agentleFS
steerlabssteerlabs/opensteer/.agents/skills/mac-gui/SKILL.md

mac-gui

Skill204 starsChanged 6 days agoMITView on GitHub

Use when running or diagnosing macOS GUI or Electron journeys in disposable Tart VMs (`pnpm test:vm`, goldens, persistent guests), changing Mac app observation, background input, owner viewing or the computer-use helper wire contract, diagnosing a Mac task Watch or owner window picture that freezes, disappears or fails to reopen, or helping a person enable macOS grants for an approved Mac app.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Stop everything you start by captured PID or serial, even after a failure.

    line 15
  2. Very specific:

    Never drive the host screen: GUI and Electron checks run only in the VM (pnpm test:vm).

    line 16
  3. Distinctive:

    Never read or operate signing keys, Apple accounts or release credentials.

    line 17
  4. Distinctive:

    Never use a person's real profile, credentials, saved passwords, Messages or personal stores.

    line 18
  5. Very specific:

    Never point dev, tests or scripts at the live install (~/Library/Application Support/Opensteer, ~/Opensteer, Opensteer Beta), and never …

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Mac GUI

Procedures for anything that drives a macOS screen, and for Mac app control. GUI test VMs and Computer use hold the constraints.

Safety rules

  • Devices have one owner: never take another task's simulator, emulator, USB phone or VM slot.
  • Stop everything you start by captured PID or serial, even after a failure; never kill by name.
  • Never drive the host screen: GUI and Electron checks run only in the VM (pnpm test:vm).
  • Never read or operate signing keys, Apple accounts or release credentials.
  • Never use a person's real profile, credentials, saved passwords, Messages or personal stores.
  • Never point dev, tests or scripts at the live install (~/Library/Application Support/Opensteer, ~/Opensteer, Opensteer Beta), and never modify, migrate or repair it. Reading its logs read-only to diagnose a live view is the one exception.
  • Skipped, blocked or unrun checks are unverified, never passed.
  • VM checks run after merge or on request, never as a pre-merge gate. Never boot a golden.

Procedures

  • VM journeys: runs, records, native resources, persistent guests, goldens.
  • Mac app control: helper checks and app-control journeys.
  • Frozen live view: diagnosing window pictures from logs.
  • Set up a Mac app: guiding a person through macOS grants.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.