CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

autopilot-pr-review-scheduler

Queue microsoft/apm pull requests labelled `panel-review` (or an explicit named list) and fan them out through an isolated pool (default 2) of autopilot-pr-review-worker sessions. Advisory only. Never implements. Never composes autopilot-pr-merge-worker. Never review every open PR. Works in a local session, Copilot App automation, Cloud Agent, Remote Agent, or Agentic Workflow. Does not triage issues or open greenfield PRs.

63

Quality

79%

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-review-scheduler/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

The body is highly actionable and workflow-clear: concrete gh commands, an exact activation card, a mandatory queue table, and fail-closed validation checkpoints throughout a batch fan-out process. Its only weaknesses are minor redundant guardrails and a dense, manual-like inline structure that externalizes just one asset.

DimensionReasoningScore

Conciseness

The body is lean and directive with no concept explanations Claude already knows (no 'what a PR/CODEOWNERS is'), but a few guardrails are repeated ('Never compose autopilot-pr-merge-worker', 'Do not comment/label...', 'Never list all open PRs') across sections, which is trimmable redundancy placing it just below the 5 'every token earns its place' anchor.

4 / 5

Actionability

Provides copy-paste-ready executable commands (`gh pr list --state open --label panel-review --json ...`), an exact activation-card template with defined fields, and a mandatory queue table with concrete column specs and drop-rationale strings, matching the 5 'fully executable, copy-paste ready, covers common cases' anchor.

5 / 5

Workflow Clarity

The Procedure section gives a clear numbered sequence with explicit validation checkpoints and fail-closed feedback loops (probe sibling -> stop, CODEOWNERS gate 'unclear -> fail closed', 'Missing table -> stop. Do not spawn.', empty keep-set = success, slot-return -> dispatch next), satisfying the 5 anchor with checklists and error-recovery loops for this batch operation.

5 / 5

Progressive Disclosure

Structure is good with clear section headers and a well-signaled one-level-deep reference to a real bundle file ('Load [assets/fan-out-pool.md]'), but the body is a dense manual keeping most detail inline with only one externalized asset, so it sits at 4 'good structure, references mostly clear' rather than the 5 'lean overview with well-split references'.

4 / 5

Total

18

/

20

Passed

Description

62%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.

The description is specific and strongly distinct, with explicit boundary statements that prevent mis-triggering against sibling scheduler skills. Its main weakness is the absence of an explicit 'Use when...' trigger clause and sparse natural-language trigger terms, which cap completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g. 'Use when the user asks to review queued microsoft/apm PRs or mentions the panel-review label').

Include common synonyms users say — 'PRs', 'review queue', 'panel review' — alongside the technical 'panel-review' label to raise trigger-term coverage.

Lead with the one-line action summary before the boundary 'Never' clauses so the 'what' lands first and reads more concisely.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — 'Queue microsoft/apm pull requests labelled `panel-review`', 'fan them out through an isolated pool (default 2) of autopilot-pr-review-worker sessions' — but the core actions reduce to queue + fan-out with parameters rather than a comprehensive action list, so it sits just below the comprehensive 5 anchor.

4 / 5

Completeness

The 'what' is clear (queue and fan out advisory PR reviews) but there is no explicit 'Use when...' trigger clause; the 'when' is only weakly implied via the panel-review label, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords exist ('pull requests', 'review', 'panel-review') but the phrasing is domain-jargon-heavy and lacks common synonyms or natural variations a user would actually say (e.g. 'PRs', 'review queue'), matching the 'some relevant keywords but missing variations' anchor rather than the 4 'good coverage' anchor.

3 / 5

Distinctiveness Conflict Risk

The description carves an explicit niche and actively disambiguates from siblings ('Never composes autopilot-pr-merge-worker', 'Does not triage issues', 'Never review every open PR'), giving it a clear distinct trigger set with minimal conflict risk matching the 5 anchor.

5 / 5

Total

15

/

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-review-scheduler/SKILL.md

Revision

0495ced

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill