correctness) and API Analyst (compatibility/conventions) sub-agents while the orchestrator reviews architecture, tests, performance, and security' — covering the major review activities, with only minor gaps (e.g., no mention of report generation).	4 / 5
Completeness	Explicitly answers both what ('Spawns Breaker ... and API Analyst ... orchestrator reviews architecture, tests, performance, and security') and when ('Use when asked to review code, review a branch, or do a code review') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases users would say are present ('review code', 'review a branch', 'do a code review'), but a few common synonyms like 'pull request' or 'PR review' are missing.	4 / 5
Distinctiveness Conflict Risk	The multi-agent orchestration niche (Breaker + API Analyst + Inspector) is distinctive, though the trigger terms 'review code / code review' overlap somewhat with a generic code-review skill.	4 / 5
	Total	17 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: microsoft/FluidFramework
Path: .claude/skills/review/SKILL.md
Commit: f02e424

Reviewed: 3 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.