New to Claude Skills? Learn how to install them →

stablyai on GitHub

Orca Orchestration

Free

Streamline multi-agent coordination with structured workflows.

by stablyai41.8k stars on stablyai/orca
21 views
Updated Aug 10, 2026
Get this skill

Free · Opens the source repo

What Orca Orchestration does

Orca Orchestration is designed for developers and teams needing to manage complex interactions between multiple agents in a structured manner. It facilitates various coordination tasks such as threaded messaging, blocking ask/reply flows, and task dispatching. This skill is particularly useful for those who require precise control over workflows, enabling users to decompose tasks across agents and implement decision gates and coordinator loops effectively.

The skill leverages the orca-cli for handling ownership transfers, allowing users to phrase requests in natural language for seamless agent handoffs. This means that when a user wants to delegate tasks without explicitly asking for supervision, the system can intelligently manage these transitions. The orchestration capabilities are further enhanced by the ability to manage task Directed Acyclic Graphs (DAGs), which is essential for organizing complex workflows that depend on the completion of multiple tasks.

For those working within the Orca environment, this skill provides a structured approach to managing agent interactions, ensuring that tasks are executed in the correct order and that dependencies are respected. It is particularly beneficial in development environments where automation and coordination of tasks are critical for productivity. By utilizing the built-in browser and terminal management features, users can automate workflows effectively without needing to switch contexts frequently.

Orca Orchestration is ideal for teams that rely on multi-agent systems to achieve their goals, whether in software development, data processing, or any other domain where structured task management is necessary. It is important to note that coordination requires the real Orca runtime state; therefore, it is not suitable for use with non-Orca tools, ensuring that users are working within a compatible framework for optimal results.

When to use it

Use Orca Orchestration when you need to manage complex workflows involving multiple agents and require structured coordination.

When not to use it

This skill is not suitable for simple tasks or when working outside the Orca environment, as it relies on specific Orca runtime features.

What you can build with it

Task Delegation in Development

Use Orca Orchestration to delegate tasks among multiple agents in a software development project, ensuring efficient workflow management.

Complex Workflow Automation

Automate complex workflows that require multiple agents to interact and complete tasks in a structured manner.

Real-time Coordination

Implement real-time coordination of agents for tasks that require immediate responses and decision-making.

How to install Orca Orchestration

View source

1. Install with the skills CLI

npx skills add stablyai/orca/orchestration --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by stablyai

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 full guide before running Orca commands

ORCA skills get orchestration

That prints the complete, version-matched guide for the exact binary that will handle your next commands — task creation and dispatch, injected lifecycle preambles, worker_done authority, decision gates, and coordinator loops. Read it first, then run the specific command you need.

Don't guess subcommands or flags from memory or from a cached copy of this stub. They change between Orca releases, and this file deliberately no longer lists them. Confirm the app is up with ORCA status --json (start it with ORCA open --json if needed), and prefer --json for agent-driven calls.

If an older Orca does not recognize skills get

Use this fallback only when the selected binary explicitly reports that skills get is an unknown command. Another failure is not proof of an older binary; report it rather than guessing or changing executables. For a confirmed pre-guide binary, use only this bounded, read-only bootstrap to orient. Do not dead-end and do not invent commands:

ORCA status --json
ORCA orchestration task-list --json
ORCA terminal list --json

Then tell the user that updating Orca restores the full, version-matched guide via ORCA skills get orchestration. Beyond these commands, ask the user rather than guessing a command surface this older binary may not support.

Frequently asked questions about Orca Orchestration

Similar skills