CtrlK
BlogDocsLog inGet started
Tessl Logo

nemoclaw-maintainer-morning

Runs the morning maintainer standup for NemoClaw. Triages the backlog, determines the day's target version, labels selected items, surfaces stragglers from previous versions, and outputs the daily plan. Use at the start of the workday. Trigger keywords - morning, standup, start of day, daily plan, what are we shipping today.

68

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

68%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 action-oriented and well-structured with executable commands and a clear step sequence. Its main weakness is the absence of validation/verification feedback loops for the batch labeling and state-save operations, which caps workflow clarity.

Suggestions

Add an explicit validation checkpoint after Step 3 (e.g. re-run gh pr view to confirm the version label was applied) and after Step 4 (verify state was saved) — this would lift workflow clarity above the batch-operation cap of 3.

Tighten the Step 1 straggler rationale to a single clause; the post-tag housekeeping explanation is context Claude can infer from the script output.

Replace bare placeholders like <version> and <number> with a brief note on how to obtain them (e.g. from the Step 1 script output) so the commands are fully copy-paste ready.

DimensionReasoningScore

Conciseness

Largely lean with executable commands and decision guidance rather than concept explanation, but the straggler rationale in Step 1 ('they indicate post-tag housekeeping was interrupted...') could be trimmed. Not a 5 because a few sentences over-explain context Claude could infer.

4 / 5

Actionability

Provides concrete, executable bash commands (node scripts, gh label/pr/issue edits) and a sample plan table, but placeholders like <version> and <number> require substitution, keeping it just short of copy-paste-ready 5.

4 / 5

Workflow Clarity

Four steps are clearly sequenced with a user-confirmation checkpoint in Step 3, but this is a batch labeling/state operation with no validation or verification step (e.g. confirm labels applied, confirm queue saved), so the batch-operation cap of 3 applies.

3 / 5

Progressive Disclosure

Well-organized into labeled steps with a clearly signaled one-level reference to PR-REVIEW-PRIORITIES.md; no local bundle dirs exist, and the referenced scripts live in a sibling skill directory, a minor organization gap that keeps it below 5.

4 / 5

Total

15

/

20

Passed

Description

100%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 third-person, specific, and gives both concrete actions and explicit trigger guidance with natural keywords. It cleanly matches the top anchors on every dimension.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'Triages the backlog, determines the day's target version, labels selected items, surfaces stragglers from previous versions, and outputs the daily plan' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what (triage/version/label/plan actions) and when ('Use at the start of the workday') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Provides natural trigger phrases a user would actually say — 'morning, standup, start of day, daily plan, what are we shipping today' — comprehensive coverage of natural terms with no jargon-only language.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (NemoClaw maintainer morning standup) with distinct, specific triggers unlikely to fire for unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.