Name: autopilot-issue-triage-worker
Rating: 60.8 (1 reviews)
Author: microsoft

autopilot-issue-triage-worker

Use this skill to triage ONE microsoft/apm issue already selected by autopilot-issue-triage-scheduler. Return one advisory recommendation and a proposed scope brief, never human approval. Do not implement the issue, manage the backlog, or list the queue.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/autopilot-issue-triage-worker/SKILL.md

Quality

Content

73%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, highly actionable orchestration skill with an explicit sequenced workflow and rich validation checkpoints. Its weaknesses are repeated injunctions that pad the length and a broken reference to a missing scripts/triage_state.py bundle file.

Suggestions

Consolidate the repeated advisory-only/human-approval and no-sub-agent injunctions into a single authoritative section and reference it, rather than restating them in the intro, routing, rubric, brief, anti-patterns, and gotchas.

Either add the missing scripts/triage_state.py to the bundle or remove the reference and --help invocation so progressive_disclosure navigation is fully resolvable.

Provide one filled example of the triage-template.md output to lift actionability from concrete guidance to fully copy-paste-ready coverage of the common case.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept over-explanation, but the same injunctions (advisory-only/human-approval, no-sub-agent, single-comment discipline) recur 3-5 times across sections, which is more than minor trimming would catch; it lands at 3 rather than 4.	3 / 5
Actionability	Provides concrete, specific guidance throughout (exact gh/safe-outputs commands, exact label names, exact template path and JSON fields, exact ASCII symbol set), but references scripts/triage_state.py with a --help invocation while that file is absent from the bundle, a minor executability gap that holds it at 4.	4 / 5
Workflow Clarity	A 9-step sequenced execution checklist with an explicit pre-arbitration completeness gate (step 4) and re-render feedback loop (step 8), plus a Quality gates checklist; validation checkpoints and error-recovery feedback loops are explicit and complete, satisfying the anchor for 5.	5 / 5
Progressive Disclosure	Good structure that signals one-level-deep on-demand loading (persona .agent.md files, assets/label-contract.json, assets/triage-template.md, scripts/triage_state.py) with clear 'load at synthesis time only' guidance, but the referenced scripts/triage_state.py does not exist in the bundle, a real broken navigation path that prevents a 5.	4 / 5
	Total	16 / 20 Passed

Description

71%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 clear, well-bounded description that answers both what and when with concrete actions and a distinct niche. Its main weaknesses are jargon-heavy triggers lacking natural synonyms and a narrow, scheduler-gated activation condition.

Suggestions

Add natural user-facing trigger phrases and synonyms (e.g. 'triage', 'assess', 'prioritize an issue') alongside the scheduler jargon so users would naturally say the trigger terms.

Broaden or clarify the 'when' clause so it reads as a concrete trigger rather than only firing after a specific scheduler step.

Reconsider first/second-person phrasing compliance: 'Use this skill' is acceptable, but ensure no first-person voice slips in to protect the specificity score.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('triage ONE microsoft/apm issue', 'Return one advisory recommendation and a proposed scope brief'), but capability coverage is bounded more by exclusions than comprehensiveness, so it stops at 4 rather than 5.	4 / 5
Completeness	Explicitly answers both what (triage one issue, return advisory recommendation and scope brief) and when ('Use this skill to triage ONE microsoft/apm issue already selected by autopilot-issue-triage-scheduler'), but the trigger is gated and specialized rather than broadly concrete, capping it at 4 instead of 5.	4 / 5
Trigger Term Quality	Includes a couple of natural-ish keywords ('triage', 'issue') but is dominated by project jargon ('autopilot-issue-triage-scheduler', 'microsoft/apm') and lacks synonyms or common variations, placing it at 3 rather than 4.	3 / 5
Distinctiveness Conflict Risk	Tightly scoped to a single project and a specific scheduler-selected issue, giving a clear niche with minimal conflict risk; it is clearly distinguishable from other skills.	5 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 6 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: microsoft/apm
Path: .agents/skills/autopilot-issue-triage-worker/SKILL.md
Commit: b914b1b

Reviewed: 4 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.