Name: apm-triage-panel
Rating: 70.39999999999999 (1 reviews)
Author: microsoft

apm-triage-panel

Use this skill to triage one microsoft/apm issue selected by the daily sweep, the `status/needs-triage` fast path, or manual dispatch. Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action.

Quality

86%

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

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 highly actionable, well-sequenced orchestration skill with strong validation gates and clean progressive disclosure through on-demand persona and template references. Its main weakness is verbosity from restating the same invariants across multiple sections.

Suggestions

Consolidate the single-emission, ASCII-only, and no-sub-agent rules into one authoritative 'Output contract' or 'Anti-patterns' section and reference it elsewhere instead of restating it.

The conditional-panelist YES/NO routing rules and the fast-path triggers are spelled out both in the per-persona sections and restated in the Anti-patterns wildcard-heuristics block; define each rule once and cross-reference.

The 'Notes' section repeats the progressive-disclosure / no-sub-agent / load-persona-on-demand guidance already covered in 'Output contract' and 'Persona pass procedure'; fold the unique points into those sections and drop the rest.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concepts Claude already knows, but several invariants are restated across sections (single-emission, ASCII-only, no sub-agents, roster agreement, conditional rules in two forms), adding padding that could be tightened.	3 / 5
Actionability	Fully executable guidance -- a numbered 9-step execution checklist, an exact persona-pass procedure, a complete label taxonomy, the exact-match milestone rule with a null fallback, and anti-patterns with concrete thresholds (e.g. 'Do not exceed 6 labels').	5 / 5
Workflow Clarity	A clearly sequenced 9-step procedure with explicit validation checkpoints -- a pre-arbitration completeness gate with a redo loop, duplicate-link verification, and a render-verification gate before the single output emission.	5 / 5
Progressive Disclosure	A clear overview that points one level deep to on-demand persona .agent.md files and assets/triage-template.md (verified present), each clearly signaled and loaded only at the appropriate step.	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 tightly scoped, well-written description that clearly answers both what and when with concrete outputs and natural trigger terms tied to a specific repo and label taxonomy. Minor specificity gap from the broad word 'decision' keeps it just short of perfect.

Dimension	Reasoning	Score
Specificity	Names concrete actions -- 'triage', 'Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action' -- listing several specific outputs, though 'decision' is somewhat broad so it is not a fully comprehensive 5.	4 / 5
Completeness	Explicitly answers both what ('Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action') and when ('Use this skill to triage one microsoft/apm issue selected by the daily sweep, the status/needs-triage fast path, or manual dispatch').	5 / 5
Trigger Term Quality	Natural domain phrases a user would say -- 'triage one microsoft/apm issue', 'daily sweep', 'status/needs-triage fast path', 'manual dispatch' -- give good keyword coverage with a few synonyms missing.	4 / 5
Distinctiveness Conflict Risk	A clearly bounded niche -- triaging microsoft/apm issues with specific named label/status triggers -- leaves minimal conflict risk with other skills.	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
relative_links	Relative link issues: 6 suspicious	Warning

	Total	15 / 16 Passed

Repository: microsoft/apm
Path: .agents/skills/apm-triage-panel/SKILL.md
Commit: e38261c

Reviewed: 10 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.