Claude Cursor Skill

agent-orchestration

AI DevKit · Supervise multi-agent workflows over repeated passes: poll progress, unblock waiting agents, coordinate dependencies, relay outputs, resolve conflicts, and verify completion. Use only for ongoing multi-agent coordination, not one-off list/detail/send/start/kill action

LLM Mart · 0 points · 0 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download codeaholicguy-ai-devkit-skills_agent-orchestration-ac73d58.zip · 1 KB

codeaholicguy/ai-devkit 1639 257 forks Apache-2.0 Updated 1d ago

Part of codeaholicguy/ai-devkit — 24 skills

Install

skills CLI npx skills add https://github.com/codeaholicguy/ai-devkit/tree/main/skills/agent-orchestration

Claude Code

claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install codeaholicguy-ai-devkit@llmmart

Git git clone https://github.com/codeaholicguy/ai-devkit.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole codeaholicguy/ai-devkit collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Agent Orchestration

Use only for multi-agent supervision: coordinating dependencies, polling progress, unblocking waiting agents, relaying outputs, resolving conflicts, and verifying completion across agents. For one-off list/detail/send/start/kill work, use $agent-management or $agent-communication.

Use $agent-management for safe agent selection and lifecycle actions. Use $agent-communication for list/detail/send mechanics. Use $verify before accepting any agent's completion claim.

Rules

Own the loop until assigned work is complete, blocked, or stopped.
Run agent list --json before each pass; never assume names/statuses.
Inspect waiting, idle, unknown, missing, or stale agents before acting.
Send self-contained instructions and avoid duplicate follow-ups.
Sequence agents that touch the same files; relay only relevant upstream output.
Escalate only for repeated failures, unresolved conflicts, product/business decisions, or destructive/shared/production/security-sensitive actions.

Loop

If the goal or agent ownership is unclear, run one scan/detail pass. Ask the user once only if context is still insufficient.

Scan agents.
Assess agents needing attention with detail --tail 10.
Act: approve, clarify, correct, delegate, relay, verify, or escalate.
Report one brief status line.
Sleep 10-60s and repeat.

Completion

Finish when all assigned work is verified, blocked with a clear reason, or stopped by the user. Summarize per-agent outcomes, verification, unresolved issues, and next step.

Files (ai-devkit)

agents

openai.yaml 406 B

interface:
  display_name: "Agent Orchestration"
  short_description: "AI DevKit · Proactively orchestrate and coordinate running AI agents"
  default_prompt: "Use $agent-orchestration to scan all running agents, assess their status, send next instructions to waiting agents, and coordinate multi-agent workflows. Act as the lead — drive progress autonomously and escalate only when you need my input."

SKILL.md 1.9 KB

---
name: agent-orchestration
description: "AI DevKit · Supervise multi-agent workflows over repeated passes: poll progress, unblock waiting agents, coordinate dependencies, relay outputs, resolve conflicts, and verify completion. Use only for ongoing multi-agent coordination, not one-off list/detail/send/start/kill actions."
---

# Agent Orchestration

Use only for multi-agent supervision: coordinating dependencies, polling progress, unblocking waiting agents, relaying outputs, resolving conflicts, and verifying completion across agents. For one-off list/detail/send/start/kill work, use `$agent-management` or `$agent-communication`.

Use `$agent-management` for safe agent selection and lifecycle actions. Use `$agent-communication` for list/detail/send mechanics. Use `$verify` before accepting any agent's completion claim.

## Rules

- Own the loop until assigned work is complete, blocked, or stopped.
- Run `agent list --json` before each pass; never assume names/statuses.
- Inspect waiting, idle, unknown, missing, or stale agents before acting.
- Send self-contained instructions and avoid duplicate follow-ups.
- Sequence agents that touch the same files; relay only relevant upstream output.
- Escalate only for repeated failures, unresolved conflicts, product/business decisions, or destructive/shared/production/security-sensitive actions.

## Loop

If the goal or agent ownership is unclear, run one scan/detail pass. Ask the user once only if context is still insufficient.

1. Scan agents.
2. Assess agents needing attention with `detail --tail 10`.
3. Act: approve, clarify, correct, delegate, relay, verify, or escalate.
4. Report one brief status line.
5. Sleep 10-60s and repeat.

## Completion

Finish when all assigned work is verified, blocked with a clear reason, or stopped by the user. Summarize per-agent outcomes, verification, unresolved issues, and next step.