Core Features

Skills

Orca abilities your coding agents get automatically. Orchestration, automations, feedback, diagnostics, and more

Skills teach the coding agents you already use how to drive Orca: orchestrate parallel agents, create automations, diagnose problems, and more.

Installation

Using the Orca desktop app? Skills are already installed. The app provisions them at launch and keeps them updated.

Otherwise, install them directly:

npx skills add MarcoFaul/skills

Or, in Claude Code, via the plugin marketplace:

/plugin marketplace add MarcoFaul/orca

What You Get

SkillWhat it does
orca:setupMakes a repo Orca-ready: authors .orca/config.json and project lifecycle scripts, then verifies with a real workspace
orca:orchestrateTurns the agent you're talking to into a coordinator of parallel agents; see Agent Orchestration
orca:automateTurns a recurring chore into a scheduled automation and reviews its first run with you
orca:pageBuilds and publishes shareable Pages, then updates them in response to pinned team comments
orca:browserDrives a workspace's in-app browser panes — open, navigate, screenshot, eval, read console, and raw CDP for click/type automation — and routes to Browser Use 3.0 for browsers the panes can't reach
orca:computerDrives native desktop apps through an accessibility-first driver (Cua Driver by default) — inspect windows, click, type, use menus, and verify results with background interaction when the platform supports it
orca:standupSweeps your workspaces, tasks, and agent terminals into a digest: what needs you, what's in flight, what's blocked
orca:doctorDiagnoses Orca problems (expired auth, offline hosts, stale versions) and fixes them one step at a time
orca:feedbackFiles a bug report or feature request: privately to the Orca team (from your account, so we can reply) or as a public GitHub issue
orca:10xAudits how you use Orca and teaches the advanced features you're not using yet
orca:contributeSets up a Orca open-source contribution end to end, following the repo's contribution rules

Using Skills

You usually don't invoke them; agents pick the right skill from context:

  • "report this bug to the orca team" → orca:feedback
  • "what did my agents do overnight?" → orca:standup
  • "run these three refactors in parallel" → orca:orchestrate
  • "open localhost:3000 and click through the signup flow" → orca:browser
  • "open the desktop app and change its settings" → orca:computer

To invoke one explicitly: /orca:feedback in Claude Code, or /orca/feedback in the in-app chat. Other agents that read skills (Codex, Kimi, Vibe, Grok) see the same skills with a orca- prefix.

How They're Delivered

At launch, the desktop app writes managed copies into the standard discovery locations: ~/.claude/skills/orca/ (loaded by Claude Code as a plugin, hence the orca: namespace), ~/.agents/skills/, and ~/.agents/commands/.

  • Your files are never touched. Managed files carry a marker; a skill or command you authored at the same path is left alone.
  • Updates are automatic. Managed skills refresh on every app launch, and ones that no longer ship are cleaned up.

On this page