parallel-pr-review

Review a batch or stack of pull requests, or run a recurring PR-review pass on a repo. Best 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

100%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.

The body is a model of lean, actionable skill writing: executable commands, a complete subagent prompt template, an explicit sequenced workflow with validation/re-check loops for destructive steps, and clean single-file organization. Nothing meaningful to improve.

Dimension	Reasoning	Score
Conciseness	Lean and dense throughout — it never explains what a PR or git is, and every section (workflow, prompt template, output format, common mistakes) earns its tokens with high-signal, actionable content.	5 / 5
Actionability	Provides copy-paste-ready executable `gh`/`git` commands and a complete subagent prompt template with explicit placeholders, plus a fixed output/verdict format covering the common cases.	5 / 5
Workflow Clarity	A clearly numbered 6-step workflow with explicit validation checkpoints for batch and destructive operations (re-checking CONFLICTING after rebase, confirming commits exist on a remote before branch deletion).	5 / 5
Progressive Disclosure	No bundle files are present (references/scripts/assets absent), and the single-file body is well-sectioned with one-level structure and no nested references, fitting a skill that needs no external materials.	5 / 5
	Total	20 / 20 Passed

Description

92%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.

The description is specific, trigger-rich, and complete, clearly stating both what the skill does and when to use it with concrete natural-language triggers. Its only minor gap is a few everyday phrasings ('code review', 'review my PRs') not appearing directly in the description text.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions — 'grouping, fan-out to review subagents, verdict synthesis, and posting' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers 'what' (review/group/fan-out/synthesize/post) and 'when' ('Best with many PRs, stacked branches, conflicts, or security-sensitive changes'), with 'Best with...' serving as an explicit trigger clause.	5 / 5
Trigger Term Quality	Strong natural coverage ('batch or stack of pull requests', 'stacked branches, conflicts, security-sensitive changes') but the description itself omits a few common phrasings a user might say, like 'code review' or 'review my PRs'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — parallel/stacked PR review with subagent fan-out — with specific triggers and minimal overlap risk against generic single-PR review skills.	5 / 5
	Total	19 / 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: nearai/ironclaw
Path: skills/parallel-pr-review/SKILL.md
Commit: 2831516

Reviewed: 8 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.