OpenClaw

multi-agent-protocol

Production protocol for multi-agent collaboration in OpenClaw. Combines Spec-First task definition, two-stage review (Spec + Quality), beads dependency graph as task bus, blackboard.json for direct inter-agent communication, Circuit Breaker retry strategy, and git worktree isolation for parallel implementation. Use when orchestrating 2+ sub-agents on complex tasks requiring coordination, quality gates, and fault tolerance.

hakityc0 来源安装数☆ 0 仓库 Starsv1.0.0

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install hakityc/multi-agent-protocol

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

Multi-Agent Collaboration Protocol

Production playbook for orchestrating multiple sub-agents in OpenClaw with structured task flow, quality gates, inter-agent communication, and automatic fault recovery.

Synthesized from community research: subagent-driven-development, beads, swarm-self-heal, agent-team-orchestration, and http-retry-circuit-breaker patterns.

When to Use

Use this skill when:

Spawning 2+ sub-agents on a complex task
Tasks have dependencies between agents
Quality matters (not just "done", but "correct and well-built")
You need fault tolerance without manual intervention
Multiple agents need to share state without going through the orchestrator

Don't use for:

Single-agent tasks (unnecessary overhead)
One-off spawns with no handoff
Simple question delegation

Core Principles

Spec-First — No spawning without a spec file. No spec = no work starts.
Two-Stage Review — Every implementation goes through Spec Review, then Quality Review.
Serial Implementation — Only one Implementer runs at a time. Parallel = research/analysis only.
Blackboard Communication — Agents read/write a shared file directly. Orchestrator is not a relay.
Circuit Breaker — Failures have a ceiling. After threshold → alert human, don't loop forever.
Fixed sessionKeys — Same role = same sessionKey = agent memory persists across spawns.

Directory Layout

{project-root}/
  .beads/              ← beads task graph (git-tracked, auto-managed)
  specs/
    {task-id}.md       ← Task spec (MUST exist before spawning Implementer)
  shared/
    blackboard.json    ← Live state bus (any agent reads/writes directly)
    artifacts/
      {role}/          ← Each agent's output artifacts

Task Lifecycle

Write Spec → bd create → bd ready → Claim → Implement → Self-Review
  → Spec Review → Quality Review → bd close → bd sync

Step 1 — Write the Spec

Before spawning anythin...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/hakityc/multi-agent-protocol
Version: 1.0.0
Commit: b32010580dc9d8c6749203373de3cf96b5a5e8cc
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# Multi-Agent Collaboration Protocol

Production playbook for orchestrating multiple sub-agents in OpenClaw with structured task
flow, quality gates, inter-agent communication, and automatic fault recovery.

Synthesized from community research: `subagent-driven-development`, `beads`, `swarm-self-heal`,
`agent-team-orchestration`, and `http-retry-circuit-breaker` patterns.

---

## When to Use

Use this skill when:
- Spawning 2+ sub-agents on a complex task
- Tasks have dependencies between agents
- Quality matters (not just "done", but "correct and well-built")
- You need fault tolerance without manual intervention
- Multiple agents need to share state without going through the orchestrator

**Don't use for:**
- Single-agent tasks (unnecessary overhead)
- One-off spawns with no handoff
- Simple question delegation

---

## Core Principles

1. **Spec-First** — No spawning without a spec file. No spec = no work starts.
2. **Two-Stage Review** — Every implementation goes through Spec Review, then Quality Review.
3. **Serial Implementation** — Only one Implementer runs at a time. Parallel = research/analysis only.
4. **Blackboard Communication** — Agents read/write a shared file directly. Orchestrator is not a relay.
5. **Circuit Breaker** — Failures have a ceiling. After threshold → alert human, don't loop forever.
6. **Fixed sessionKeys** — Same role = same sessionKey = agent memory persists across spawns.

---

## Directory Layout

```
{project-root}/
  .beads/              ← beads task graph (git-tracked, auto-managed)
  specs/
    {task-id}.md       ← Task spec (MUST exist before spawning Implementer)
  shared/
    blackboard.json    ← Live state bus (any agent reads/writes directly)
    artifacts/
      {role}/          ← Each agent's output artifacts
```

---

## Task Lifecycle

```
Write Spec → bd create → bd ready → Claim → Implement → Self-Review
  → Spec Review → Quality Review → bd close → bd sync
```

---

## Step 1 — Write the Spec

Before spawning anythin...

搜索