Cao Learning

Cao Learning 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 Learning

Copy Cao Learning 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-learning ~/.claude/skills/cao-learning

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

What Cao Learning does

Cao Learning reports task outcomes and stores durable lessons so future CAO sessions can reuse them. Use it when supervising or working in a CAO workflow that supports outcome logging and memory.

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

Documentation

README

Excerpt

CAO Self-Learning

CAO workflows can improve as they repeat: outcomes you report feed a retrospector agent that distills durable lessons into memory, and those lessons reach future sessions automatically. Your job depends on your role.

All of this is opt-in infrastructure. If report_outcome or a memory tool returns disabled: true, skip it silently and continue your task — learning is off for this run (often deliberately, e.g. a control run) and that is expected, not an error.

If you are a SUPERVISOR

Report an outcome after each meaningful unit of work

One report_outcome call per completed step, delegated task, or work item — after validation/review, not before:

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

Frequently asked about Cao Learning

What else does awslabs publish alongside Cao Learning?
Cao Learning 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 Learning 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 Learning compare to other AI Engineering skills?
Cao Learning ranks #1264 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 Learning against them. Open each page to compare what they document and how they install.