agentleFS
joinwell52-AIjoinwell52-AI/CodeFlowMu-open/skills/windows-use/SKILL.md

windows-use

Skill2 starsChanged 4 months agoMITView on GitHub

Control approved Windows desktop applications through CodeFlowMu Windows Use tools. Use when a Cursor Agent must inspect, click, type, scroll, invoke UI Automation controls, or capture a window in a native Windows app; do not use for browser-only work when a browser-specific capability is available.

The file

Show its rules and text

We split this skill into the rules it gives an agent

17 rules. About 0 are common, 6 are distinctive, and 11 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 11

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call windows.capabilities when host readiness is unknown.

    line 12
  2. Very specific:

    Call windows.list_targets before handling login.

    line 13
  3. Very specific:

    Call windows.inspect_ui when labels or standard controls can identify the target.

    line 17
  4. Very specific:

    Only when an operation truly needs foreground input, call windows.activate.

    line 18
  5. Very specific:

    Use windows.screenshot and window-relative coordinates only when UI Automation is insufficient.

    line 19
  6. Very specific:

    Call windows.cancel when the user asks to stop.

    line 21
  7. Very specific:

    Read approved targets and login characteristics: windows.list_targets

    line 26
  8. Very specific:

    Wait for a launched native window: windows.wait_for_app

    line 28
  9. Very specific:

    Verify/pause/resume the current session: windows.status, windows.cancel, windows.resume

    line 30
  10. Very specific:

    Read control structure: windows.inspect_ui

    line 32
  11. Very specific:

    Use literal text with windows.type_text.

    line 37
  12. Distinctive:

    Never attempt to authorize an application through the tools.

    line 41
  13. Distinctive:

    Never automate terminals, CodeFlowMu, ChatGPT/Codex, authentication dialogs, password managers, Windows security tools, the Run dialog, or …

    line 42
  14. Distinctive:

    Do not bypass CAPTCHA, MFA, paywalls, safety warnings, or access controls.

    line 43
  15. Distinctive:

    Ask for action-time confirmation before deleting data, sending messages, submitting forms, uploading files, changing sharing/access, …

    line 44
  16. Distinctive:

    Stop if the desktop is locked, the target window cannot be activated, observation fails, or the window no longer belongs to the approved …

    line 45
  17. Distinctive:

    Prefer a browser-specific capability for Chrome or web applications so logged-in browser state and page semantics remain available.

    line 46

≈ “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

Windows Use

Control only applications the user approved in CodeFlowMu Panel. Treat application approval as permission to access that app, not blanket permission for risky side effects.

Workflow

  1. Call windows.capabilities when host readiness is unknown.
  2. Call windows.list_targets before handling login. Follow loginMethod, verificationChannel, loginInstruction, and requiresUser; never infer an authentication flow. A saved password is reported only as a boolean and is never returned.
  3. For qr_code or verification-code methods, stop at the login step and wait for the user. If the method is unspecified, ask the user instead of guessing.
  4. To open an approved target, first reuse any window returned by discovery. Call windows.launch_target only when the target is not already running. Native launch is idempotent and may return already_running=true; never relaunch a minimized, hidden, or initializing application. Web launch only opens the URL—route all page DOM work to a browser-specific capability.
  5. For a native target, call windows.wait_for_app instead of using Shell sleep, then select the returned app_id and window_id. Never invent or reuse a stale window identifier.
  6. Call windows.inspect_ui when labels or standard controls can identify the target. Prefer windows.invoke_ui: UI Automation InvokePattern works without taking foreground focus.
  7. Only when an operation truly needs foreground input, call windows.activate. Never use PowerShell, Alt+Tab, or a terminal to force focus. If activation is blocked, windows.click can deliver a bounded window-message fallback, while text/keyboard input must pause for one user click.
  8. Use windows.screenshot and window-relative coordinates only when UI Automation is insufficient.
  9. Batch a small set of related actions, then inspect again to verify the result. Stop after an error or if the user takes over the foreground window.
  10. Call windows.cancel when the user asks to stop. Claim “paused” only after it returns paused=true. This is an MCP-session pause, not project-level disablement. Call windows.status to verify; call windows.resume only after explicit user instruction.

Tool selection

  • Discover applications: windows.list_apps
  • Read approved targets and login characteristics: windows.list_targets
  • Open an approved native or Web target: windows.launch_target
  • Wait for a launched native window: windows.wait_for_app
  • Restore and activate a window: windows.activate
  • Verify/pause/resume the current session: windows.status, windows.cancel, windows.resume
  • Observe pixels: windows.screenshot
  • Read control structure: windows.inspect_ui
  • Invoke a standard control: windows.invoke_ui
  • Point interaction: windows.click, windows.scroll
  • Text and keys: windows.type_text, windows.keypress

Use literal text with windows.type_text; use windows.keypress for Enter, Tab, Escape, arrows, and chords. Focus the observed editable surface before typing.

Safety

  • Never attempt to authorize an application through the tools. Ask the user to approve it in Panel.
  • Never automate terminals, CodeFlowMu, ChatGPT/Codex, authentication dialogs, password managers, Windows security tools, the Run dialog, or permission/security settings.
  • Do not bypass CAPTCHA, MFA, paywalls, safety warnings, or access controls.
  • Ask for action-time confirmation before deleting data, sending messages, submitting forms, uploading files, changing sharing/access, installing software, making purchases, or transmitting sensitive data unless the user explicitly pre-approved that exact action and destination.
  • Stop if the desktop is locked, the target window cannot be activated, observation fails, or the window no longer belongs to the approved application.
  • Prefer a browser-specific capability for Chrome or web applications so logged-in browser state and page semantics remain available.

Windows Use actions bring the target app to the foreground. Keep operations bounded and allow immediate user interruption.

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.