orchestration — Claude Code skill: what it does, how to install
Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents.
npx skills add stablyai/orca --skill orchestration -a claude-codeWhat orchestration does
The skill configures coordination for supervised Orca workers. It handles task dispatch and blocking ask/reply sequences. Workers communicate progress through worker_done signals or escalation waits. If you only need full task handoffs without monitoring or waiting for DAG output, the project suggests using orca-cli instead.
This file acts as a discovery stub. The full guide comes directly from the installed binary via ORCA skills get orchestration, which prevents documentation drift. Binary resolution inspects environment variables like ORCA_CLI_COMMAND and ORCA_DEV_REPO_ROOT. On Linux outside Orca terminals, it targets orca-ide so it never invokes the GNOME screen reader at /usr/bin/orca.
Coordination relies on a live Orca runtime. If the daemon is down, start it using ORCA open --json. A runtime_access_denied error indicates sandbox restrictions, which requires elevated execution rights rather than restarting the daemon. Install this skill when your workflow requires supervising multi-agent DAG execution.
What it helps with
- dispatch tasks across supervised agents using a DAG
- handle blocking ask/reply loops between coordinator and workers
- wait for worker_done signals or escalations
- control decision gates during multi-agent task execution
Example prompts for the agent
- Coordinate supervised Orca workers to process this task DAG
- Decompose this feature across workers and wait for worker_done
- Check for escalation messages from running Orca subagents
How to install orchestration
1Skills CLI (Vercel)
npx skills add stablyai/orca --skill orchestration -a claude-code2Manually: put the files in place
~/.claude/skills/orchestration/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/orchestration/
1Skills CLI (Vercel)
npx skills add stablyai/orca --skill orchestration -a codex2Manually: put the files in place
.agents/skills/orchestration/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add stablyai/orca --skill orchestration -a cursor2Manually: put the files in place
.cursor/skills/orchestration/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install stablyai/orca orchestration2Manually: put the files in place
.github/skills/orchestration/SKILL.md1Skills CLI (Vercel)
npx skills add stablyai/orca --skill orchestration -a gemini-cli2Platform CLI
gemini skills install https://github.com/stablyai/orca --path skills/orchestrationManually: put the files in place
.devin/skills/orchestration/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add stablyai/orca --skill orchestration -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set8
The whole set →Similar
Questions about orchestration
How to install orchestration in Claude Code?
Run npx skills add stablyai/orca --skill orchestration -a claude-code. You can also place the specification directly into ~/.claude/skills/orchestration/SKILL.md.
What does the orchestration skill do?
It manages structured multi-agent coordination inside the Orca runtime. The coordinator supervises worker messages, tracks task DAGs, and evaluates decision gates.
Why does the skill resolve to orca-ide on Linux?
Standard Linux installations associate orca with the GNOME Orca screen reader /usr/bin/orca. Using orca-ide prevents the system from triggering speech synthesis.
Source text
SKILL.md · MIT
---
name: orchestration
description: >-
Coordinate supervised Orca workers: threaded messages, blocking ask/reply,
task dispatch, worker_done/escalation waits, task DAGs, decision gates,
coordinator loops, and decomposing work across agents. Use `orca-cli` for full
ownership handoffs — "hand off", "handoff", "handover", "give this to another
agent", "another worktree" — unless asked to supervise, monitor, or coordinate
a DAG, and for terminal control, lightweight terminal prompts, shell commands,
Orca worktree management, and reading or waiting on terminals.
---
# Orca Orchestration
This file is a discovery stub, not the usage guide. The full, version-matched Orca
orchestration reference is served by the `orca` binary itself — kept out of this file on
purpose so it can never drift from the binary that will actually run your commands.
Engage Orca orchestration whenever you need structured multi-agent coordination: threaded
messages, blocking ask/reply flows, task dispatch, worker_done/escalation waits, task DAGs,
decision gates, coordinator loops, or decomposing work across agents. Use the orca-cli skill
instead for full ownership handoffs ("hand off", "handoff", "handover", "give this to
another agent", "another worktree") when the user did not ask to supervise, monitor, wait
for results, or coordinate a DAG — and for ordinary terminal control, shell commands,
worktree management, and the built-in browser. Coordination requires real Orca runtime
state; never substitute a non-Orca subagent tool.
## Resolve the CLI for this session
Choose the executable once and reuse it for every later command:
- If the `ORCA_CLI_COMMAND` environment 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`, use `orca-dev`.
- Otherwise, on Linux outside an Orca-managed terminal, use `orca-ide`. Never run bare
`orca` there — 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
```text
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. 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.
Prefer `--json`. 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.
© stablyai · MIT · stablyai/orca