nemoclaw-maintainer-morning

Prepare the NemoClaw morning maintainer plan: triage the backlog, select a target version, and identify release candidates and stragglers.

Quality

78%

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-morning/SKILL.md

Quality

Content

82%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 tight, command-driven workflow that scores well on token efficiency and structure: every step has an executable bash block, sequencing is clear, and detail is delegated to one-level-deep references. The gaps are modest — no shown usage for find-review-pr, no verification step after batch labeling, and total reliance on a sibling skill's files for scripts and priorities.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-first: each step is a short bash block ('node --no-warnings .../version-target.ts', 'gh pr edit <number> ... --add-label "<version>"') with only domain-specific context Claude could not infer (e.g. why stragglers matter: 'they indicate post-tag housekeeping was interrupted'). No padding or explanation of known concepts — matches the 'every token earns its place' anchor.	5 / 5
Actionability	Steps 1–4 give concrete, mostly copy-paste-ready commands, including a worked example table for the output plan. It falls short of fully executable because 'find-review-pr' is invoked by name with no command or usage shown, and Step 3's commands contain unsubstituted placeholders (<version>, <number>) without an example of resolved values.	4 / 5
Workflow Clarity	A clear four-step sequence (version/stragglers → triage → label → save state/output) with a human-in-the-loop checkpoint before the batch labeling ('After they confirm which items to target') and decision guidance for stragglers ('Decide whether to relabel them to today's target or defer'). It is not a 5 because there is no post-labeling verification (e.g. confirming labels applied) before state is saved and the plan is published.	4 / 5
Progressive Disclosure	The body is well organized into per-step sections and pushes all detail to clearly signaled, one-level-deep references ('See [PR-REVIEW-PRIORITIES.md](../nemoclaw-maintainer-day/PR-REVIEW-PRIORITIES.md)', script paths under .agents/skills/nemoclaw-maintainer-day/scripts/). It is not a 5 because everything — scripts and the priorities doc — lives in a sibling skill's bundle rather than this one, so the overview depends on cross-bundle navigation and cannot stand alone as a self-contained reference structure.	4 / 5
	Total	17 / 20 Passed

Description

66%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 concrete, third-person description that names the exact workflow steps of the morning routine, with good domain-natural trigger terms. Its main weakness is the absence of any explicit 'when to use this' guidance, which caps completeness; it also has minor overlap risk with the sibling maintainer-day skill.

Suggestions

Add an explicit trigger clause, e.g. 'Use at the start of a maintainer day to plan daily releases, or when the user asks for the NemoClaw morning triage/backlog plan.'

Include a few natural synonyms or variations users might say, such as 'daily plan', 'backlog triage', or 'release stragglers', to broaden trigger coverage.

Sharpen the distinction from the sibling skill, e.g. 'Use /nemoclaw-maintainer-day during the day to execute this plan' — signaling this skill is only for morning planning.

Dimension	Reasoning	Score
Specificity	The description lists several concrete third-person actions — 'triage the backlog', 'select a target version', and 'identify release candidates and stragglers' — matching the anchor for several specific actions with minor gaps. It is not a 5 because it omits concrete downstream actions the skill performs (labeling items and outputting the daily plan), keeping coverage slightly short of comprehensive.	4 / 5
Completeness	The 'what' is clearly stated ('Prepare the NemoClaw morning maintainer plan: triage... select... identify...'), but there is no 'Use when...' clause or equivalent explicit trigger guidance — e.g. nothing like 'Use at the start of a maintainer day'. Per the rubric guideline, a missing explicit 'when' caps completeness at 3, and it is not lower because the 'what' is concrete and well-scoped.	3 / 5
Trigger Term Quality	Terms like 'maintainer', 'triage the backlog', 'release candidates', and 'stragglers' are natural phrases a NemoClaw maintainer would say, giving good keyword coverage. A few natural variations are missing (e.g. 'daily plan', 'start the day', 'version labels'), so it falls just below the comprehensive-synonym anchor of 5.	4 / 5
Distinctiveness Conflict Risk	'NemoClaw morning maintainer plan' carves a clear niche, distinct from generic repo-maintenance skills. It is not a 5 because a closely related sibling skill ('nemoclaw-maintainer-day') covers the same repo's workflow, so a request like 'nemoclaw maintainer' has minor overlap risk with that skill.	4 / 5
	Total	15 / 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: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: NVIDIA/NemoClaw
Path: .agents/skills/nemoclaw-maintainer-morning/SKILL.md
Commit: 766cc03

Reviewed: 3 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.