prp-review

Comprehensive PR code review - checks diff, patterns, runs validation, comments on PR. Single-pass by default; pass --agents for a multi-agent specialist fan-out (comments, tests, errors, types, code, docs, simplify). Use when the user wants to review a pull request, wants a thorough/multi-agent review, or invokes /prp-review.

Quality

88%

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

77%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced multi-phase workflow with strong validation checkpoints, but it is let down by padding (generic review-principle coaching Claude already knows) and references to bundle files (workflows/agents.md, templates/review-report.md) that are not actually present.

Suggestions

Trim or remove the 'Critical Reminders' section - guidance like 'Be constructive', 'Acknowledge good work', and 'Think about edge cases' restates review fundamentals Claude already applies.

Provide the referenced workflows/agents.md and templates/review-report.md bundle files, or move the inline Phase 6 report template into templates/review-report.md so the signaled references resolve.

Move the verbose Phase 6 report template out of SKILL.md into the referenced template file to tighten the body and let SKILL.md serve as an overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-structured, but the 'Critical Reminders' section coaches Claude on basic review principles it already knows ('Understand before judging', 'Be constructive', 'Acknowledge good work', 'Think about edge cases'), and the full ~100-line inline report template pads the body.	2 / 3
Actionability	Provides concrete, executable commands throughout - gh pr view/diff/checkout, npm run type-check/lint/test/build, gh pr review/comment - plus a copy-paste-ready report template and specific decision logic.	3 / 3
Workflow Clarity	An explicit 8-phase sequence (FETCH through OUTPUT) each ending in a PHASE_N_CHECKPOINT checklist, with Phase 4 running validation and Phase 5 decision logic providing clear feedback loops for the review process.	3 / 3
Progressive Disclosure	References are clearly signaled ('follow workflows/agents.md', 'see templates/review-report.md') but neither file exists in the bundle, breaking navigation, and the large inline report template is content that should live in the referenced template file.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that covers concrete capabilities, natural trigger terms, explicit use-when guidance, and a distinct niche. Voice is correctly third person throughout with no first/second-person slips.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions - 'checks diff, patterns, runs validation, comments on PR' plus a named specialist fan-out (comments, tests, errors, types, code, docs, simplify) - rather than vague language.	3 / 3
Completeness	Explicitly answers both: what it does ('Comprehensive PR code review - checks diff, patterns, runs validation, comments on PR') and when to use it via a clear 'Use when the user wants to review a pull request...' clause.	3 / 3
Trigger Term Quality	Uses natural phrasing a user would actually say - 'review a pull request', 'thorough/multi-agent review', and the /prp-review invocation - giving good keyword coverage.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear PR-code-review niche with distinct triggers (/prp-review, 'review a pull request') that are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (573 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Wirasm/prp
Path: .claude/skills/prp-review/SKILL.md
Commit: 1142738

Reviewed: 11 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.