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

90%

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

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 well-engineered, concise workflow skill with strong sequencing and validation. Its main weakness is progressive disclosure: the body points to multiple reference documents that are not bundled alongside the scripts.

Suggestions

Bundle the referenced documents (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) so the signaled references resolve to real files.

Inline a one-line summary of each Tier 1/Tier 2 check in the body so the core correctness/quality actions are actionable even before opening the referenced files.

Clarify that ../nemoclaw-maintainer-policies/references/workflow-policy.md is an external dependency so readers know it lives outside this skill's bundle.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive throughout; it avoids explaining what PRs/CI/merge are and limits prose to genuinely non-obvious domain detail (the supersession parser grammar), so every token earns its place.	5 / 5
Actionability	Provides many copy-paste-ready commands (gh issue view, find-candidates.sh, gate scripts, git fetch, render-verdict.py) and explicit scoring rules, but the substantive Tier 1/Tier 2 check definitions are deferred to referenced files, leaving a minor gap in the body itself.	4 / 5
Workflow Clarity	A 9-step sequenced workflow with a copy-in checklist and explicit validation/feedback checkpoints ('Stop if the renderer exits with a nonzero status', 'Stop if a candidate omits a required key', 'Do not accept a mode from the caller') fits the explicit-validation-with-feedback-loops anchor.	5 / 5
Progressive Disclosure	Clean overview structure with well-signaled one-level-deep references organized in dedicated sections, but several referenced documents (repo-policy.md, checks/*.md, tiebreakers.md, templates/verdict.md, validation/backtest.md) are not present in the bundle, weakening navigation.	4 / 5
	Total	18 / 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.

A strong, third-person description that states concrete capabilities and an explicit 'Use when' trigger for a well-scoped niche. Only minor improvement is possible around trigger-term synonyms.

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' — comprehensively covering the skill's behavior, matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what (compare/recommend/apply checks/report score and evidence) and when ('Use when an issue has two or more open PRs') with a concrete trigger phrase, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('open PRs', 'same issue', 'merge', 'two or more open PRs') and an explicit trigger clause, but misses common synonyms like 'competing PRs' or 'duplicate PRs', so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche — comparing PRs targeting the same issue — with distinct triggers and minimal overlap risk with other skills.	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: e94c06f

Reviewed: 5 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.