CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

autopilot-pr-review-worker

Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. panel-mode (full | lean | delta) selects a surface-gated roster plus a CEO synthesizer; omitted or unknown mode is lean. Do not spawn inactive stubs. The orchestrator is the sole writer to the PR: ONE recommendation comment, no verdict labels, no merge gating. The panel is advisory -- it surfaces findings, prioritizes follow-ups, and renders a ship-recommendation that the maintainer and author weigh.

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 ./packages/autopilot/autopilot-pr-review-worker/SKILL.md

The canonical home for this skill is autopilot-pr-review-worker in microsoft/apm

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

An exceptionally actionable, validation-heavy orchestration spec: every step has exact commands, schemas, budgets, and error-recovery paths, and the bundle files it cites are real and well-integrated. Its weaknesses are redundancy — the same invariants (non-empty exit, advisory-not-gate, label-sweep rationale) restated in four to six places — plus one dangling reference and content duplicated between SKILL.md and assets/panel-mode.md.

Suggestions

Consolidate the spawn-and-forget / non-empty-exit warning, currently stated in 'Architecture invariants', the checklist preamble, step 5, step 9, and 'Gotchas', into one canonical section referenced from the other locations.

Defer roster, Models, and lean/delta cap details to assets/panel-mode.md instead of restating them in SKILL.md — the duplication is a sync hazard the 'Roster invariant' gotcha itself acknowledges.

Fix or remove the dangling reference to evals/fixtures/03-panel-mode-walkthrough.md, which does not exist in the bundle.

DimensionReasoningScore

Conciseness

Nearly all content is project-specific contract Claude cannot infer ("Single-writer interlock", "Synchronous fan-out -- never spawn-and-forget", gh-aw safe-output semantics), so no tokens teach known concepts. But the same warnings repeat across sections: the empty-output/background-spawn failure is restated in "Architecture invariants", the checklist preamble, step 5, step 9, and "Gotchas", and the advisory/no-verdict-label point appears ~6 times. Mostly efficient but could be tightened by consolidating; not 2 because the padding is concentrated in repeated warnings rather than pervasive unnecessary explanation.

3 / 5

Actionability

Fully executable throughout: exact commands ("gh pr view <PR_NUMBER> --json author,reviewRequests,headRefOid", "gh pr edit --add-reviewer @me"), a runnable script invocation with flags and an example path, exact label lists ("[panel-review, panel-approved, panel-rejected]"), a literal receipt line format, concrete budgets ("< 8 KB", "65536 characters"), and copy-paste prompt contracts for every subagent spawn. Not 4 because the common cases are covered with no material gaps.

5 / 5

Workflow Clarity

A strictly ordered 0-9 execution checklist with explicit validation checkpoints and feedback loops at every stage: acceptance gate (step 0), CODEOWNERS last-comment gate (1b), delta noop (1c), persona preflight via script (2b), schema validation with bounded re-spawn ("Maximum two re-spawn attempts") and placeholder fallback (step 4), CEO re-spawn-once on failure, and the ownership consistency gate ("re-render once. If it still contradicts, emit noop"). This matches the anchor-5 pattern of clear sequence, explicit validation, and error-recovery loops.

5 / 5

Progressive Disclosure

Bundle structure is real and well-signaled one level deep: all referenced assets exist (assets/panel-mode.md, panelist-return-schema.json, ceo-return-schema.json, recommendation-template.md, shared-brief.example.json, scripts/check_required_agents.py) and each is cited with its purpose ("Load assets/panel-mode.md before fan-out", "Shape: assets/shared-brief.example.json"). But "evals/fixtures/03-panel-mode-walkthrough.md" is referenced and absent from the bundle, and roster/Models/lean-cap/shared-brief rules are duplicated between SKILL.md and assets/panel-mode.md instead of deferred. Not 5 because of the broken reference and the inline duplication; not 3 because references are clearly signaled and most content is appropriately placed.

4 / 5

Total

17

/

20

Passed

Description

75%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 highly specific and clearly differentiated, with concrete actions and an unambiguous single-writer contract. Its main weakness is the missing explicit 'when to use' clause and the absence of natural trigger synonyms like 'PR' or 'code review', leaving activation guidance only weakly implied by 'labelled pull request'.

Suggestions

Add an explicit trigger clause, e.g. "Use when a pull request in microsoft/apm is labelled panel-review (and a linked issue or the PR carries status/accepted) and an advisory review is requested."

Include natural trigger synonyms users would actually say — "PR", "code review", "panel review" — alongside "pull request" and "advisory review".

State the activation condition (who or what invokes it: merge-worker, scheduler, or human) in one sentence so the 'when' is explicit rather than inferred from the target object.

DimensionReasoningScore

Specificity

Quotes: "run a multi-persona expert advisory review", "selects a surface-gated roster plus a CEO synthesizer", "surfaces findings, prioritizes follow-ups, and renders a ship-recommendation", "ONE recommendation comment, no verdict labels, no merge gating". Multiple concrete actions comprehensively covering the skill's behavior; not 4 because the action coverage has no real gaps within its domain.

5 / 5

Completeness

The 'what' is explicit ("run a multi-persona expert advisory review ... The orchestrator is the sole writer to the PR: ONE recommendation comment"), but there is no 'Use when...' clause or equivalent explicit trigger guidance — "on a labelled pull request in microsoft/apm" only weakly implies when to activate. Per the guideline, a missing explicit when-clause caps this at 3; not 4 because the 'when' is implied by domain rather than stated.

3 / 5

Trigger Term Quality

Natural terms present: "pull request", "advisory review", "panel-mode", "merge gating", "findings". Good keyword coverage, but common variations users say are missing ("PR", "code review", "panel review"); not 5 because no synonyms or shorthand forms appear, not 3 because coverage goes well beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers: repo-scoped ("a labelled pull request in microsoft/apm"), mode-parameterized ("panel-mode (full | lean | delta)"), and behaviorally unique ("no verdict labels, no merge gating"). Minimal conflict risk with any generic review skill; not 4 because the scoping leaves essentially no overlap.

5 / 5

Total

17

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (768 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 2 possibly missing (references/algorithmic-patterns.md, scripts/perf/)

Warning

Total

13

/

16

Passed

Repository

microsoft/apm

Path

packages/autopilot/autopilot-pr-review-worker/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.