Official agent skill

Cao Learning

by awslabs in awslabs/cli-agent-orchestrator

Report task outcomes and distill lessons so the team improves across runs — reportoutcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons.

OfficialApache-2.0Auto-check passedAgent Workflows

Install Cao Learning

skills CLI

$ npx skills add awslabs/cli-agent-orchestrator --skill cao-learning -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install awslabs/cli-agent-orchestrator cao-learning --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/awslabs/cli-agent-orchestrator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cao-learning .claude/skills/cao-learning && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "cao-learning" agent skill from https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-learning into .claude/skills/cao-learning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cao-learning", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-learning

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add awslabs/cli-agent-orchestrator --skill cao-learning -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install awslabs/cli-agent-orchestrator cao-learning --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/awslabs/cli-agent-orchestrator.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cao-learning .agents/skills/cao-learning && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "cao-learning" agent skill from https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-learning into .agents/skills/cao-learning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cao-learning", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add awslabs/cli-agent-orchestrator --skill cao-learning -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install awslabs/cli-agent-orchestrator cao-learning --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/awslabs/cli-agent-orchestrator.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cao-learning .cursor/skills/cao-learning && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "cao-learning" agent skill from https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-learning into .cursor/skills/cao-learning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cao-learning", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/awslabs/cli-agent-orchestrator.git --path skills/cao-learning

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add awslabs/cli-agent-orchestrator --skill cao-learning -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install awslabs/cli-agent-orchestrator cao-learning --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/awslabs/cli-agent-orchestrator.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cao-learning .gemini/skills/cao-learning && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "cao-learning" agent skill from https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-learning into .gemini/skills/cao-learning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cao-learning", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install awslabs/cli-agent-orchestrator cao-learning

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add awslabs/cli-agent-orchestrator --skill cao-learning -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/awslabs/cli-agent-orchestrator.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cao-learning .github/skills/cao-learning && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "cao-learning" agent skill from https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-learning into .github/skills/cao-learning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cao-learning", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add awslabs/cli-agent-orchestrator --skill cao-learning -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install awslabs/cli-agent-orchestrator cao-learning --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/awslabs/cli-agent-orchestrator.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cao-learning .opencode/skills/cao-learning && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "cao-learning" agent skill from https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-learning into .opencode/skills/cao-learning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cao-learning", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: cao-learning
GitHub stars: 1.4k
Token cost: ~1.3k tokens
SKILL.md length: 558 words
Files: 1
Skills in repo: 14
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Report task outcomes and distill lessons so the team improves across runs — reportoutcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons.

Works in 3 steps: Apply injected lessons first. Before… → Store new lessons immediately when you… → Correct, don't accumulate. If a stored…
Agent Workflows work in your project
SKILL.md covers If you are a SUPERVISOR, If you are a WORKER, If you are the RETROSPECTOR and What happens to lessons…
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Cao Learning is an agent skill from awslabs/cli-agent-orchestrator, published by the product's own GitHub organization. Report task outcomes and distill lessons so the team improves across runs — reportoutcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons. Use in workflows that run repeatedly over similar work items. Requires memory.learningenabled; degrade silently when the tools report disabled.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. It works with Model Context Protocol. The repository describes itself as: Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions. The licence is Apache-2.0.

When your agent uses it

Agent Workflows work in your project

Example prompts

“/cao-learning”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

Apply injected lessons first. Before working, scan your
Store new lessons immediately when you discover something durable — a
Correct, don't accumulate. If a stored lesson proves wrong, re-store

What it can do on your machine

Read from SKILL.md and the folder at commit b29f40a. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cao Learning loads about 1.3k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 558 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~87
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from awslabs/cli-agent-orchestrator at commit b29f40a, republished under its Apache-2.0 licence (© awslabs). 558 words, ~1,273 tokens.

Download SKILL.mdSave it as .claude/skills/cao-learning/SKILL.md (or your agent's skills folder).

name: cao-learning
description: Report task outcomes and distill lessons so the team improves across runs — report_outcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons. Use in workflows that run repeatedly over similar work items. Requires memory.learning_enabled; degrade silently when the tools report disabled.

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.

A bare error with no disabled key is different: say so, don't skip it. That shape means the tool could not reach a verdict — cao-server is unreachable, or its settings.json could not be read — so learning may well be ON while nothing is being recorded. Mention it in your response and carry on with the task.

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:

report_outcome(
    task_label="convert package CustomerETL (iteration 2)",
    success=false,
    workflow_name="ssis-migration",
    agent_profile="transformer",           # who did the work (defaults to you)
    score=40,                              # optional 0-100 metric if you have one
    friction_notes="Lookup with partial cache emitted an invalid join; "
                   "improver patched the cache-mode mapping."
)

Rules for friction_notes:

1–3 sentences, conclusions only — the root cause, not the story.
NEVER paste transcripts, logs, stack traces, file contents, or secrets.
Empty string on a clean pass is fine; the success flag already carries signal.

Report failures faithfully — failed iterations are the most valuable learning signal. Do not skip reporting because a step went badly.

Dispatch the retrospector at natural boundaries

After each completed work item (a package, a feature, a review cycle) — not after every step — hand off to the retrospector agent:

"Retrospect on session <session_name>, workflow <workflow_name>,
 item <item name>. Agents involved: <profiles>."

Wait for its one-line summary (outcomes read, lessons stored) and record it in your run log. If no retrospector profile is available, skip this step.

Pass lessons downstream

Your injected <cao-memory> block may contain lessons from previous runs. When a lesson's Applies when: clause matches the task you are delegating, include it in your handoff message — workers also receive their own agent-scope lessons, but your routing helps.

Show full SKILL.md (273 more words)Show less

If you are a WORKER

Apply injected lessons first. Before working, scan your <cao-memory> block and any ## Learned Patterns section of your own instructions for lessons whose Applies when: clause matches the current task. Apply them before falling back to first principles.

Store new lessons immediately when you discover something durable — a mapping that works, a trap that recurs, a tooling quirk:

memory_store(
    content="Preserve a Lookup transform's cache mode instead of defaulting "
            "to a full-table read. Applies when: translating a Lookup whose "
            "CacheType is not full cache.",
    scope="agent",
    memory_type="feedback",
    key="honor-lookup-cache-mode"
)

Format contract: 1–2 sentence conclusion, then Applies when: <trigger>. The trigger clause is how future curators match your lesson to a task.

Correct, don't accumulate. If a stored lesson proves wrong, re-store the corrected text under the SAME key (or memory_forget it). Never store a contradicting lesson under a new key.

If you are the RETROSPECTOR

Follow your profile (retrospector.md). Read outcomes with the list_outcomes tool; store worker-craft lessons with store_lesson(target_agent_profile=..., content=...) — NOT memory_store, which files agent-scope lessons under YOUR profile, where the worker will never see them. The quality bar, in brief: 0–3 lessons per retrospection, each supported by a concrete outcome, actionable, general enough to recur, under 400 characters, ending with Applies when:. "No lessons" is a valid and often correct answer.

What happens to lessons afterwards

Lessons are ordinary agent-scope memories: injected into future sessions, recalled on demand (each recall reinforces them), lint-checked for contradictions, audited.
An operator may promote reinforced lessons into your profile's ## Learned Patterns block with cao memory promote — that block is CAO-maintained; treat its contents as instructions, and don't edit it by hand.

Files

Just SKILL.md in skills/cao-learning of awslabs/cli-agent-orchestrator.

Open the folder on GitHubat commit b29f40a

Compare with similar skills

Cao Learning next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cao Learning compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Cao Learning this skillawslabs/cli-agent-orchestrator	1.4k	—	~1.3k	Automated safety check: Pass	Apache-2.0	today
MCP Server Builderanthropics/skills	180k	64 repos	~2.3k	Automated safety check: Pass	Apache-2.0	3 days ago
MCP Server BuildershareAI-lab/learn-claude-code	78k	5 repos	~1.2k	Automated safety check: Pass	MIT	10 days ago
MCP Integration for Pluginsanthropics/claude-plugins-official	38k	11 repos	~3.1k	Automated safety check: Pass	Apache-2.0	today
Fastmcp Client CLIPrefectHQ/fastmcp	28k	1 repos	~823	Automated safety check: Pass	Apache-2.0	today
MemPalace Memory SearchMemPalace/mempalace	59k	—	~1.4k	Automated safety check: Pass	MIT	today

Similar skills

MCP Server Builder
anthropics/skills
Official
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
180k GitHub starsUsed in 64 repos~2.3k tokens
Agent WorkflowsAuto-check passed
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
78k GitHub starsUsed in 5 repos~1.2k tokens
Agent WorkflowsAuto-check passed
MCP Integration for Plugins
anthropics/claude-plugins-official
Official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
38k GitHub starsUsed in 11 repos~3.1k tokens
Agent WorkflowsAuto-check passed
Fastmcp Client CLI
PrefectHQ/fastmcp
Query and invoke tools on MCP servers using fastmcp list and fastmcp call.
28k GitHub starsUsed in 1 repo~823 tokens
Agent WorkflowsAuto-check passed
MemPalace Memory Search
MemPalace/mempalace
Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.
59k GitHub stars~1.4k tokensUpdated today
Agent WorkflowsAuto-check passed
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
29k GitHub stars~3.7k tokensUpdated yesterday
Agent WorkflowsAuto-check passed

Questions about Cao Learning

What does Cao Learning do?

Report task outcomes and distill lessons so the team improves across runs — reportoutcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons. Cao Learning is an agent skill from awslabs/cli-agent-orchestrator, published by the product's own GitHub organization. Report task outcomes and distill lessons so the team improves across runs — reportoutcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons.

When should I use Cao Learning?

Cao Learning fits situations like: agent Workflows work in your project.

How do I install Cao Learning in Claude Code?

Run `npx skills add awslabs/cli-agent-orchestrator --skill cao-learning -a claude-code`. Or copy the skill folder (skills/cao-learning in awslabs/cli-agent-orchestrator) into .claude/skills/cao-learning in your project. Claude Code loads it when a task matches its description.

How do I install Cao Learning in Codex?

Run `npx skills add awslabs/cli-agent-orchestrator --skill cao-learning -a codex`. Or copy the skill folder (skills/cao-learning in awslabs/cli-agent-orchestrator) into .agents/skills/cao-learning in your project. Codex loads it when a task matches its description.

Can I use Cao Learning in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add awslabs/cli-agent-orchestrator --skill cao-learning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cao-learning, .gemini/skills/cao-learning, .github/skills/cao-learning and .opencode/skills/cao-learning in your project.

What does Cao Learning need to run?

SKILL.md names no scripts, command-line tools or credentials: Cao Learning is instructions for the agent only.

Does Cao Learning access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cao Learning safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cao Learning use?

Cao Learning is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cao Learning use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cao Learning?

Skills that share tags, products or a category with Cao Learning: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cao Learning?

awslabs (a GitHub organization, an official publisher) maintains it in awslabs/cli-agent-orchestrator, which has 1,396 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 8, 2026.

Source: awslabs/cli-agent-orchestrator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Cao Learning

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

CAO Self-Learning

If you are a SUPERVISOR

Report an outcome after each meaningful unit of work

Dispatch the retrospector at natural boundaries

Pass lessons downstream

If you are a WORKER

If you are the RETROSPECTOR

What happens to lessons afterwards

Files

Compare with similar skills

Similar skills

More from awslabs/cli-agent-orchestrator

Related

Questions about Cao Learning