nemoclaw-maintainer-analyze-ci-performance

Analyze retained NemoClaw CI timing evidence for slow CLI tests or base-image publication latency. Use for CI performance, slow tests, Vitest timing artifacts, base-image publication timing, runner queue latency, or publication-gate analysis.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

86%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, read-only analysis skill with fully executable commands, explicit operational guardrails, and clean one-level-deep references to real bundled scripts. It is concise and actionable, with only minor trimming and error-recovery detail separating it from top marks.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but phrases like 'Defaults preserve the former timing tool contract' and the long enumerated binary-dependency list are minor instances that could be trimmed, keeping it just below a 5.	4 / 5
Actionability	Both analyzers are given as full, copy-paste-ready `node --experimental-strip-types` commands with documented defaults and optional flags, covering the common cases exactly as the 5 anchor requires.	5 / 5
Workflow Clarity	Each analyzer is a single read-only command with explicit guardrails (reject artifacts >25M, require 2 reports, treat atLeast30SuccessfulJobs:false as insufficient, stop on auth failure), giving clear checkpoints; it stops short of 5 only because error-recovery feedback beyond the auth hard-stop is implicit.	4 / 5
Progressive Disclosure	The under-50-line body is a clean overview with two well-signaled, one-level-deep references to real bundle scripts (analyze-recent-cli-timings.mts, analyze-base-image-publication-timings.mts) that exist in ./scripts/, matching the simple-skill exception for a 5.	5 / 5
	Total	18 / 20 Passed

Description

87%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, third-person description that pairs a concrete statement of what the skill does with an explicit 'Use for' trigger list and a clear niche boundary. It is comprehensive for its narrow CI-performance domain with only minor synonym/extension gaps.

Dimension	Reasoning	Score
Specificity	Names the domain ('retained NemoClaw CI timing evidence') and concrete actions ('slow CLI tests', 'base-image publication latency'), listing several specific analyses with only minor coverage gaps rather than the full multi-action list of a 5.	4 / 5
Completeness	It explicitly answers both what ('Analyze retained NemoClaw CI timing evidence for slow CLI tests or base-image publication latency') and when ('Use for CI performance, slow tests...') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	The 'Use for' clause surfaces six natural trigger phrases ('CI performance', 'slow tests', 'Vitest timing artifacts', 'base-image publication timing', 'runner queue latency', 'publication-gate analysis') — good coverage with a few common synonyms/file extensions missing, so not a 5.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (NemoClaw CI performance analysis) with distinct, repo-specific triggers and an explicit boundary against the PR value-stream skill, giving minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NVIDIA/NemoClaw
Path: .agents/skills/nemoclaw-maintainer-analyze-ci-performance/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.