Name: nemoclaw-maintainer-verify-stale
Rating: 69.6 (1 reviews)
Author: NVIDIA

nemoclaw-maintainer-verify-stale

Verifies whether stale NVIDIA/NemoClaw bug reports still reproduce on the newest 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

80%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-organized, concise pointer-layer skill body with excellent workflow clarity and validation gates. The major defect is that nearly all referenced reference files are missing from the bundle, breaking progressive disclosure navigation.

Suggestions

Add the missing reference/ files (candidate-selection.md, environment-and-reproducer.md, brev-provisioning.md, reproduction-rubrics.md, by-design.md, scoring-comments-and-logging.md) and ../_shared/documentation-writing-review.md, or remove the dangling links.

Inline a minimal reproducer validation snippet so the core action is executable directly from SKILL.md without requiring an absent reference.

Keep one canonical navigation surface (either the Workflow prose links or the Reference map) to reduce duplication once the files exist.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — a progress checklist, a 7-step pointer workflow, non-negotiables, and a reference map — with no padding explaining Brev/NemoClaw/GitHub; every line earns its place.	5 / 5
Actionability	Concrete commands and parameters are surfaced ("brev exec", "brev copy", scripts/redact-evidence.py, word-count defaults, 60-minute/120-second budgets), but most executable specifics live one level deeper in references rather than inline.	4 / 5
Workflow Clarity	A clearly numbered sequence with explicit validation/approval checkpoints ("Stop for approval before remote effects or cost", "re-check issue state") and feedback loops (validate reported release -> retry synthesized reproducer -> verify newest tag) satisfies the destructive/batch validation cap.	5 / 5
Progressive Disclosure	The structure and signaling are well designed, but all six reference/ files plus ../_shared/documentation-writing-review.md are referenced and do not exist in the bundle (only scripts/redact-evidence.py is present), so real navigation is broken.	2 / 5
	Total	16 / 20 Passed

Description

91%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, specific, third-person description that answers both what the skill does and when to invoke it with natural trigger phrases. Minor additional synonym/extension coverage is the only gap.

Dimension	Reasoning	Score
Specificity	Multiple concrete actions are named explicitly ("verifies...still reproduce on the newest release tag", "validates them on the reported release", "requires approval before Brev cost or GitHub writes", "never auto-closes"), giving comprehensive coverage.	5 / 5
Completeness	Both "what" (verifies stale reproduction on the newest release tag) and "when" (explicit "Use when maintainers ask to verify stale issues, reproduce old bugs..., or drain the bug backlog") are clearly and concretely answered.	5 / 5
Trigger Term Quality	Natural maintainer phrases appear ("verify stale issues", "reproduce old bugs on the newest release tag", "drain the bug backlog") with synonym variation, but a few common variants/extensions are not exhaustively covered.	4 / 5
Distinctiveness Conflict Risk	A clear maintainer-only niche (stale NemoClaw bug verification, never auto-closes, approval-gated) with distinct triggers and minimal overlap 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: 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.