nemoclaw-maintainer-find-review-pr

Find open PRs with the security label and Urgent or High Project Priority. Link each PR to its issue. Identify competing or superseded PRs and report review candidates. Use when looking for the next PR to review. Trigger keywords - find pr, find review, next pr, pr to review, duplicate pr, security pr.

Quality

88%

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.

A well-structured, executable workflow with a clear sequenced process, explicit validation checkpoints, and concrete gh/jq commands. The main weaknesses are the two external sibling-skill references that do not resolve and minor verbosity in the duplicated authorization boilerplate.

Suggestions

Bundle or vendor the comparator script (parse-supersession.sh) and the workflow-policy reference so the Step 4 command and policy link resolve within the skill's own bundle, or mark these sibling-skill dependencies as external prerequisites.

De-duplicate the authorization-before-closing conditions: state them once in Step 4 and have the output template reference them rather than repeating the full checklist inline.

Tighten the supersession 'bracket expressions describe the parser grammar; not literal text' explanation or move it into the comparator reference, keeping only the concrete phrase families Claude must recognize.

Dimension	Reasoning	Score
Conciseness	The body is lean: numbered steps with concrete bash snippets and no padding about what a PR is or how `gh` works. Minor over-explanation remains in the duplicated authorization conditions (Step 4 and the output template) and the bracket-expression supersession grammar, which is why it is not a 5.	4 / 5
Actionability	Provides copy-paste-ready commands (the `gh project item-list \| jq` filter, `gh pr view --json ... --jq`, the supersession detector) and concrete issue-reference patterns. Gaps keep it below 5: Step 4's command depends on `../nemoclaw-maintainer-pr-comparator/scripts/parse-supersession.sh`, which is not present in the bundle, and `<number>` placeholders require substitution.	4 / 5
Workflow Clarity	A clear five-step sequence with explicit checkpoints ('If no PRs remain, report that result and stop', 'Remove entries for closed PRs') and a policy-gated checklist (transfer, verify commits/attribution/CI, rerun comparator, merge) before recommending close. The skill is explicitly read-only ('Never close a PR'), so the destructive-operation cap does not apply.	5 / 5
Progressive Disclosure	Well-organized single-file structure with clear section headers and a one-level-deep, clearly signaled external reference pattern. It is not a 5 because the two referenced sibling-skill paths (`../nemoclaw-maintainer-pr-comparator/scripts/parse-supersession.sh` and `../nemoclaw-maintainer-policies/references/workflow-policy.md`) do not resolve in the bundle, leaving a navigation gap.	4 / 5
	Total	17 / 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, third-person description that names concrete actions and pairs a clear 'Use when' clause with an explicit trigger-keyword list. It is comprehensive and largely distinct; the only soft spot is mild overlap risk with generic PR-review phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Find open PRs with the security label and Urgent or High Project Priority', 'Link each PR to its issue', 'Identify competing or superseded PRs and report review candidates' — giving comprehensive coverage of the workflow. It is third-person voice and clearly exceeds the 'several specific actions; minor gaps' (4) anchor.	5 / 5
Completeness	Explicitly answers both 'what' (find/link/identify competing PRs) and 'when' ('Use when looking for the next PR to review' plus an explicit 'Trigger keywords' list). Matches the 5-anchor ('clearly and explicitly answers both what AND when with concrete trigger phrases').	5 / 5
Trigger Term Quality	Includes natural user phrases and synonyms — 'find pr', 'find review', 'next pr', 'pr to review', 'duplicate pr', 'security pr' — covering multiple ways a user would ask for the same intent. Sits clearly above the 4-anchor ('PDF files, forms, document extraction') which has fewer variants.	5 / 5
Distinctiveness Conflict Risk	The security-label + Urgent/High priority niche and duplicate-detection intent form a clear, narrow scope, but generic review phrasing like 'find review', 'next pr', and 'pr to review' could overlap with a general PR-review skill. Best fits the 4-anchor ('mostly distinct; minor overlap risk').	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NVIDIA/NemoClaw
Path: .agents/skills/nemoclaw-maintainer-find-review-pr/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.