Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →microsoft/apm-review-panel
Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. The panel fans out to five mandatory specialists plus a test-coverage specialist (active on every PR that touches src/) plus three conditional specialists (auth, doc-writer, performance-expert), all running in their own agent threads, and a CEO synthesizer. The orchestrator is the sole writer to the PR: ONE recommendation comment, no verdict labels, no merge gating. The panel is advisory --
Passed 12 of 19 test cases with the skill, and 4 of 19 without it.
and 14 more in the full report
11 fixed4 passed either way7 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
The python-architect subagent wants to style a modified class in a Mermaid class diagram by appending :::highlight directly to a relationship line like ClassA --|> ClassB:::highlight. How should class styling be formatted for GitHub rendering?
| Checked | Without skill | With skill |
|---|---|---|
| Class styles must be applied using standalone class Name:::cssClass declarations. | Missed | Passed |
The instructions your model reads when the skill loads.
The panel is FAN-OUT + SYNTHESIZER. Each persona runs in its own agent
thread (via the task tool) and returns JSON matching
assets/panelist-return-schema.json. The orchestrator schema-validates
each return, hands all returns to the apm-ceo synthesizer (also a task
thread, returns JSON matching assets/ceo-return-schema.json), then
renders ONE recommendation comment from assets/recommendation-template.md.
This skill is ADVISORY by design. It does not compute a binary verdict, it does not apply verdict labels, and it does not gate merge. The panel surfaces findings; the maintainer and the PR author decide ship.
APPROVE / REJECT,
no panel-approved / panel-rejected label, no deterministic verdict
computation. The CEO returns a ship_recommendation.stance (ship_now
/ ship_with_followups / needs_discussion / needs_rework); this is
prose for the human reviewer, never auto-applied as a label or status
check. This is the architectural fix for the previous regime's
over-strictness: removing the binary gate removes the incentive for
panelists to inflate required[] defensively.severity: blocking | recommended | nit. blocking is the highest
signal a panelist can send and renders prominently in the comment; it
still does not block merge. recommended is the default for substantive
feedback. nit is one-line polish. The orchestrator never reads
severity to gate anything.add-comment and one remove-labels call. The
remove-labels call always sweeps panel-review (trigger
idempotency) AND defensively removes panel-approved /
panel-rejected if present (legacy verdict labels from the
pre-advisory regime; they have no meaning here and would mislead
readers if left on a PR after a fresh advisory pass). NO add-labels
call -- there are no verdict labels to apply. Panelist subagents and
the CEO subagent return JSON only and MUST NOT call any gh write
command, post comments, apply labels, or touch the PR state.test cases passed, vs 4 / 19 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.