nemoclaw-maintainer-day

Run one NemoClaw daytime maintainer pass. Prioritize items for the release version. Select a merge, salvage, security, test, conflict, or sequencing workflow and report progress. Use during the workday to land PRs and close issues. Designed for /loop, for example /loop 10m /nemoclaw-maintainer-day. Trigger keywords - maintainer day, work on PRs, land PRs, make progress, what's next, keep going, maintainer loop.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/nemoclaw-maintainer-day/SKILL.md

Quality

Content

83%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 tight, well-sequenced maintainer loop with executable scripts and clear gates, exhibiting excellent token efficiency. Its main gap is that a number of referenced workflow and reference files are not bundled alongside SKILL.md, which weakens in-file actionability and progressive-disclosure navigation.

Suggestions

Bundle or co-locate the referenced workflow files (MERGE-GATE.md, SALVAGE-PR.md, SECURITY-SWEEP.md, TEST-GAPS.md, HOTSPOTS.md, SEQUENCE-WORK.md) and references (PR-REVIEW-PRIORITIES.md, RISKY-AREAS.md, STATE-SCHEMA.md) so every link resolves.

Inline a one-line validation/checkpoint cue for each selected workflow (e.g. 're-run CI check before approving') to raise workflow-clarity to the top anchor.

Verify the script paths (.agents/skills/nemoclaw-maintainer-day/scripts/...) match the actual bundle layout so the commands are copy-paste runnable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: no concept explanations, no padding, every line is either an instruction, a guard, or an executable command, and it avoids explaining what a PR or CI is.	5 / 5
Actionability	It provides concrete, runnable commands (the version-progress and state scripts) and clear selection criteria, but several core workflows live only behind named reference links (MERGE-GATE.md, SALVAGE-PR.md) whose content is not shown, leaving a minor gap for in-file execution.	4 / 5
Workflow Clarity	Steps 1–4 are clearly sequenced with selection rules and a reporting re-run checkpoint, plus stop-and-ask gates; it falls short of 5 because validation feedback loops (validate→fix→retry) are delegated to the linked workflow files rather than surfaced inline.	4 / 5
Progressive Disclosure	Structure is good: an overview body with well-signaled one-level-deep reference links and a real scripts/ bundle backing the commands; it is short of 5 because several referenced files (PR-REVIEW-PRIORITIES.md, RISKY-AREAS.md, MERGE-GATE.md, etc.) are not present in the bundle, so navigation is partially unresolved.	4 / 5
	Total	17 / 20 Passed

Description

75%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 concrete, third-person, and supplies explicit trigger guidance plus a clear when-clause for /loop usage. It is well above the midpoint but falls short of the top anchor because a couple of natural phrasings could be added and the what/when could be condensed into a single tight sentence.

Suggestions

Lead with one explicit 'Use when...' sentence that fuses the 'what' and 'when' so the trigger clause is unmistakable.

Add a couple of natural synonyms (e.g. 'triage PRs', 'review queue') to broaden trigger coverage.

Clarify what distinguishes the 'day' variant from the 'evening' variant in the description itself to reduce sibling-skill overlap.

Dimension	Reasoning	Score
Specificity	The description names concrete workflow types ('merge, salvage, security, test, conflict, or sequencing workflow') and a concrete action ('report progress'), giving several specific actions, though the precise outcomes of each workflow are left to the body.	4 / 5
Completeness	It states both what (run a maintainer pass selecting among named workflows) and when ('Use during the workday to land PRs and close issues', plus trigger keywords), with the 'when' explicit but could be slightly tighter as a single 'Use when...' clause.	4 / 5
Trigger Term Quality	It lists natural trigger keywords ('maintainer day, work on PRs, land PRs, make progress, what's next, keep going, maintainer loop') that a user might plausibly say, with good though not exhaustive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The NemoClaw-specific framing and maintainer-loop context make it mostly distinct from generic skills, with only minor overlap risk against a sibling 'nemoclaw-maintainer-evening' skill.	4 / 5
	Total	16 / 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: 9 missing, 1 suspicious	Warning

	Total	14 / 16 Passed

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