nemoclaw-maintainer-pr-comparator

Compare open PRs that address the same issue and recommend one to merge. Apply eligibility, correctness, quality, and tie-break checks. Report the score and evidence. Use when an issue has two or more open PRs.

Quality

86%

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

81%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 well-sequenced, action-oriented workflow with strong validation checkpoints and clean sectioning. Its main weakness is that several referenced reference/template/check files are not actually present in the bundle, slightly undermining progressive disclosure and a couple of the delegated steps.

Suggestions

Add the missing referenced files (repo-policy.md, checks/tier-0-gates.md, checks/tier-1-correctness.md, checks/tier-2-quality.md, tiebreakers.md, templates/verdict.md, validation/backtest.md) to the bundle, or remove the references and inline the essential rules so every cited path resolves.

Move the detailed supersession parser-grammar block (lines 70-78) into a reference file, keeping only a one-line summary in SKILL.md to tighten conciseness.

For Tier 1/Tier 2 steps that currently delegate entirely to absent files, inline a brief summary of the checks so the step remains actionable even before the reference file is opened.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows (no "what a PR is" filler), but the supersession-grammar block (lines 70-78) is detailed enough that it arguably belongs in a reference rather than the overview, leaving it just short of the every-token-earns-its-place bar.	4 / 5
Actionability	Each step ships executable commands ("gh issue view ...", "scripts/find-candidates.sh <issue-number>") plus concrete scoring rules (Tier 1 weight 2.0x, pass/yellow/fail), but several steps delegate the actual checks to reference files (e.g. "Apply the six model checks in checks/tier-1-correctness.md") that are not present in the bundle, a minor gap against the copy-paste-ready bar.	4 / 5
Workflow Clarity	A 9-step checklist gives an explicit sequence with concrete validation/stop checkpoints for this batch operation ("Stop if a candidate omits a required key", "Stop if the renderer exits with a nonzero status. Do not recommend a merge.") plus a mode-computation feedback loop, matching the clear-sequence-with-explicit-validation anchor.	5 / 5
Progressive Disclosure	Structure is good with section headers, a "Reference files" list, and a "Scripts (execute, do not read)" section giving one-level-deep navigation, but several referenced paths (repo-policy.md, checks/*.md, tiebreakers.md, templates/verdict.md, validation/backtest.md) do not exist in the bundle, a real navigation gap that keeps it below 5.	4 / 5
	Total	17 / 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 concise, concrete, and explicitly pairs a clear what with a specific when-trigger, occupying a distinct niche. Slight room for richer synonym coverage in trigger terms, but overall it reads as a strong, well-targeted skill description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "compare open PRs", "recommend one to merge", "Apply eligibility, correctness, quality, and tie-break checks", "Report the score and evidence" — covering the full task comprehensively, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what (compare/apply checks/recommend/report) and when with the concrete trigger "Use when an issue has two or more open PRs", matching the score-5 anchor for explicit what-and-when with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural maintainer-facing terms ("open PRs", "recommend one to merge", "two or more open PRs") are present and would naturally be said, but synonym/variation coverage is thin and there are no file-extension-style triggers; a few natural terms are missing, so it sits just below 5.	4 / 5
Distinctiveness Conflict Risk	The trigger "an issue that has two or more open PRs" carves a clear niche (multi-PR comparison) with minimal overlap risk against other maintenance skills, matching the clear-niche anchor.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 7 missing	Warning

	Total	14 / 16 Passed

Repository: NVIDIA/NemoClaw
Path: .agents/skills/nemoclaw-maintainer-pr-comparator/SKILL.md
Commit: e987b00

Reviewed: about 4 hours 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.