# taskswarm

> taskswarm — wersky-taskswarm. Use this tool when you need to manage complex tasks across multiple agents, requiring hierarchical decomposition, parallel execution, and progress tracking. Taskswarm solves problems of task dependencies, parallelization, and auditing, providing a shared dashboard for progress updates and PPR review gates. It takes in task definitions and dependencies as input, outputting a coordinated workflow with automated auditing and feedback loops.

Canonical page: https://skillsregistry.net/skills/wersky-taskswarm  
JSON: https://api.skillsregistry.net/v1/skills/wersky-taskswarm

## Description

多 Agent 编排插件：任务树多级拆解 + 按依赖波次并行派发子代理 + 共享 MCP 看板进度互通。带 PPR 审核门（未过审不放行下游）与提案采纳回路。零依赖 Node，123 tests passing / 行覆盖 90.3%。   DSH, Codex, Zcode

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Wersky/taskswarm)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "wersky-taskswarm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/wersky-taskswarm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/wersky-taskswarm/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt