orca-per-workspace-env — Claude Code skill: setup and usage
Configures, reviews, and debugs Orca per-workspace environment recipes. Useful when provisioning disposable VMs, containers, SSH hosts, or cloud sandboxes.
npx skills add stablyai/orca --skill orca-per-workspace-env -a claude-codeWhat orca-per-workspace-env does
This skill sets up and validates Orca per-workspace environment recipes. It handles disposable cloud sandboxes, VMs, SSH hosts, and local containers created fresh for each workspace. The skill edits the environmentRecipes entry in orca.yaml, scaffolds lifecycle scripts, and resolves orca vm recipe doctor errors. For ordinary worktrees without custom runtimes, use orca-cli instead.
The skill resolves the right CLI binary before running commands. Under managed WSL it uses ORCA_CLI_COMMAND. In development checkouts with ORCA_DEV_REPO_ROOT it chooses orca-dev. On Linux outside Orca terminals it selects orca-ide. This prevents triggering the GNOME screen reader at /usr/bin/orca. Guides load via ORCA skills get orca-per-workspace-env --json.
Use this when your workspaces require isolated runtimes. Skip it for standard local worktrees.
What it helps with
- Configure and validate an
environmentRecipesblock inorca.yaml - Troubleshoot failures reported by
orca vm recipe doctor - Scaffold provider lifecycle scripts for disposable VMs or containers
- Start an inactive Orca process using
ORCA open --json
Example prompts for the agent
- Help me write an environmentRecipes block in orca.yaml for a local container
- Fix the failures returned by orca vm recipe doctor
- Scaffold provider lifecycle scripts for an on-demand cloud sandbox
How to install orca-per-workspace-env
1Skills CLI (Vercel)
npx skills add stablyai/orca --skill orca-per-workspace-env -a claude-code2Manually: put the files in place
~/.claude/skills/orca-per-workspace-env/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/orca-per-workspace-env/
1Skills CLI (Vercel)
npx skills add stablyai/orca --skill orca-per-workspace-env -a codex2Manually: put the files in place
.agents/skills/orca-per-workspace-env/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add stablyai/orca --skill orca-per-workspace-env -a cursor2Manually: put the files in place
.cursor/skills/orca-per-workspace-env/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install stablyai/orca orca-per-workspace-env2Manually: put the files in place
.github/skills/orca-per-workspace-env/SKILL.md1Skills CLI (Vercel)
npx skills add stablyai/orca --skill orca-per-workspace-env -a gemini-cli2Platform CLI
gemini skills install https://github.com/stablyai/orca --path skills/orca-per-workspace-envManually: put the files in place
.devin/skills/orca-per-workspace-env/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add stablyai/orca --skill orca-per-workspace-env -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set8
The whole set →Similar
Questions about orca-per-workspace-env
How do I install orca-per-workspace-env in Claude Code?
Run npx skills add stablyai/orca --skill orca-per-workspace-env -a claude-code in your terminal.
What does orca-per-workspace-env do?
It assists in building, debugging, and validating disposable workspace runtimes such as VMs, cloud sandboxes, and containers in Orca.
Why does the skill resolve to orca-ide on Linux?
Outside Orca-managed terminals on Linux, running orca calls the GNOME screen reader at /usr/bin/orca. The skill picks orca-ide to avoid speech output.
Source text
SKILL.md · MIT
--- name: orca-per-workspace-env description: >- Set up, review, debug, or validate an Orca per-workspace environment recipe: the on-demand, disposable runtime (cloud sandbox, VM, SSH host, or local container) Orca creates fresh for each workspace. Use to stand up a new recipe end to end, fix an `environmentRecipes` entry in `orca.yaml`, scaffold provider lifecycle scripts, or resolve an `orca vm recipe doctor` failure. Use `orca-cli` for ordinary worktree and workspace creation with no recipe involved. --- # Per-Workspace Environments 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-per-workspace-env ``` 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