# taskflow

> taskflow — heggria-taskflow. Use this tool when you need to manage complex workflows across multiple AI agents, such as Pi, Codex, and Claude Code, to compile, verify, and run multi-agent directed acyclic graphs (DAGs). It solves problems like workflow management, error handling, and recomputation, providing features like resume, replay, and incremental recomputation. Ideal for use cases involving multi-agent collaboration, version control with git, and large-scale task automation.

Canonical page: https://skillsregistry.net/skills/heggria-taskflow  
JSON: https://api.skillsregistry.net/v1/skills/heggria-taskflow

## Description

Compile, verify, and run multi-agent DAGs across Pi, Codex, Claude Code, OpenCode, and Grok—with resume, replay, and incremental recomputation.

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **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/heggria/taskflow)

## 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": "heggria-taskflow"
    }
  }
}
```

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