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 the prp-review skill.

Quality

85%

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

70%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 a highly actionable, well-sequenced multi-phase review workflow with strong validation and checkpoints. Its main weaknesses are length/redundancy and broken progressive-disclosure references to bundle files that do not exist.

Suggestions

Add the referenced `workflows/agents.md` and `templates/review-report.md` bundle files (or remove the references and inline only the essential multi-agent/report details), since the body currently points to files that are absent.

Trim the redundant 'Critical Reminders' and 'Success Criteria' sections that restate the Phase 3 checklist and per-phase checkpoints, or fold them into a single concise wrap-up to reduce token cost.

Consider moving the full Phase 6 report template into `templates/review-report.md` (which the text already names) so the main SKILL.md body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable with little concept-padding, but at ~570 lines it carries redundancy — the 'Critical Reminders' and 'Success Criteria' sections restate the Phase 3 checklist and phase checkpoints — so it could be tightened to respect the token budget.	2 / 3
Actionability	It provides concrete, executable guidance throughout: real `gh` commands, a complete report-template skeleton with placeholders, and decision tables, which is copy-paste ready rather than abstract.	3 / 3
Workflow Clarity	The 8 phases are clearly sequenced, each closes with an explicit `PHASE_N_CHECKPOINT` checklist, and Phase 4 provides a validation feedback loop feeding the Phase 5 decision logic, matching the 'clear sequence with explicit validation steps and checklists' anchor.	3 / 3
Progressive Disclosure	The body points to `workflows/agents.md` and `templates/review-report.md` for offloaded detail, but neither file nor directory exists in the bundle, so the references are broken; the main body is also a monolithic wall rather than appropriately split.	1 / 3
	Total	9 / 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 specific, third-person, and explicitly covers both capabilities and trigger conditions with natural user phrasing. It is a strong, concise description with no notable over-claims or fluff.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('checks diff, patterns, runs validation, comments on PR') and enumerates the fan-out aspects, matching the 'lists multiple specific concrete actions' anchor; it does not stop at naming only the domain.	3 / 3
Completeness	It explicitly answers both what (checks diff, patterns, validation, comments) and when via an explicit 'Use when...' trigger clause, so neither half is missing or merely implied.	3 / 3
Trigger Term Quality	It uses natural phrasings a user would actually say ('review a pull request', 'wants a thorough/multi-agent review', 'invokes the prp-review skill'), giving good coverage of common variations rather than jargon.	3 / 3
Distinctiveness Conflict Risk	It carves a clear PR-review niche with distinct triggers and names its own skill ('prp-review'), making it 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 (576 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Wirasm/prp
Path: profiles/kild/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.