skill-mass-triage

[Skill] Batch-triage build failures from a JSON results file — diagnose with parallel sub-agents, bucketize by root cause, and produce a consolidated summary. Use when asked to triage a Koji results file. Triggers: batch triage, mass triage, triage results file, bucketize failures.

Quality

88%

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

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced orchestration workflow with strong validation and feedback loops, but it suffers from redundant admonitions repeated across sections and inlines a large prompt template instead of practicing the file-based progressive disclosure it advocates.

Suggestions

Consolidate the repeated directives — each of 'do NOT diagnose inline, always use a sub-agent', 'reference the prompt .md by path, do not inline it', and 'do NOT call set_koji_url' is stated 2–3 times; state each once authoritatively and reference it.

Move the sub-agent prompt template into a reference file (e.g. references/diagnose-prompt.md) and reference it by path, offloading ~50 lines from the body and aligning the skill with the progressive-disclosure practice it instructs.

The '.github/skills/skill-koji-triage/SKILL.md' dependency is assumed but its existence is not guaranteed; note this prerequisite or bundle the investigation workflow so the skill is self-contained.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and instructionally dense, but key directives are repeated across contexts — 'do NOT diagnose inline / always use a sub-agent' appears in the STOP block, the step-6 blockquote, and the Notes; 'reference the prompt .md by path, do not inline' and 'do NOT call set_koji_url' are each stated two or more times — which could be consolidated.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: exact JSON input/output schemas, file paths, batch-size targets (~6), tool names (jq, python, runSubagent), and a full sub-agent prompt template with variable placeholders.	3 / 3
Workflow Clarity	Two clearly sequenced phases with explicit validation checkpoints and feedback loops — 'verify that a JSON file exists for each failed build. Re-run any missing ones' and cleanup ordered 'only after the summary is written' — satisfying the batch-operation validation requirement.	3 / 3
Progressive Disclosure	Well-sectioned but monolithic: no bundle files exist in references/scripts/assets, and the ~50-line sub-agent prompt template is inlined in the body rather than offloaded to a reference file, which is content that should be separate presented inline.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that explicitly covers capabilities and use-conditions with concrete trigger terms and a clear, narrow niche. The leading '[Skill]' tag is a cosmetic artifact but does not undermine the substantive content.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Batch-triage build failures from a JSON results file — diagnose with parallel sub-agents, bucketize by root cause, and produce a consolidated summary' — each a distinct operation rather than vague language.	3 / 3
Completeness	Clearly answers both what (triage/diagnose/bucketize/summarize) and when ('Use when asked to triage a Koji results file' with explicit trigger terms), meeting the top anchor.	3 / 3
Trigger Term Quality	Explicit 'Triggers: batch triage, mass triage, triage results file, bucketize failures' plus 'Use when asked to triage a Koji results file' gives good coverage of natural phrasings a user would say.	3 / 3
Distinctiveness Conflict Risk	The 'Koji results file' build-failure triage niche is specific with distinct triggers, making conflict with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/azurelinux
Path: .github/skills/skill-mass-triage/SKILL.md
Commit: 9e308ff

Reviewed: 6 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.