Cao Workflow

Cao Workflow is an AI Engineering skill for Claude Code, published by awslabs in cli-agent-orchestrator.

1.1K stars226 forkson awslabs/cli-agent-orchestratorAdded 2026/08/21+1% in starsRepository updated 2026/08/21

agent-orchestrationai-agentsai-coding-assistantantigravityclaude-codecodexcopilot-clicursor-clideveloper-toolshermeskimi-clikiromcpmodel-context-protocolmulti-agent-systemsopencodeorchestrationpythontmux

Install in seconds

Install Cao Workflow

Copy Cao Workflow into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-workflow ~/.claude/skills/cao-workflow

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/awslabs/cli-agent-orchestrator.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/cao-workflow/SKILL.md in awslabs/cli-agent-orchestrator
Installs to: ~/.claude/skills/cao-workflow
Collection: One of 18 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Cao Workflow does

Cao Workflow author and run CAO Python workflow scripts for multi-step, parameterized agent jobs with fan-out and resume support. Use it when a task needs validation and coordinated steps instead of a single agent call.

Cao Workflow is cataloged under AI Engineering on DirSkills. Cao Workflow comes from a repository tagged agent-orchestration, ai-agents, ai-coding-assistant, antigravity and claude-code.

Documentation

README

Excerpt

CAO Workflows

A CAO workflow is a Python script you write, validate, and — only after asking the user — run through cao workflow run. Each script drives one or more agent steps through CAO's shared substrate, so you can fan work out across agents, collect their results, and resume a run that was interrupted.

Your job as an author ends at a validated script file on disk. Authoring does NOT run the workflow. Never claim a workflow ran, or will run, when all you did was write it. Running is a separate step the user must approve (see Lifecycle step c).

When to use

Reach for this skill when the user asks to build or run a multi-step or parameterized workflow — for example:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Cao Workflow

What else does awslabs publish alongside Cao Workflow?
Cao Workflow is one of 18 skills that DirSkills catalogs from awslabs/cli-agent-orchestrator, the repository it ships in. Its siblings there include AG-UI Author, AI-DLC Portfolio and Add UI To MCP Server. Each one is a separate skill with its own page in this directory, installs the same way Cao Workflow does, and is maintained by awslabs in that same repository. The rest of the collection is listed on the awslabs/cli-agent-orchestrator page.
How does Cao Workflow compare to other AI Engineering skills?
Cao Workflow ranks #1272 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Cao Workflow against them. Open each page to compare what they document and how they install.