Name: nemoclaw-maintainer-verify-stale
Rating: 68.8 (1 reviews)
Author: NVIDIA

nemoclaw-maintainer-verify-stale

Verifies whether stale NVIDIA/NemoClaw bug reports still reproduce on the newest exact release tag. Use when maintainers ask to verify stale issues, reproduce old bugs on the newest release tag, or drain the bug backlog. Treats issue reproducers as untrusted, validates them on the reported release before a fixed verdict, requires approval before Brev cost or GitHub writes, and never auto-closes.

Quality

85%

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

77%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.

Well-structured content with a clear, validated workflow and good progressive-disclosure intent, but the body's actionability and navigation depend on reference/*.md files that are missing from the bundle, which materially weakens both dimensions.

Suggestions

Ship the missing reference/*.md files (candidate-selection, environment-and-reproducer, brev-provisioning, reproduction-rubrics, by-design, scoring-comments-and-logging) so the signaled one-level-deep references actually resolve.

Add a few copy-paste-ready commands or a minimal inline example in SKILL.md so the body is actionable even before a reference file is opened.

Drop the reference map table or the in-workflow links to remove the duplicated path listing and tighten the token budget.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, delegating detail to reference files without explaining known concepts; the reference map partially duplicates links already present in the workflow, and a few non-negotiables could be trimmed.	4 / 5
Actionability	Names concrete tools and commands (brev exec, brev copy, scripts/redact-evidence.py) and a sequenced workflow, but the body itself contains little copy-paste-ready code and leans on reference files that are not present in the bundle.	4 / 5
Workflow Clarity	A clear 7-step sequence with a progress checklist, explicit approval gates ('Wait for maintainer approval before any brev exec...'), issue-state re-checks, and feedback loops (validate on reported release, then verify newest tag; re-run cited commands).	5 / 5
Progressive Disclosure	Structure is well-signaled with one-level-deep references in both the workflow and reference map, but scoring against the actual bundle reveals the referenced reference/*.md files do not exist (only scripts/redact-evidence.py is present), which breaks navigation.	3 / 5
	Total	16 / 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 precise, third-person description that clearly states what the skill does and when to use it, with concrete trigger phrases and a well-scoped niche. Minor trigger-synonym coverage gaps keep it just short of flawless on trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'verifies whether stale bug reports still reproduce,' 'validates them on the reported release before a fixed verdict,' 'requires approval before Brev cost or GitHub writes,' 'never auto-closes' — with comprehensive coverage of the verification lifecycle.	5 / 5
Completeness	Explicitly answers both what (verify stale reports reproduce on newest release tag, validate on reported release, require approval, never auto-close) and when ('Use when maintainers ask to verify stale issues, reproduce old bugs on the newest release tag, or drain the bug backlog') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural maintainer-facing phrases like 'when maintainers ask to verify stale issues,' 'reproduce old bugs on the newest release tag,' 'drain the bug backlog' are present, but some common-synonym phrasings a user might actually say (e.g. 'check if this old bug still happens') are not mirrored.	4 / 5
Distinctiveness Conflict Risk	Clear, narrow niche (stale NVIDIA/NemoClaw bug verification on the newest exact release tag) 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: 12 missing, 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: NVIDIA/NemoClaw
Path: .agents/skills/nemoclaw-maintainer-verify-stale/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.