afk-team-workflow

Orchestrates unattended multi-agent execution of GitHub issue batches through staged pull requests.

4.3k|859|Updated Feb 7, 2026
One-click install
npx skills add https://github.com/ArcReel/ArcReel --skill afk-team-workflow
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: afk-team-workflow
Source: https://github.com/ArcReel/ArcReel/tree/main/.agents/skills/afk-team-workflow
Command: npx skills add https://github.com/ArcReel/ArcReel --skill afk-team-workflow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Coordinating a team of AI agents to implement, review, and merge an entire Spec's sub-issues without human supervision is error-prone: dependencies get missed, merges conflict, and interrupted runs lose state. This Skill acts as a team-lead that plans, dispatches, integrates, and adjudicates a batch of GitHub issues until every stage PR is merged or explicitly paused.

Core Features & Use Cases

  • Batch planning and dependency projection: Polls a Spec's sub-issues or an explicit issue list via the GitHub CLI, builds the canonical blocked-by graph, and partitions work into minimal independently mergeable stages.
  • Role-based agent delegation: Dispatches implementer, local-reviewer, and review-looper agents with contract prompts, isolated git worktrees, per-issue conventional commits, and a stage-level AI review loop that converges on a green, mergeable HEAD.
  • Crash-safe ledger and recovery: Appends decision, authorization, fault, and pause events to a thin JSONL ledger under .afk/, enabling a new team-lead to resume an unfinished batch from remote truth.
  • Use Case: Point it at Spec #42 with twelve sub-issues; it plans three stages, runs implementer/reviewer relays per issue, opens staged draft PRs with Closes references, drives each PR through AI review to green, rebase-merges them in order, and posts a human QA checklist on the Spec.

Quick Start

Ask the agent to use the afk-team-workflow skill to run Spec #42's sub-issues unattended until all stage PRs are merged.

Frequently Asked Questions about afk-team-workflow

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a GitHub Spec's sub-issues unattended with AI agents?

Invoke the skill with a Spec number; it polls sub-issues via the gh CLI, builds the dependency graph, plans mergeable stages, and delegates implementer and reviewer agents per issue. It keeps running until every stage PR is rebase-merged or a genuine business tradeoff forces a pause.

How does the skill recover an interrupted issue batch?

Recovery reads the batch's JSONL ledger under .afk/ for scope, then reconciles with remote truth: merged stages advance, open PRs resume from their remote HEAD, and completed issues are identified by Refs commits on the remote stage branch. Prior merge authorizations are not inherited and must be re-requested.

What tools does the afk-team-workflow skill require?

The scripts require the GitHub CLI (gh), jq, and git with worktree support. Issue dependencies use the native GitHub sub-issues and blocked-by APIs, with a body-based Blocked-by fallback when those endpoints return 404.

When does the unattended workflow pause and ask the user?

It pauses only for genuine business tradeoffs, uncovered Spec requirements, or unrecoverable faults blocking a green HEAD. Absorbable runtime failures and purely technical decisions are handled by the team-lead and recorded in the ledger without interrupting the user.

Can it run agents across different AI harnesses?

Yes. When HERDR_ENV=1, it reads the herdr-teammate reference and delegates through Herdr workspaces labeled with the batch ID; otherwise it uses the current harness's native teaming capabilities. Cross-harness teammates notify the team-lead pane with handoff or request messages.