Official agent skill

Autopilot Issue Delivery Scheduler

by microsoft in microsoft/apm

A skill your agent uses to queue maintainer-accepted microsoft/apm issues (status/accepted) and fan them out through an isolated pool (default 2) of autopilot-issue-delivery-worker sessions.

OfficialMITAuto-check passedProductivity & Automation

Install Autopilot Issue Delivery Scheduler

skills CLI
$ npx skills add microsoft/apm --skill autopilot-issue-delivery-scheduler -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install microsoft/apm autopilot-issue-delivery-scheduler --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/microsoft/apm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/autopilot-issue-delivery-scheduler .claude/skills/autopilot-issue-delivery-scheduler && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
autopilot-issue-delivery-scheduler
GitHub stars
4k
Token cost
~1.7k tokens
SKILL.md length
784 words
Files
2 (incl. assets)
Skills in repo
27
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses to queue maintainer-accepted microsoft/apm issues (status/accepted) and fan them out through an isolated pool (default 2) of autopilot-issue-delivery-worker sessions.

  • Works in 5 steps: Probe worker-code on disk. Missing… → Build the queue. Emit the mandatory… → Drain the selected list. Concurrent… → …
  • Queue maintainer-accepted microsoft/apm issues (status/accepted) and fan them out through an isolated pool (default
  • SKILL.md covers Activation card, Invocation, Selector and Selection, plus 4 more sections
  • Calls gh

What it does

Autopilot Issue Delivery Scheduler is an agent skill from microsoft/apm, published by the product's own GitHub organization. Use this skill to queue maintainer-accepted microsoft/apm issues (status/accepted) and fan them out through an isolated pool (default 2) of autopilot-issue-delivery-worker sessions. Any accepted type is eligible. Advisory triage/recommended is not authorization. Does not triage. Does not review PRs. Works in a local session, Copilot App automation, Cloud Agent, Remote Agent, or Agentic Workflow.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including assets (for example `assets/fan-out-pool.md`).

It sits in Productivity & Automation, covering App automation through connectors and Monitoring and alerting. The repository describes itself as: Agent Package Manager. The licence is MIT.

When your agent uses it

  • Queue maintainer-accepted microsoft/apm issues (status/accepted) and fan them out through an isolated pool (default
  • Of autopilot-issue-delivery-worker sessions

Example prompts

  • “/autopilot-issue-delivery-scheduler”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Probe worker-code on disk. Missing sibling -> stop.
  2. Build the queue. Emit the mandatory queue table (labels +
  3. Drain the selected list. Concurrent slots <= FANOUT_LIMIT.
  4. Never auto-merge.
  5. Print a final report from the table.

What it can do on your machine

Read from SKILL.md and the folder at commit 280b8a7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Autopilot Issue Delivery Scheduler loads about 1.7k tokens when it runs. Until then it costs about 109 tokens; SKILL.md has 784 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~109
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from microsoft/apm at commit 280b8a7, republished under its MIT licence (© microsoft). 784 words, ~1,704 tokens.

Download SKILL.mdSave it as .claude/skills/autopilot-issue-delivery-scheduler/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
autopilot-issue-delivery-scheduler
description
Use this skill to queue maintainer-accepted microsoft/apm issues (`status/accepted`) and fan them out through an isolated pool (default 2) of autopilot-issue-delivery-worker sessions. Any accepted type is eligible. Advisory `triage/recommended` is not authorization. Does not triage. Does not review PRs. Works in a local session, Copilot App automation, Cloud Agent, Remote Agent, or Agentic Workflow.
activation_card
on

autopilot-issue-delivery-scheduler

User-facing ACCEPTED-ISSUE implementation queue. This skill SELECTS authorized issues and THROTTLES fan-out. It does not triage and does not review PRs.

Compose autopilot-issue-delivery-worker one issue per slot. Never borrow slots from autopilot-issue-triage-scheduler, autopilot-pr-review-scheduler, or autopilot-pr-triage-scheduler.

Activation card

activation_card: on. Before any queue read or spawn, emit this Enter card with every field filled. Missing field -> stop.

text
skill: autopilot-issue-delivery-scheduler
skill_path: <resolved directory of this SKILL.md>
mode: run
subject: microsoft/apm
path: delivery
intent: select accepted issues and fan out delivery workers
origin: unattended | actor-session
write: off
repo: microsoft/apm
fanout_limit: <positive integer>
invocation: agentic-workflow | actor-session

Rules:

  • write is always off. This scheduler never comments, labels, assigns, or requests reviewers.
  • write: on -> stop.
  • origin fail-closed unknown -> unattended.
  • invocation is the harness. Copilot App, local session, Cloud Agent, and Remote Agent are actor-session. agentic-workflow is only gh-aw / GitHub Actions. Do not copy origin into invocation.
  • One queue. Do not nest another scheduler path.

After the run, emit this Exit receipt:

text
skill: autopilot-issue-delivery-scheduler
subject: microsoft/apm
path: delivery
write: off
queued: <integer>
spawned: <integer>
approved: n/a

Invocation

Works in local sessions, Copilot App automations, Cloud Agent, Remote Agent, and Agentic Workflows.

Resolve ORIGIN before any GitHub write:

  • unattended -- workers still run; they must not assign.
  • actor-session -- workers treat assignment as a hard gate before any implementation. Assignment is the public signal of which user is working the issue.

Ownership writes:

  • Issue triage: none (no assignment needed)
  • Code (accepted implementation): assign the implementing user (@me)
  • PR review: request the reviewing user as reviewer, never assignee

INTENT for this scheduler is implement only as a parent signal to workers. This scheduler itself never assigns, never requests reviewers, and never writes human decision labels.

Selector

  • all (default) -- every open issue that already carries status/accepted, plus any issue the caller named as a bounded accept. Type does not matter (type/bug, type/feature, type/automation, docs, refactor). Escalate everything else. Do not run triage-panel from this scheduler.
  • bugs -- same gate, plus type/bug. Worker uses LEGIT / UNCLEAR / FIXED-AT-HEAD plus PRINCIPLES.md alignment.

type/bug or triage/recommended without status/accepted is not eligible unless the caller named a bounded accept.

Selection

Build the queue from the caller list or gh issue list on status/accepted (selector bugs: also require type/bug).

An issue is eligible for the queue only if it already carries status/accepted or the caller named it as a bounded accept. That membership is a communication signal, not implementation permission. triage/recommended and legacy status/triaged are advisory processing markers and are not authorization. Workers re-check scripts/governance/eligibility.cjs from the trusted default branch and require fresh responsible-human confirmation before any mutate. ORIGIN unattended never implements. Do not dispatch an unaccepted issue. Do not run triage-panel to create any marker. Do not write status/accepted.

Skip locked and closed issues unless the caller named them. Deduplicate by number. Do not skip bot-authored issues that already carry status/accepted or that the caller named. Human accept is the gate; author type is not.

Skip status/needs-design unless the caller named the issue. Skip status/needs-triage and status/deferred unless named. Skip status/shepherding and status/in-flight unless named (those belong to PR review or an in-flight owner). Skip issues assigned to another user unless the caller named them; do not steal in-progress work.

Do not open a second PR when one already addresses the issue; return that PR number.

After a worker opens a PR, do NOT fill this pool with autopilot-pr-merge-worker. Hand the PR number to the caller for autopilot-pr-review-scheduler.

Show full SKILL.md (273 more words)Show less

Queue table (mandatory)

Before any spawn, emit the keep-set and the drop-set in plan.md and in the session report. Missing table, missing column, or blank rationale -> stop. Do not spawn.

Keep-set (items this run will schedule). One row per item. Do not truncate to FANOUT_LIMIT:

| number | kind | labels | rationale | slot |

Drop-set (considered, then not scheduled). slot is -:

| number | kind | labels | rationale | slot |

  • kind: issue or pr
  • labels: current GitHub labels, comma-separated; none if empty
  • rationale: why queued or dropped (helper rule and labels)
  • slot: 1-based spawn order, or - when dropped

Empty keep-set is success. Still emit the drop-set, or none. You are the sole table writer. Put selector and existing-PR facts in rationale.

Fan-out

Load assets/fan-out-pool.md. Default FANOUT_LIMIT=2 concurrent slots. Isolated to this run. FANOUT_LIMIT is concurrency, not queue length. Drain the full selected list; when a slot returns, fill it with the next item.

Procedure

  1. Probe worker-code on disk. Missing sibling -> stop.
  2. Build the queue. Emit the mandatory queue table (labels + rationale) before any spawn.
  3. Drain the selected list. Concurrent slots <= FANOUT_LIMIT. One issue per slot. When a slot returns, dispatch the next queued issue. Do not stop because the pool was full. Name each worker session Issue delivery #<issue-number>.
  4. Never auto-merge.
  5. Print a final report from the table.

Hard nos

  • Do not share this pool.
  • Do not dispatch the same issue to two slots.
  • Do not dispatch an unaccepted issue.
  • Do not dispatch an issue assigned to another user unless named.
  • Do not drop a bot-authored issue that already carries status/accepted.
  • Do not triage or review PRs inside this scheduler.
  • Do not contradict CODEOWNERS.
  • ASCII only.

© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (assets) in .agents/skills/autopilot-issue-delivery-scheduler of microsoft/apm.

  • SKILL.md
  • assets/fan-out-pool.md

Open the folder on GitHubat commit 280b8a7

Compare with similar skills

Autopilot Issue Delivery Scheduler next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Autopilot Issue Delivery Scheduler compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Autopilot Issue Delivery Scheduler this skillmicrosoft/apm4k—~1.7kAutomated safety check: PassMIT
Pagerduty Automationdavepoon/buildwithclaude3.6k7 repos~2.6kAutomated safety check: PassMIT
GitHub Automationdavila7/claude-code-templates32k5 repos~2.8kAutomated safety check: PassMIT
External Electron App Automationcashew-labs/libretto904—~967Automated safety check: PassMIT
Release Reviewm4r1k/Eneru149—~1.9kAutomated safety check: PassMIT
Live Debugmacro-inc/macro4.6k—~2.4kAutomated safety check: NotesAGPL-3.0

Similar skills

  • Pagerduty Automation

    davepoon/buildwithclaude

    Automate PagerDuty tasks via Rube MCP (Composio): manage incidents, services, schedules, escalation policies, and on-call rotations.

    3.6k GitHub starsUsed in 7 repos~2.6k tokens
    Productivity & AutomationAuto-check passed
  • GitHub Automation

    davila7/claude-code-templates

    Automate GitHub repositories, issues, pull requests, branches, CI/CD, and permissions via Rube MCP (Composio).

    32k GitHub starsUsed in 5 repos~2.8k tokens
    Productivity & AutomationAuto-check passed
  • Drives desktop Electron apps already installed on your machine, such as Slack, Discord or VS Code, by relaunching them with a debugging port and using the Libretto CLI.

    904 GitHub stars~967 tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed
  • Release Review

    m4r1k/Eneru

    Mandatory pre-release deep review for minor/major releases (X.Y.0 / X.0.0).

    149 GitHub stars~1.9k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Live Debug

    macro-inc/macro

    Debug the running local stack with traces, logs, and a shared headless browser.

    4.6k GitHub stars~2.4k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Circleci Automation

    davepoon/buildwithclaude

    Automate CircleCI tasks via Rube MCP (Composio): trigger pipelines, monitor workflows/jobs, retrieve artifacts and test metadata.

    3.6k GitHub starsUsed in 7 repos~1.7k tokens
    Productivity & AutomationAuto-check passed

More from microsoft/apm

All 27 skills in this repo
  • Cut Release

    microsoft/apm

    Official

    A skill your agent uses to cut an APM release from the current worktree: assess whether the cycle since the last tag warrants a patch or minor bump (semver discipline against the…

    4k GitHub stars~2.5k tokensUpdated 2 days ago
    Auto-check passed
  • Docs Corpus Audit

    microsoft/apm

    Official

    A skill your agent uses to run a holistic regrounding pass on the entire microsoft/apm documentation corpus against current source code, page-by-page, and emit surgical fixes for stale claims.

    4k GitHub stars~2.6k tokensUpdated 2 days ago
    Auto-check passed
  • Official

    A skill your agent uses to verify CLAIM-LEVEL grounding of a documentation page (or set of pages) against the source code.

    4k GitHub stars~1.9k tokensUpdated 2 days ago
    Auto-check passed
  • Official

    A skill your agent uses to write the PR description (PR body) for any pull request opened against microsoft/apm.

    4k GitHub stars~4.1k tokensUpdated 2 days ago
    Auto-check passed
  • Official

    A skill your agent uses to implement ONE microsoft/apm issue already selected by autopilot-issue-delivery-scheduler.

    4k GitHub stars~1.7k tokensUpdated 2 days ago
    Auto-check passed
  • Official

    Drive ONE already selected open pull request in microsoft/apm to mergeable.

    4k GitHub stars~3.4k tokensUpdated 2 days ago
    Auto-check passed

Questions about Autopilot Issue Delivery Scheduler

What does Autopilot Issue Delivery Scheduler do?

A skill your agent uses to queue maintainer-accepted microsoft/apm issues (status/accepted) and fan them out through an isolated pool (default 2) of autopilot-issue-delivery-worker sessions. Autopilot Issue Delivery Scheduler is an agent skill from microsoft/apm, published by the product's own GitHub organization. Use this skill to queue maintainer-accepted microsoft/apm issues (status/accepted) and fan them out through an isolated pool (default 2) of autopilot-issue-delivery-worker sessions.

When should I use Autopilot Issue Delivery Scheduler?

Autopilot Issue Delivery Scheduler fits situations like: queue maintainer-accepted microsoft/apm issues (status/accepted) and fan them out through an isolated pool (default; of autopilot-issue-delivery-worker sessions.

How do I install Autopilot Issue Delivery Scheduler in Claude Code?

Run `npx skills add microsoft/apm --skill autopilot-issue-delivery-scheduler -a claude-code`. Or copy the skill folder (.agents/skills/autopilot-issue-delivery-scheduler in microsoft/apm) into .claude/skills/autopilot-issue-delivery-scheduler in your project. Claude Code loads it when a task matches its description.

How do I install Autopilot Issue Delivery Scheduler in Codex?

Run `npx skills add microsoft/apm --skill autopilot-issue-delivery-scheduler -a codex`. Or copy the skill folder (.agents/skills/autopilot-issue-delivery-scheduler in microsoft/apm) into .agents/skills/autopilot-issue-delivery-scheduler in your project. Codex loads it when a task matches its description.

Can I use Autopilot Issue Delivery Scheduler in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microsoft/apm --skill autopilot-issue-delivery-scheduler -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/autopilot-issue-delivery-scheduler, .gemini/skills/autopilot-issue-delivery-scheduler, .github/skills/autopilot-issue-delivery-scheduler and .opencode/skills/autopilot-issue-delivery-scheduler in your project.

What does Autopilot Issue Delivery Scheduler need to run?

Going by SKILL.md and its folder, Autopilot Issue Delivery Scheduler needs the command-line tools its instructions call (gh).

Does Autopilot Issue Delivery Scheduler access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Autopilot Issue Delivery Scheduler safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Autopilot Issue Delivery Scheduler use?

Autopilot Issue Delivery Scheduler is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Autopilot Issue Delivery Scheduler use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Autopilot Issue Delivery Scheduler?

Skills that share tags, products or a category with Autopilot Issue Delivery Scheduler: Pagerduty Automation (davepoon/buildwithclaude, 3.6k stars), GitHub Automation (davila7/claude-code-templates, 32k stars), External Electron App Automation (cashew-labs/libretto, 904 stars) and Release Review (m4r1k/Eneru, 149 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Autopilot Issue Delivery Scheduler?

microsoft (a GitHub organization, an official publisher) maintains it in microsoft/apm, which has 3,982 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on October 7, 2026.

Source: microsoft/apm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.