CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

autopilot-pr-triage-scheduler

Queue open microsoft/apm pull requests (community fixes, PRs without an issue, or PRs that close an issue) and fan them out through an isolated pool (default 2) of autopilot-pr-triage-worker sessions. Advisory only. Never merges, never assigns, never requests reviewers, never runs autopilot-pr-review-worker. Activate on a mixed PR list or queue-open when the job is PR triage. Works in a local session, Copilot App automation, Cloud Agent, Remote Agent, or Agentic Workflow.

64

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/autopilot-pr-triage-scheduler/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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, and validation-conscious body with executable helper commands, a mandatory queue table, and properly signaled one-level-deep bundle references. It is held just below top marks by recurring constraint redundancy and the lack of fix-retry feedback loops.

Suggestions

Deduplicate the 'never comments/labels/assigns' constraints by stating them once in 'Hard nos' and referencing that section elsewhere, to tighten conciseness toward 5.

Add a short fix-retry feedback loop for helper failures (e.g., 'on fetch_queue failure: verify gh availability / --records-json fallback, then re-run') to lift workflow clarity from 4 to 5.

Move the full activation-card template and queue-table column spec into a referenced asset file so the SKILL.md body stays a lean overview, improving progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and assumes Claude's competence without explaining known concepts; minor redundancy (the 'never comments/labels/assigns' constraints recur in Activation card, Invocation, Selection, and Hard nos) keeps it just below the lean 5 anchor.

4 / 5

Actionability

Provides concrete executable commands ('python <this-skill>/scripts/fetch_queue.py --kind pr --mode sweep --repo microsoft/apm > batch.json', '--mode dispatch --number N') and a fill-in activation-card template; residual placeholders like <this-skill> and <positive integer> leave minor gaps, matching the 4 anchor.

4 / 5

Workflow Clarity

The Procedure is a clear 4-step sequence with explicit fail-closed validation checkpoints ('Missing -> stop', 'Missing table ... -> stop. Do not spawn.') and a mandatory queue-table checklist; because validation is present (and the skill is advisory/non-destructive), the batch-cap of 3 does not apply, but absent fix-retry feedback loops keep it at 4 rather than 5.

4 / 5

Progressive Disclosure

Body is an overview that signals one-level-deep bundle references (assets/fan-out-pool.md, scripts/fetch_queue.py, scripts/triage_state.py, assets/label-contract.json) which exist on disk; the full activation card and queue-table format are inlined rather than split out, a minor organization gap placing it at 4.

4 / 5

Total

16

/

20

Passed

Description

78%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 specific, well-scoped description that states concrete actions, explicit trigger guidance, and clear disambiguation from sibling triage skills. It is strong across all dimensions with only minor room for more natural trigger synonyms and a sharper 'when' clause.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Queue open microsoft/apm pull requests', 'fan them out through an isolated pool (default 2) of autopilot-pr-triage-worker sessions') plus explicit selection criteria; the 'never merges/assigns/requests reviewers' lines are constraints rather than actions, leaving minor coverage gaps, so it sits at 4 rather than 5.

4 / 5

Completeness

Answers both 'what' (queues and fans out PRs through worker sessions, advisory only) and 'when' ('Activate on a mixed PR list or queue-open when the job is PR triage'); the 'when' is explicit but could be more specific, matching the 4 anchor and avoiding the missing-trigger cap of 3.

4 / 5

Trigger Term Quality

Includes natural trigger phrases users would say ('pull requests', 'PR triage', 'mixed PR list', 'queue-open') and an explicit activation clause; a few common synonyms/variations are absent, so it is above the midpoint but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

Narrow niche (PR triage scheduling for microsoft/apm) with explicit disambiguation against sibling skills ('Never ... runs autopilot-pr-review-worker') and distinct triggers, giving minimal conflict risk.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

microsoft/apm

Path

.agents/skills/autopilot-pr-triage-scheduler/SKILL.md

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.