parallel-pr-review

Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.

Quality

96%

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

92%

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

An actionable, concisely written, well-sequenced workflow with concrete commands and explicit validation checkpoints for a risky batch operation. Its one weakness is progressive disclosure: a long single-file body where the prompt template and maintainability lens could be split into referenced files if a bundle were provided.

Suggestions

If a bundle is permitted, move the full 'Subagent prompt template' and/or the 'Maintainability lens' into one-level reference files (e.g. references/review-prompt.md, references/maintainability-lens.md) and link to them from a leaner overview so progressive disclosure reaches the 3-anchor.

Even without a bundle, consider tightening the 'Maintainability lens' to its operational rules and flag-impact list, dropping framing prose, to reduce inline bulk.

Dimension	Reasoning	Score
Conciseness	Dense, high-signal body with no padding about concepts Claude already knows (e.g. no 'what is a PR'); every line is operational guidance ('one agent per independent unit of review', 'Bias to deletion ("code judo").'). It is not below 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands — 'gh pr list ... --jq ...', 'gh pr review <n> --comment --body-file /tmp/reviews/<n>.md', 'gh pr diff <n>' — plus a complete review prompt template, not pseudocode.	3 / 3
Workflow Clarity	A clear 6-step sequence (Enumerate → Group → Fan out → Synthesize → Post → Clean up) with explicit validation checkpoints for this batch operation — 'confirm its commits exist on a remote (no local-only work lost)', 'print OK/FAILED per PR so a failed post is visible', 'require a non-vacuity argument'.	3 / 3
Progressive Disclosure	Well sectioned and one-level (no nested references) but monolithic: the embedded subagent prompt template and the lengthy 'Maintainability lens' section are content that, with a bundle, would plausibly live in separate one-level reference files rather than inline — matching 'content that should be separate is inline'.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 tight, third-person description that names concrete capabilities, surfaces natural trigger terms, and explicitly states both what it does and when to use it. It is distinctive and low-conflict.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'grouping, fan-out to review subagents, verdict synthesis, and posting' — plus concrete review scenarios (stacked branches, conflicts, security-sensitive changes), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'when' ('Use when asked to "review the open PRs"...') and 'what' ('Covers grouping, fan-out to review subagents, verdict synthesis, and posting'), with an explicit 'Use when...' trigger clause.	3 / 3
Trigger Term Quality	Quotes natural user phrasings — 'review the open PRs', 'review open PRs', 'batch PR review', 'stacked PRs', 'review pull requests', 'PR review pass' — giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	A clear niche — batch/stacked/recurring PR review — with distinct triggers ('review the open PRs', 'recurring PR-review pass on a repo') 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nearai/ironclaw
Path: skills/parallel-pr-review/SKILL.md
Commit: 800b781

Reviewed: 2 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.