Agent Skills › codeaholicguy/ai-devkit › agent-orchestration

agent-orchestration

GitHub

负责多智能体工作流的持续监督与协调,包括轮询进度、解除阻塞、依赖协调、输出中继及冲突解决。适用于多轮迭代中的复杂协作场景,而非单次操作。

skills/agent-orchestration/SKILL.md codeaholicguy/ai-devkit

Trigger Scenarios

需要协调多个智能体的依赖关系 监控并推进多智能体工作流进度 处理智能体间的冲突或阻塞状态

Install

npx skills add codeaholicguy/ai-devkit --skill agent-orchestration -g -y
More Options

Use without installing

npx skills use codeaholicguy/ai-devkit@agent-orchestration

指定 Agent (Claude Code)

npx skills add codeaholicguy/ai-devkit --skill agent-orchestration -a claude-code -g -y

安装 repo 全部 skill

npx skills add codeaholicguy/ai-devkit --all -g -y

预览 repo 内 skill

npx skills add codeaholicguy/ai-devkit --list

SKILL.md

Frontmatter
{
    "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.

Version History

  • d2e170a Current 2026-11-02 14:56

    将 agent-orchestration 设为内置技能,并使用无框架特定的技能引用格式

  • 15b09d2 2026-07-31 07:50

Same Skill Collection

skills/agent-communication/SKILL.md
skills/agent-management/SKILL.md
skills/ai-devkit-setup/SKILL.md
skills/brainstorm/SKILL.md
skills/changelog/SKILL.md
skills/dev-commit/SKILL.md
skills/dev-debug/SKILL.md
skills/dev-design/SKILL.md
skills/dev-implementation/SKILL.md
skills/dev-lifecycle/SKILL.md
skills/dev-planning/SKILL.md
skills/dev-pr/SKILL.md
skills/dev-refactor/SKILL.md
skills/dev-requirements/SKILL.md
skills/dev-retro/SKILL.md
skills/dev-review/SKILL.md
skills/dev-simplify/SKILL.md
skills/dev-smoke/SKILL.md
skills/dev-testing/SKILL.md
skills/dev-worktree/SKILL.md
skills/document-code/SKILL.md
skills/memory/SKILL.md
skills/refactor/SKILL.md
skills/remote-from-slack/SKILL.md
skills/remote-from-telegram/SKILL.md
skills/security-review/SKILL.md
skills/session-compact/SKILL.md
skills/simplify-implementation/SKILL.md
skills/structured-debug/SKILL.md
skills/task/SKILL.md
skills/tdd/SKILL.md
skills/technical-writer/SKILL.md
skills/verify/SKILL.md

Metadata

Files
0
Version
d2e170a
Hash
76ba7c8a
Indexed
2026-07-31 07:50

trang chủ - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-11-02 21:21
浙ICP备14020137号-1