Menü
Master orchestrator control for PR lifecycle management with multi-agent coordination
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Setup Nuxt/Vue/TypeScript project. Use when user needs to install dependencies, prepare Nuxt, setup LSP, or fix TypeScript errors in a Nuxt/Vue project. Works in both main repo and worktrees.
Manage git worktrees. Use when user wants to create, list, delete, or switch worktrees. Helps with branch-based development workflows where each branch has its own working directory.
Maintain the Claude Code plugin marketplace - create plugins, add skills, bump versions, update registry. Use when creating new plugins, adding skills/agents/commands to plugins, updating versions, or managing the marketplace registry.
SSH operations for remote server management, tunneling, and proxy-based connections. Use when connecting to remote servers, running remote commands, setting up SSH tunnels, port forwarding, managing jump hosts/bastions, or executing kubectl/k9s on remote clusters. Triggers on SSH, remote, tunnel, bastion, jump host, port forward, or remote kubernetes access.
Kubernetes troubleshooting and debugging workflows. Use when diagnosing pod failures, networking issues, resource problems, CrashLoopBackOff, ImagePullBackOff, pending pods, OOMKilled, or any cluster issues. Covers systematic debugging approaches and common failure patterns.
Generate Kubernetes manifest templates for deployments, services, configmaps, secrets, ingress, and other resources. Use when creating new k8s resources, scaffolding applications, or needing YAML templates. Triggers on requests to create, generate, or scaffold kubernetes resources.
| name | orchestrator-control-skill |
| description | Master orchestrator control for PR lifecycle management with multi-agent coordination |
| allowed-tools | Bash,Read,Write,Edit |
| version | 1.1.0 |
This skill spawns a control thread that manages the entire orchestrator, PR shepherds, and multi-agent coordination.
Activate this skill when the user wants to:
# Start orchestrator control thread
ct control start [--interactive] [--auto-merge]
# Check control status
ct control status
# Stop control
ct control stop
# Watch a PR with full lifecycle management
ct pr watch <number> [--auto-merge] [--interactive] [--poll-interval 30]
# Check PR lifecycle status
ct pr status <number>
# View PR comment status
ct pr comments <number>
# List all watched PRs
ct pr list
| Flag | Description | Default |
|---|---|---|
--auto-merge | Auto-merge when all criteria met | notify only |
--interactive | Confirm actions before executing | autonomous |
--poll-interval | Seconds between PR status polls | 30 |
A PR is considered "done" when ALL are true:
CRITICAL: Do NOT use "pending" states that wait passively. Always check proactively:
# Check IMMEDIATELY after Copilot review arrives
UNRESOLVED=$(gh api graphql -f query='query {
repository(owner: "hanibalsk", name: "property-management") {
pullRequest(number: <PR_NUMBER>) {
reviewThreads(first: 100) { nodes { isResolved } }
}
}
}' | jq '[.data.repository.pullRequest.reviewThreads.nodes[] | select(.isResolved == false)] | length')
if [ "$UNRESOLVED" -gt 0 ]; then
# Spawn review-comment-handler agent IMMEDIATELY
# Do NOT mark as "pending" and wait
fi
Use the GitHub Actions workflows for approval:
# Trigger auto-approve (waits for CI, checks conditions)
gh workflow run auto-approve.yml -f pr_number=<PR_NUMBER>
# Direct approval (with options)
gh workflow run approve-pr.yml -f pr_number=<PR_NUMBER> [-f skip_ci_check=false]
Control Thread (ct control start)
|
+-- Git Poller (polls PR status)
|
+-- PR Shepherd (per watched PR)
|
+-- Merge Conflict Agent (on conflict)
|
+-- Comment Handler Agent (per comment)
# Start orchestrator control
ct control start --auto-merge
# Watch a specific PR
ct pr watch 123 --auto-merge
# The system will:
# 1. Poll PR status every 30 seconds
# 2. Detect and auto-resolve merge conflicts
# 3. Handle all review comments (respond + resolve)
# 4. Auto-merge when all criteria are met
# Start in interactive mode
ct control start --interactive
# You'll be asked to confirm:
# - Spawning new PR shepherds
# - Auto-merging PRs
# - Handling escalations
ct control start
ct pr watch 123
ct pr watch 124
ct pr watch 125
# Check status of all
ct pr list
# Detailed status
ct pr status 123
ORCHESTRATOR_STARTED - Control thread startedSHEPHERD_SPAWNED - New PR shepherd spawnedSYSTEM_STATUS - Periodic status updatePR_STATE_CHANGED - State machine transitionMERGE_CONFLICT_DETECTED - Conflict needs resolutionREVIEW_COMMENTS_PENDING - Comments need handlingPR_READY_FOR_MERGE - All criteria metMERGE_CONFLICT_RESOLVED - Conflict fixedCOMMENT_RESPONDED - Reply postedCOMMENT_RESOLVED - Thread closedThis skill extends the threads skill with:
Use alongside:
bmad-autopilot for epic developmentthread-spawner for parallel thread creationSub-agents use memory-efficient fork worktrees:
PR Base Worktree (created when watching PR)
│
├── Fork: conflict-resolver (on conflict)
│ └── Shares git objects with base
│
├── Fork: comment-handler-1 (per comment)
│ └── Shares git objects with base
│
└── Fork: comment-handler-2
└── Shares git objects with base
After each fork completes:
1. Merge fork back to base
2. Remove fork
3. Push from base (once for all)
# Create fork for sub-agent
ct worktree fork 123 conflict-fix fix/conflict conflict_resolution
# After sub-agent completes
ct worktree merge-back conflict-fix
ct worktree remove-fork conflict-fix
# Push from base
cd $(ct worktree base-path 123)
git push
Run orchestrator on central server with remote workers:
# Central server
ct api start --bind 0.0.0.0 --token $TOKEN
# Worker machines
ct remote connect central:31337 --token $TOKEN
ct spawn epic-7a --template bmad-developer.md
if ! ct worktree merge-back my-fork; then
# Retry with fresh fork
ct worktree remove-fork my-fork --force
ct worktree base-update 123
# Re-fork and retry
fi
# Check for inconsistencies
ct worktree reconcile
# Auto-fix orphans
ct worktree reconcile --fix