orchestration
🎯SkillLets your AI agent hand work to other agents running in Orca, a tool for running several coding agents, and get the results back. For example, Claude can ask Codex to review its work and report back.
Installation
npx skills add stablyai/orca --skill orchestrationRun it in a terminal; it asks which AI coding tools to install it for (Claude Code, Codex, Cursor and more).
Uses skills.sh · Node.js 22.20+
After installing
Ask for related work and the agent uses it on its own, or call it yourself.
/orchestrationInstall by hand
Copy the whole skill folder from GitHub to the place below. Copying only SKILL.md can leave out files the skill uses.
Open the skill folder →- This project
.claude/skills/orchestration/ - All projects
~/.claude/skills/orchestration/
These paths are for Claude Code. For other tools, the command above puts it in the right place.
What this skill does
Overview
Orca can run several coding agents, each in its own workspace. This skill tells the agent when to use an Orca worker (an agent running in Orca) instead of its own subagents (helper agents it starts itself), for example when you want a different agent such as Codex or a separate Orca workspace. It is a short starter: it picks the right Orca program and then loads the full guide for your installed version with ORCA skills get orchestration.
Key Features
- Ask another agent, such as Codex, to review your work and report back.
- Pick the right program for your setup: the
ORCA_CLI_COMMANDsetting,orca-dev,orca-ide, ororca. - Avoid starting the GNOME Orca screen reader by mistake, since bare
orcacan run it on Linux outside Orca's terminals. - Load only the extra reference you need with
--reference, or the full guide with--full. - Recover from common errors, such as starting Orca with
ORCA open --jsonwhen it is not running.
Who is this for?
It is for Orca users who want agents like Claude and Codex to work together and share results. It also helps when your agent is itself a worker that received a task from Orca.
Summarized by AI from this skill's SKILL.md. Suggest a better one
SKILL.md
View on GitHub →Run work in separate Orca worker agents and get their results back. Use when the user asks for Orca workers or supervision (monitor, task DAGs, ask/reply, decision gates), or when the work needs something your own subagents cannot give: a different agent (such as Codex from Claude) or its own Orca workspace. "Have Codex (or Claude) review this and report back" means an Orca worker of that agent, even when you have your own model subagents. Also use when you are a dispatched worker (a prompt with Task and Dispatch IDs: ask, worker_done). Otherwise prefer your own subagents, including for long or parallel work. Use `orca-cli` to hand work off with nothing expected back ("hand off", "handover", "give this to another agent", "another worktree"), and for terminal control, shell commands, worktree management, and reading or waiting on terminals.
Orca Orchestration
This discovery stub loads the version-matched guide from the Orca executable used for this session.
Never substitute a non-Orca subagent tool when the user asked for Orca orchestration.
Resolve the CLI for this session
Choose the executable once and reuse it for every later command:
- If the
ORCA_CLI_COMMANDenvironment variable is set, use its value. Orca exports this for managed WSL sessions. - Otherwise, in a dev checkout whose session exposes
ORCA_DEV_REPO_ROOT, useorca-dev. - Otherwise, on Linux outside an Orca-managed terminal, use
orca-ide. Never run bareorcathere — outside Orca's terminals it normally resolves to the GNOME Orca screen reader (/usr/bin/orca) and starts speech on the user's machine. - Otherwise, use
orca.
Below, ORCA is a placeholder for the executable you resolved. Substitute it before
running anything; do not create a shell variable or run ORCA literally. This works the
same way in POSIX shells, PowerShell, and cmd.exe.
If the selected executable cannot run, report its exact error and stop. Do not fall through to another executable, which could silently target a different Orca build.
Load the version-matched guide before running Orca commands
ORCA skills get orchestration
That prints the compact, version-matched guide for the exact binary that will handle your
next commands. It covers the normal local coordinator loop and dispatched-worker
obligations. For a conditional action gate such as remote placement, uncertain release
recovery, or expanded DAG work, load only the reference that gate names with
ORCA skills get orchestration --reference references/<file>.md
(--references lists the names). If that binary rejects --reference, run
ORCA skills get orchestration --full and read the named bundled reference before acting.
Use the selected executable's --help for commands or flags the guide does not cover. If a
command reports that Orca is not running, start it with ORCA open --json and retry. If it
fails with runtime_access_denied, your sandbox blocked the connection: re-run it with
escalated permissions, and do not run ORCA open or restart Orca. If skills get is unknown,
explain that updating Orca restores the guide; use --help for read-only discovery and do not
guess unsupported commands.