CtrlK
BlogDocsLog inGet started
Tessl Logo

nemoclaw-maintainer-fix-e2e-failures

Fixes failures from automatic NemoClaw E2E runs on main through continuous maintainer coordination. Groups failures by root cause, assigns one PR to each cause, reviews peer changes, satisfies GitHub merge requirements, merges eligible PRs when authorized, and monitors new results. Use for continuous main E2E maintenance or coordinated multi-agent E2E maintenance. Do not use for manual E2E dispatch; use nemoclaw-maintainer-e2e instead.

72

Quality

88%

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

85%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-structured, actionable instruction skill with explicit sequencing and validation gates for destructive merge operations, and clean one-level-deep references. Minor conciseness gains are available by consolidating the repeated rescan/refresh rules.

Suggestions

Consolidate the rescan-on-state-change and refresh-before-write rules into a single stated rule in 'Run the Loop', then reference it from the other sections instead of restating it.

Tighten 'Apply Common Decisions' so its items don't restate guidance already covered in 'Run the Loop'; keep it to decisions not derivable from the loop steps.

Consider surfacing one or two concrete command examples for the most common write actions (e.g., the draft-PR creation via nemoclaw-contributor-create-pr) to lift actionability toward fully copy-paste-ready.

DimensionReasoningScore

Conciseness

The body is dense and almost entirely operational with no padding about concepts Claude already knows, but the rescan-on-state-change and refresh-before-write guidance recurs across several sections and could be consolidated.

4 / 5

Actionability

For an instruction-only skill it gives concrete, specific guidance — named sub-skills to load, an explicit PR-body field list, exact commands to avoid (gh run rerun, gh workflow run .github/workflows/e2e.yaml) — with execution detail delegated to referenced files.

4 / 5

Workflow Clarity

The loop is a clearly sequenced multi-step process with explicit validation checkpoints ('Run both checks immediately before the write', 'stop editing it' while waiting for CI/review, 'Re-read the PR and rules immediately before merge') and feedback loops for obsolete-work and failed-merge containment.

5 / 5

Progressive Disclosure

The body is a concise overview pointing to one-level-deep references that all exist (queue-and-ownership.md, review-and-merge.md, continuity-handoff.md), each clearly signaled inline and appropriately split out for easy navigation.

5 / 5

Total

18

/

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 strong, specific description that concretely states the skill's actions and provides explicit 'use when' guidance plus a clear anti-trigger. Trigger-term coverage is the only soft spot — a few natural synonyms are missing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Groups failures by root cause, assigns one PR to each cause, reviews peer changes, satisfies GitHub merge requirements, merges eligible PRs when authorized, and monitors new results' — giving comprehensive coverage with no significant gaps.

5 / 5

Completeness

Explicitly answers both what (group/assign/review/merge/monitor) and when ('Use for continuous main E2E maintenance or coordinated multi-agent E2E maintenance'), with concrete trigger phrases and disambiguation.

5 / 5

Trigger Term Quality

Includes natural trigger phrases ('continuous main E2E maintenance', 'coordinated multi-agent E2E maintenance') and an explicit anti-trigger, but coverage of common synonyms a user might say (e.g. 'test failures', 'CI failures', 'flaky tests') is partial.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (automatic main E2E maintenance via maintainer coordination) and explicitly distinguishes itself from the sibling skill ('Do not use for manual E2E dispatch; use nemoclaw-maintainer-e2e instead'), minimizing conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

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.