Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Autopilot Pr Triage Worker

ASecurity

Use this skill to triage ONE microsoft/apm pull request already selected by autopilot-pr-triage-scheduler. Covers community PRs that fix an issue and PRs opened without an issue. Return one advisory recommendation, never human approval, never a diff review, never merge. Not a queue manager and not autopilot-pr-review-worker.

3,953 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsgit

Works with

cli

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 9/20/2026

$npx -y skills add microsoft/apm --skill autopilot-pr-triage-worker --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Autopilot Pr Triage Worker?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Autopilot Pr Triage Worker
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/microsoft-autopilot-pr-triage-worker/badge)](https://www.skillsdirectory.com/skills/microsoft-autopilot-pr-triage-worker)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: autopilot-pr-triage-worker
activation_card: on
description: >-
  Use this skill to triage ONE microsoft/apm pull request already
  selected by autopilot-pr-triage-scheduler. Covers community
  PRs that fix an issue and PRs opened without an issue. Return one
  advisory recommendation, never human approval, never a diff review,
  never merge. Not a queue manager and not autopilot-pr-review-worker.
---

# autopilot-pr-triage-worker

Advisory classification of ONE already-selected PR. Do not review
the diff as `autopilot-pr-review-worker` does. Do not drive merge.

## Activation card

`activation_card: on`. Before any PR read or GitHub write, emit
this Enter card with every field filled. Missing field -> stop.

```text
skill: autopilot-pr-triage-worker
skill_path: <resolved directory of this SKILL.md>
mode: run
subject: microsoft/apm#<pr-number>
path: triage
intent: advise one already-selected PR
origin: unattended | actor-session
write: on | off
json: off | on
debug: off | on
repo: microsoft/apm
pr: <positive integer>
invocation: agentic-workflow | actor-session
```

Rules:

- `write` defaults to `on` when the caller omitted it.
- `write: off` returns the filled template only. Do not comment,
  add labels, or remove labels.
- `write: on` posts one GitHub comment via `autopilot-comment`
  and processing / classification labels. Never assign. Never
  request reviewers. Do not call `gh pr comment` yourself.
  Do not write `status/accepted`, `status/needs-design`, or
  `status/needs-triage`. Write `status/deferred` only when this
  PR is not labelled `status/accepted` and has no same-repo
  linked issue labelled `status/accepted`.
- `json` defaults to `off` when omitted or unknown. Omitted `json`
  is not a missing-field stop.
- `json: off` -> no machine JSON receipt.
- `json: on` -> fill JSON only as an internal payload (session
  file or parent Exit). Never post it on GitHub.
- `debug` defaults to `off` when omitted or unknown. Omitted `debug`
  is not a missing-field stop.
- `debug: off` -> pass `public_body` as the Suggested PR comment
  (unwrap the markdown fence) to `autopilot-comment`. Do not
  pass recommendation, linked issue, classification, or next
  action headings as `public_body`.
- `debug: on` -> pass `debug_body` as the filled template
  without a JSON fence. `autopilot-comment` prefixes
  `[i] Skill debug is on.`
- Load `autopilot-comment` before any GitHub comment write.
  `source_skill: autopilot-pr-triage-worker`. Missing card ->
  stop.
- `origin` fail-closed unknown -> `unattended`.
- One PR. Do not nest a scheduler path.

After the run, emit this Exit receipt:

```text
skill: autopilot-pr-triage-worker
subject: microsoft/apm#<pr-number>
path: triage
write: on | off
json: off | on
debug: off | on
posted: yes | no
labels_applied: <comma list or none>
approved: n/a
```

Read `assets/label-contract.json` (same contract as issue triage)
before reasoning. Do not invent a second marker.

## Origin and writes

No assignment needed. Never request reviewers. Unattended and
actor-session are equally read-only for ownership.

This worker owns those writes even when summoned without a
scheduler. The scheduler must not comment or label.

Allowed writes: one advisory comment plus processing / optional
classification labels from the contract. Never write
`status/accepted`, `status/needs-design`, or
`status/needs-triage`.

Auto-defer: if this PR is not labelled `status/accepted` and
has no same-repo linked issue labelled `status/accepted`, add
`status/deferred` (`write: on` only).
Do not overwrite `status/accepted` already on the PR. Linked
means `Fixes` / `Closes` / `#N` in the body or commits, or
GitHub `closingIssuesReferences`, same repository. Any one
accepted linked issue or `status/accepted` on the PR blocks
auto-defer.

CODEOWNERS `reviewRequests` is runtime authority. Note owners in
the comment. Never add or remove review requests.

## Context (mandatory)

Before advising, paginate the complete PR conversation, reviews,
and review comments. If the body or commits reference `Fixes` /
`Closes` / `#N`, read that issue's complete conversation too.
No fresh advisory without that context.

If a prior triage comment's watermark still matches HEAD
conversation, no-op (do not post a duplicate).

## Procedure

1. Confirm the PR is the single target. Missing number -> stop.
2. Gather full context. Record whether this PR is labelled
   `status/accepted`, and linked same-repo issues and whether
   any carries `status/accepted`.
3. Fill [assets/pr-triage-template.md](assets/pr-triage-template.md).
   Recommendation is one of: `ready-for-review` | `needs-design` |
   `needs-issue` | `duplicate-of` | `decline-with-reason` |
   `auto-handle`.
4. Neither this PR nor a linked same-repo issue is
   `status/accepted` -> recommend `needs-issue`,
   add `status/deferred` when `write: on`, and thank the author.
   Invite them to open an issue for maintainer review and
   acceptance first, per CONTRIBUTING.md ("Start with an issue,
   not an implementation."). Link
   https://github.com/microsoft/apm/blob/main/CONTRIBUTING.md
5. `ready-for-review` when this PR or a linked same-repo issue is
   `status/accepted`. It is not merge approval and is not a
   request to run `autopilot-pr-review-scheduler`.
6. Post only if the comment would change. Probe
   `$REPO_ROOT/.agents/skills/autopilot-comment/SKILL.md` (or the
   sibling package). Missing -> stop. Do not post. Activate
   `autopilot-comment` (`source_skill:
   autopilot-pr-triage-worker`). Do not call `gh pr comment`
   yourself. `debug: off`: Suggested PR comment body as
   `public_body` (not the filled template). `debug: on`: filled
   template as `debug_body`. Missing footer after that write
   is a failed post -- patch via `autopilot-comment`
   (`intent: patch`). Add the contract processing marker.
   Do not remove `status/needs-triage`.

## Hard nos

- Do not merge, push, assign, or request reviewers.
- Do not run `autopilot-pr-review-worker` or `autopilot-pr-merge-worker`.
- Do not contradict CODEOWNERS.
- Do not treat labels or this comment as `status/accepted`.
- Do not write `status/deferred` when a linked issue is
  `status/accepted` or the PR already has `status/accepted`.
- ASCII only.

Attribution

microsoftmicrosoft
View sourceSee grades on GitHubMore from microsoft →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →