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.

The body is highly actionable with a well-sequenced, checkpointed workflow and executable commands. Its weak spots are length that could be trimmed and inlined/broken external references that hurt progressive disclosure.

Suggestions

Move the Phase 6 report template and the multi-agent flow into real bundle files (templates/review-report.md, workflows/agents.md) and link to them instead of inlining, so the referenced paths actually exist.

Consolidate the recurring type-check/lint/test/build commands into a single validation section referenced from Phase 4 to reduce repetition and trim tokens.

Tighten the inline markdown templates (report and final output) to the essential fields, since Claude can expand standard formatting.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and tables, but it is long — validation commands recur across phases and the full report template is inlined — so it could be tightened.	2 / 3
Actionability	Provides executable gh/npm/bun/npx commands, copy-paste-ready report and output templates, and specific decision tables — fully concrete and actionable.	3 / 3
Workflow Clarity	A clear 8-phase sequence with an explicit PHASE_N_CHECKPOINT after each phase, a validation suite, and decision logic with feedback loops, matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	It references workflows/agents.md and templates/review-report.md, but those bundle files are absent and the large report template is inlined rather than split out, fitting the 'content that should be separate is inline' anchor.	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.

The description is concrete, third-person, and pairs a clear what-with an explicit when/trigger clause, hitting all anchors at the top level. It is slightly CLI-flag-flavored but remains natural enough to score full marks.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'checks diff, patterns, runs validation, comments on PR' — plus an enumerated specialist fan-out (comments, tests, errors, types, code, docs, simplify), matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both what (review steps) and when via an explicit 'Use when the user wants to review a pull request, wants a thorough/multi-agent review, or invokes $prp-review' clause.	3 / 3
Trigger Term Quality	Natural user phrasings like 'wants to review a pull request' and 'wants a thorough/multi-agent review' plus the explicit '$prp-review' invocation give good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped to PR code review via gh with distinct triggers, occupying a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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
skill_md_line_count	SKILL.md is long (574 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Wirasm/prp
Path: .agents/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.