Agent Orchestra

Use when three or more AI agents are available and a task needs coordinated execution, or when work must be handed to another agent, session or tool. It ships the coordination rules as ENFORCED invariants rather than advice: one writer per resource (a conflicting claim is refused and names the holder), a verifier that is never the implementer and whose PASS must carry criterion-linked evidence, a failed verification that blocks both done and dispatch to evidence, three failed rounds that block the task outright, an external action that cannot be dispatched until an approval covering it is reco

93 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add 3338902669-ops/agent-orchestra --skill agent-orchestra

Manual install

git clone --depth 1 https://github.com/3338902669-ops/agent-orchestra.git /tmp/agent-orchestra
mkdir -p ~/.claude/skills
cp -r /tmp/agent-orchestra/. ~/.claude/skills/agent-orchestra

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Agent Orchestra

> 中文对照（不随 skill 常驻加载）：`references/zh-contrast.md`

One protocol for two axes of multi-agent work:

- **In-task coordination** - who does what right now, who may write, who verifies, and what counts as done.
- **Cross-session handoff** - how the state survives when the work moves to another agent, another session or another tool.

Both axes share the same hard rules: one writer per resource, a verifier that is never the implementer, graded evidence, and a shared record that outranks any scheduler. It makes coordination failures visible and recoverable. It cannot promise infallibility, and it never replaces user authorization.

## Activation (when to use this skill)

Configure in `config/agents.example.yaml` under `activation:`.

| mode | behavior | token cost |
|---|---|---|
| global | engages for every task | highest (always loaded) |
| keyword | engages only when task text matches keywords | default; low |
| manual | engages only when the user explicitly invokes it | lowest |

1. Read the activation block from `config/agents.example.yaml`.
2. global -> engage. manual -> engage only when the user asked for multi-agent work or a handoff.
3. keyword -> run `node scripts/detect-trigger.mjs --text "<task text>"` and read the exit code:

| exit | label | meaning | what to do |
|---|---|---|---|
| **0** | ENGAGED | a curated, self-anchored keyword phrase matched **and** no comparison marker is present | use the skill |

Read the full skill on GitHub

Details

Skill name: agent-orchestra
Repository: 3338902669-ops/agent-orchestra
License: Apache-2.0
Repo updated: 23 October 2026

FAQ

What does the Agent Orchestra skill do?

How do I install the Agent Orchestra skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add 3338902669-ops/agent-orchestra --skill agent-orchestra. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Agent Orchestra popular?

It lives in 3338902669-ops/agent-orchestra, which has 93 GitHub stars and 0 forks.

Related skills

Ham

kromahlusenii-ops/ham

Set up Hierarchical Agent Memory (HAM) — scoped CLAUDE.md files per directory that reduce token spend. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM savings", "HAM stats", "HAM dashboard", "HAM sandwich", "HAM insights", "HAM carbon", or "ham sync".

AI, LLMs & Agents

Partner Skill

LearnPrompt/partner-skill

搭子.skill / Partner — two-direction cost-split workflow between Claude Code and Codex. Direction A (Codex-driven): Codex orchestrates and implements; Claude Code plans (/goal), polishes UI/interaction, and runs final /codex:review in one reused session. Direction B (Claude-driven): Claude plans and splits the work, runs the idea-king adversarial gate, delegates to Codex background jobs, monitors, and full-reviews before accepting. Use on "搭子" / "双向搭子" / "搭子，恢复" (resume from .partner/), "搭子，配置" (first-run setup wizard), "搭子，试跑" (identity tryout report), 分工给 codex / 让 codex 做 / codex 后台跑 / Claude

AI, LLMs & Agents

AI Bounty Claim

aelf-hzz780/AI-bounty-skill

Use when claiming the AI bounty on the tDVV mainnet sidechain. This public claim skill now supports Portkey AA/CA only, requires CA sync and holder preflight before any write, and routes to AA/CA onboarding, AA/CA claim, or diagnostics-only stop handling.

AI, LLMs & Agents

Promptmaster

Jakeschincariol/promptmaster-skill

Rewrite the user's raw request into an optimized prompt before answering it, audit it against the 35 credit-waste patterns in waste-patterns.json, and enforce every locked decision in decisions.md so nothing gets re-explained and nothing contradicts itself. Use whenever the user types /promptmaster, prefixes a request with it, or asks to optimize / tighten / fix a prompt.

AI, LLMs & Agents22

Clawteam Directors Orchestrator

momozi1996/DirectorAgents

ClawTeam导演智囊团——基于ClawTeam多智能体框架的世界著名导演协同创作系统。整合31位全球顶级导演的风格思想，通过多智能体协作机制（顺序链、辩论投票、主席团模式）辅助剧本创作、影像风格设计和叙事决策。触发词：「导演智囊团」「ClawTeam」「多导演协作」「剧本创作」「影像风格」适用场景：编剧、导演、创意策划、影视教育、AI影像创作

AI, LLMs & Agents

Mcdonalds

Lemon177777/mcd-omni-assistant

麦当劳中国官方 MCP 全能助手。当用户提到麦当劳、麦乐送、开心乐园餐、麦麦省优惠券、领券、点麦当劳、外送到家、得来速、麦当劳积分、积分抽奖、积分商城兑换、麦当劳餐品热量/营养、麦当劳订单查询或取消、麦当劳周边玩具与活动时使用。覆盖官方 35 个工具的全部能力，内置领券、到店点餐、外送、玩具雷达、积分抽奖、热量计算、优惠计算器七大工作流。

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.