← Back to Skills Marketplace
wavmson

Swarm Coord

by wavmson · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
127
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install swarm-coord
Description
多 Agent 协作调度。将大任务拆分为子任务,分配给多个 Agent 并行执行,自动汇总结果。Team Lead 负责拆分、分发、监控、汇总。触发词:协作、swarm、分工、团队任务、并行执行、多 Agent、team work。
Usage Guidance
This skill appears to do what it says: it decomposes a job, spawns sub‑agent sessions, monitors them, and aggregates results. Before installing or running it: 1) Confirm where '.task-state.json' will be written and how long it is retained; sensitive data should not be stored there. 2) Review what “上下文(文件路径、配置值等)” you allow the CEO to forward—avoid sending secrets or whole config files unless necessary. 3) Ensure child agents have only the minimal credentials/permissions needed (e.g., Git or messaging tokens) and are trusted to perform external actions. 4) If you use Memory‑Dream or other memory skills, decide whether you want swarm outputs persisted to long‑term memory. 5) Test the skill in a low‑privilege environment first (no access to production repos/secrets) to observe how it passes context and handles failures. If you need, request the author/sources for the optional install repo to verify there are no hidden scripts in the packaged version.
Capability Analysis
Type: OpenClaw Skill Name: swarm-coord Version: 1.0.0 The swarm-coord skill is a legitimate orchestration tool designed to decompose complex tasks into parallel sub-tasks using OpenClaw's session management capabilities (sessions_spawn, sessions_yield). The instructions in SKILL.md and README.md are clearly aligned with the stated purpose of multi-agent coordination and do not contain any evidence of malicious intent, data exfiltration, or unauthorized execution.
Capability Assessment
Purpose & Capability
Name and description match the actual instructions: the skill decomposes tasks, spawns sessions, monitors progress, and aggregates results. It does not request unrelated credentials, binaries, or installs, and the README's install suggestions (clawhub/git clone) are consistent with an instruction-only skill.
Instruction Scope
Runtime instructions only use platform primitives (sessions_spawn, sessions_yield, etc.) and describe clear phases. However the guidance explicitly says to pass '上下文(文件路径、配置值等)' to child agents and to relay intermediate results; that can expose local files or configuration values to subordinate agents if they are fetched or attached. The skill also references external actions in examples (push to GitHub, send to Feishu) without declaring credentials — these are plausible examples but mean child agents will need access to service credentials elsewhere.
Install Mechanism
Instruction-only skill with no install spec and no code files. README mentions optional git clone or clawhub install, which are standard and not enforced by the skill itself. No remote downloads or extracted archives are specified.
Credentials
The skill declares no required env vars or credentials, which aligns with being an orchestration instruction set. But because it may instruct child agents to perform actions like Git pushes or messaging, those downstream operations will require credentials; ensure those credentials are supplied only to agents that actually need them. The instructions' mention of passing 'configuration values' is broad and could lead to unintended exposure of secrets.
Persistence & Privilege
always:false (no forced global presence). The skill recommends saving swarm progress to a local '.task-state.json' and recording results to Memory-Dream (long‑term memory). Persisting task state and writing to memory is functionalityally reasonable for long tasks, but review where .task-state.json is stored, retention policies, and what is written to Memory-Dream to avoid unwanted leakage of sensitive data.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install swarm-coord
  3. After installation, invoke the skill by name or use /swarm-coord
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: 4-phase multi-agent collaboration.
Metadata
Slug swarm-coord
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Swarm Coord?

多 Agent 协作调度。将大任务拆分为子任务,分配给多个 Agent 并行执行,自动汇总结果。Team Lead 负责拆分、分发、监控、汇总。触发词:协作、swarm、分工、团队任务、并行执行、多 Agent、team work。 It is an AI Agent Skill for Claude Code / OpenClaw, with 127 downloads so far.

How do I install Swarm Coord?

Run "/install swarm-coord" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Swarm Coord free?

Yes, Swarm Coord is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Swarm Coord support?

Swarm Coord is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Swarm Coord?

It is built and maintained by wavmson (@wavmson); the current version is v1.0.0.

💬 Comments