orca-cli
Drive a running Orca ADE (stablyai/orca) through the documented orca JSON CLI for worktrees and agent terminals.
Skill by matthewhand
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/matthewhand-orca-cli
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/orca-cli
What's inside
- Skill name
orca-cli- Description
- Drive a running Orca ADE (stablyai/orca) through the documented orca JSON CLI for worktrees and agent terminals. Use when the operator asks to create an Orca worktree or to send, wait, and read an Orca terminal. Refuses orca serve pairing and orca account.
- License
- MIT
- Instructions
- 66 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- drive.py
SKILL.md (first lines)
# Orca CLI (Orca ADE) This skill drives **Orca ADE** by Stably (`stablyai/orca`, onorca.dev): a desktop agent environment that runs coding CLIs in git worktrees. It is not Orca Security, StreamNative Orca, or maritime Orca AI. Orca ships the `orca` binary with the desktop app. It must already be on `PATH` (Settings → General → Orca CLI). This skill does not install Orca, does not sign into provider accounts, and does not speak `orca serve`. ## Drive the JSON CLI Prefer the bundled `drive.py`. It allowlists the phase-1 commands, always passes `--json`, and prints JSON on failure instead of inventing a result. ```bash python3 drive.py status python3 drive.py worktree ps python3 drive.py worktree create --repo id:<repoId> --name my-task python3 drive.py terminal list python3 drive.py terminal read python3 drive.py terminal send --text "continue" --enter python3 drive.py terminal wait --for tui-idle --timeout-ms 30000 python3 drive.py terminal read ``` Equivalent raw commands, when you are already inside an Orca-managed worktree and `drive.py` is not staged: ```bash orca status --json orca worktree create --repo id:<repoId> --name my-task --json orca terminal send --text "continue" --enter --json orca terminal wait --for tui-idle --timeout-ms 30000 --json orca terminal read --json ``` Read the terminal before sending input unless the next input is obvious. Terminal handles go stale after an Orca restart: run `terminal list` again and use the new handle. Pass `--terminal <handle>` when more than one terminal is open. Use `--worktree active` (or `id:`, `path:`, `branch:`) when the shell is not inside the target worktree. `terminal wait --for tui-idle` blocks until the agent TUI is idle. Pass `--timeout-ms` so a stuck agent cannot wait forever. After it returns, read the terminal again and report that output. ## Honesty - If `drive.py` prints `orca binary not found on PATH`, say so. Do not invent worktree ids, terminal transcripts, or a claim that Orca ran. - If `orca` exits non-zero or returns non-JSON, quote the error payload. Do not paraphrase it into a success. - Do not run `orca serve`, `orca account`, or `orca environment`. Pairing and account login are not part of this skill. - Do not publish artifacts (`orca artifacts`) unless the operator asked in this turn, and even then call `orca` directly only after they confirm publishing is enabled. `drive.py` will refuse that command. ## Out of scope `orca serve` remote pairing, managed provider logins, browser computer-use, and the mobile emulator. Those stay undocumented or out of this allowlist until Orca publishes a stable third-party API.
From matthewhand/operating-swarm, MIT.
More from matthewhand/operating-swarm
- 0.644score
support-session-ownership
matthewhand
Teaches Support the first-run open-swarm journey and when Operating Swarm owns a thread versus CLI or remote sessions.
SkillAFreshness: A★ 20Claude Code +9 - 0.641score
database-migrations
matthewhand
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs…
SkillAFreshness: A★ 20Claude Code +9 - 0.641score
error-handling
matthewhand
Patterns for robust error handling across TypeScript, Python, and Go.
SkillAFreshness: A★ 20Claude Code +9 - 0.629score
teamai-baseline
matthewhand
Shared TeamAI rules baseline (coding style, review, testing, git, security, performance) for Operating Swarm seats.
SkillAFreshness: A★ 20Claude Code +9 - 0.619score
domain-modeling
matthewhand
Build and sharpen a project's domain model.
SkillAFreshness: A★ 20Claude Code +9 - 0.607score
backend-patterns
matthewhand
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
SkillAFreshness: A★ 20Claude Code +9 - 0.604score
self-update-pr
matthewhand
Open a real GitHub pull request on matthewhand/open-swarm from an in-app coding CLI.
SkillBFreshness: B★ 20Claude Code +9 - 0.604score
ddg-search
matthewhand
Perform web searches using DuckDuckGo (free, no API key) via the bundled search.py script.
SkillBFreshness: B★ 20Claude Code +9 - 0.554score
writing-changelog
matthewhand
Writes a Keep a Changelog entry from a description of changes or a git log.
SkillCFreshness: C★ 20Claude Code +9 - 0.554score
reviewing-code
matthewhand
Reviews a diff or file for bugs, security issues, and missing tests, returning prioritized findings.
SkillCFreshness: C★ 20Claude Code +9 - 0.554score
conventional-commit
matthewhand
Writes a single Conventional Commits message from a description of changes or a git diff.
SkillCFreshness: C★ 20Claude Code +9 - 0.549score
counting-lines
matthewhand
Counts the non-blank lines in a file using the bundled count.py script.
SkillCFreshness: C★ 20Claude Code +9
Signals
- Stars
- 20
- Forks
- 6
- Open issues
- 1
- Last commit (this folder)
- Sep 30, 2026 (28 days ago)
- Last release
- Jun 19, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/matthewhand/operating-swarm
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from matthewhand
- 0.644score
support-session-ownership
matthewhand
Teaches Support the first-run open-swarm journey and when Operating Swarm owns a thread versus CLI or remote sessions.
SkillAFreshness: A★ 20Claude Code +9 - 0.641score
database-migrations
matthewhand
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs…
SkillAFreshness: A★ 20Claude Code +9 - 0.641score
error-handling
matthewhand
Patterns for robust error handling across TypeScript, Python, and Go.
SkillAFreshness: A★ 20Claude Code +9 - 0.629score
teamai-baseline
matthewhand
Shared TeamAI rules baseline (coding style, review, testing, git, security, performance) for Operating Swarm seats.
SkillAFreshness: A★ 20Claude Code +9 - 0.619score
domain-modeling
matthewhand
Build and sharpen a project's domain model.
SkillAFreshness: A★ 20Claude Code +9 - 0.607score
backend-patterns
matthewhand
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
SkillAFreshness: A★ 20Claude Code +9
Cite this page
orca-cli skill. Agent Mart. https://agentmart.dev/skills/matthewhand-orca-cli (last updated 2026-10-24)