LogoClawIndex
CasesSkillsAbout
LogoClawIndex

pi-graph - Build and run Pi agent graphs

Build, validate, run, resume, and visualize explicit-state multi-agent workflows with structured handoffs, routing, parallel branches, checkpoints, and approval gates.

Tags

Updated: 2026-10-07

Capabilities

Typical Inputs

Typical Outputs

What this skill does

  • Build agent graphs
  • Define structured handoffs
  • Route conditionally
  • Run parallel branches
  • Persist durable checkpoints
  • Resume graph execution
  • Validate graph schemas
  • Visualize graph workflows
  • Handle approval gates

Inputs

  • Graph JSON definition
  • Task input data
  • Node prompts
  • Model and tool settings
  • Approval decisions

Outputs

  • Graph execution results
  • Durable checkpoint files
  • Stored artifacts
  • Validation errors
  • Routing and execution status
  • Graph visualizations

Requirements

  • Pi agent runtime
  • Installed pi-graph extension
  • Discovered graph JSON files
  • Model access for agent nodes
  • Filesystem access for graphs and checkpoints

Source

  • Spec: SKILL.md

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Skills·
Cases

Meta

About·
Disclaimer·
Email·
GitHub
© 2026 ClawIndex All Rights Reserved.
multi-agent
workflow orchestration
state graph
conditional routing
parallel execution
structured output
human-in-the-loop
durable checkpoints
Build agent graphs
Define structured handoffs
Route conditionally
Run parallel branches
Graph JSON definition
Task input data
Node prompts
Graph execution results
Durable checkpoint files
Stored artifacts