review-pending-pr-reviews

Review, grill, edit, and post pending PR review drafts saved by /review-pr (or its batch/cron runners). Lists drafts that have not yet been posted, walks the maintainer through each finding, then posts, closes, or discards. Use when the user says "post my pending reviews", "what reviews are waiting", "go through the review outbox", or invokes /review-pending-pr-reviews.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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.

A thorough, executable outbox workflow with strong sequencing and validation gates for destructive/batch posting actions. The main gap is progressive disclosure: all templates and guidance live in one ~320-line file rather than being split into referenced bundle files.

Suggestions

Move the per-verdict close comment templates (Step 5) into a referenced file like references/close-templates.md to shorten the main body and improve progressive disclosure.

Trim the repeated grill brief vs. re-brief templates in Step 3 by factoring the shared inventory format into one template referenced once.

Pull the few over-justified rationales (e.g., why /review-pr's grill is skipped) into a one-line note to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Largely lean and operational with no padding of concepts Claude already knows, but the body runs ~320 lines with some repetition between the grill brief template and the re-brief template, and a few over-explained rationales that could be trimmed.	4 / 5
Actionability	Fully executable: concrete gh/read/edit commands, exact frontmatter fields, --body-file staging with heredocs, and copy-paste comment templates per verdict — covers the common cases copy-paste ready.	5 / 5
Workflow Clarity	Six clearly sequenced steps with explicit validation checkpoints — drift/old-pipeline checks before presenting (Step 2), grill rounds recomputing the verdict before posting (Step 3), and the standalone-command guard — plus error-recovery guidance (skip + re-run on stale or unverified facts).	5 / 5
Progressive Disclosure	Well-organized into numbered sections with clear hierarchy and no nested references, but all content is inlined in SKILL.md with no references/ or scripts/ bundle files to offload the long templates, so it leans toward a monolithic single file.	4 / 5
	Total	18 / 20 Passed

Description

96%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.

A strong description: concrete actions, a clear what/when pair, and natural user-spoken trigger phrases. Its only soft spot is adjacency to the sibling /review-pr skill, which creates slight overlap risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — Review, grill, edit, and post pending PR review drafts, Lists drafts, walks the maintainer through each finding, then posts, closes, or discards — covering the full lifecycle comprehensively.	5 / 5
Completeness	Explicitly answers both what (review/grill/edit/post pending drafts, walk through findings, post/close/discard) and when (the quoted "Use when the user says..." trigger phrases), matching the anchor for a clear what + concrete when.	5 / 5
Trigger Term Quality	Provides direct quoted natural phrases a user would say — "post my pending reviews", "what reviews are waiting", "go through the review outbox" — plus the slash-command invocation, covering synonyms and the exact trigger.	5 / 5
Distinctiveness Conflict Risk	The PR-review-outbox niche is distinct and named (pending drafts saved by /review-pr), but it sits adjacent to /review-pr itself, leaving minor overlap risk on the closely related sibling skill.	4 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: nrwl/nx
Path: .claude/skills/review-pending-pr-reviews/SKILL.md
Commit: b616fa1

Reviewed: 4 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.