orca-cli — Claude skill: drive Orca worktrees and terminals
The skill lets an agent manage Orca worktrees, terminals, artifacts and the built-in browser through the orca CLI. Useful when your work already runs inside Orca.
npx skills add stablyai/orca --skill orca-cli -a claude-codeWhat orca-cli does
The skill covers the Orca objects an agent can touch through the orca executable: worktrees and child worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, skill sharing and the embedded browser. It also handles handing a task over to another agent.
Setup is a resolution step. If ORCA_CLI_COMMAND is set, that value wins. In a dev checkout that exposes ORCA_DEV_REPO_ROOT, the skill uses orca-dev. On Linux outside an Orca-managed terminal it picks orca-ide, because bare orca there usually resolves to the GNOME screen reader and starts speech. After that the skill loads the version-matched guide with ORCA skills get orca-cli. If a command says Orca is not running, start it with ORCA open --json and retry.
Watch the failure modes. A runtime_access_denied error means your sandbox blocked the connection: re-run with escalated permissions and leave ORCA open and Orca itself alone. If skills get is unknown, updating Orca brings the guide back. Install this if you already work in Orca and want the agent to drive its state instead of raw git worktree or ad hoc PTYs. If Orca is not part of your setup, skip it.
What it helps with
- spawn a child worktree and run codex or claude inside it
- read Orca terminal output and send a command back
- hand a task over to another agent
- publish artifacts and share skills across sessions
- open Orca's embedded browser to check a page
Example prompts for the agent
- $orca-cli, create a child worktree and spawn claude there
- read the Orca terminal and wait for the build to finish
- handoff this task to another agent
How to install orca-cli
1Skills CLI (Vercel)
npx skills add stablyai/orca --skill orca-cli -a claude-code2Manually: put the files in place
~/.claude/skills/orca-cli/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/orca-cli/
1Skills CLI (Vercel)
npx skills add stablyai/orca --skill orca-cli -a codex2Manually: put the files in place
.agents/skills/orca-cli/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add stablyai/orca --skill orca-cli -a cursor2Manually: put the files in place
.cursor/skills/orca-cli/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install stablyai/orca orca-cli2Manually: put the files in place
.github/skills/orca-cli/SKILL.md1Skills CLI (Vercel)
npx skills add stablyai/orca --skill orca-cli -a gemini-cli2Platform CLI
gemini skills install https://github.com/stablyai/orca --path skills/orca-cliManually: put the files in place
.devin/skills/orca-cli/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add stablyai/orca --skill orca-cli -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set8
The whole set →Similar
Questions about orca-cli
How do I install orca-cli in Claude?
Run npx skills add stablyai/orca --skill orca-cli -a claude-code. The skill lands at ~/.claude/skills/orca-cli/SKILL.md.
What does orca-cli do?
It teaches the agent to operate Orca worktrees, terminals, repos, artifacts and the browser through the CLI, and to pass tasks between agents.
Why can't I run plain `orca` on Linux?
Outside Orca's terminals that command usually points at the GNOME screen reader and starts speech on the user's machine. Use orca-ide instead.
Source text
SKILL.md · MIT
--- name: orca-cli description: >- Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do. --- # Orca CLI This discovery stub loads the version-matched guide from the Orca executable used for this session. ## 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 orca-cli ``` 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