agentleFS
ucsandmanucsandman/claude-skills/iphone/SKILL.md

iphone

Skill5 starsChanged 2 months agoMITView on GitHub

Use when you need to window size in points; tap coordinates must stay inside this or other iphone operations from the shell. Run 'iphone describe' first.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    If 'iphone' is not on PATH, run every command as: declick run iphone <verb> ...

    line 40
  2. Very specific:

    Every verb: --json (default when piped) --fields a,b --limit N.

    line 41

≈ “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

iphone

Generated by declick from mcp:python C:/Projects/phone-claude/scripts/phone_mcp.py. Deterministic, no screenshots, JSON by default when piped.

iphone (mcp)  source: mcp:python C:/Projects/phone-claude/scripts/phone_mcp.py  server: python C:/Projects/phone-claude/scripts/phone_mcp.py
  screen-info                  Window size in points; tap coordinates must stay inside this. [mutating]
  tap <x>                      Tap at (x, y) in points. [mutating]
  tap-text <text>              Find text on screen and tap it. [mutating]
  long-press <x>               Press and hold at (x, y) in points for 'seconds', then release. [mutating]
  swipe <x1>                   Drag from (x1, y1) to (x2, y2) in points over 'seconds'. [mutating]
  scroll                       Scroll the screen content. [mutating]
  type-text <text>             Type into the currently focused text field (tap the field first). [mutating]
  set-field-text <text>        Replace 'field''s contents with 'text'. [mutating]
  set-clipboard <text>         Set the iPhone system clipboard content. [mutating]
  press-home                   Go to the Home Screen, as if the physical Home gesture were used. [mutating]
  current-page                 Where the Home Screen is: {"index", "total", "zone"}, or None. [mutating]
  goto-home-page               Land on Home Screen page 'n' from anywhere. [mutating]
  open-app <name>              Open an app by friendly name ('Settings'), bundle id, or installed-app name. [mutating]
  open-apps                    The apps that are open, as the iOS app switcher lists them, newest [mutating]
  close-app <name>             Force-quit an app: the switcher's swipe-up. [mutating]
  current-app                  Frontmost app info from WDA (bundleId, name, pid). [mutating]
  ... 15 more verbs (31 total): declick describe iphone --grep <text> | --offset N --limit N | --verb v
common: --json --fields --limit --rows --where --dry-run --full   exit: 0 ok 1 err 2 missing 3 blocked 4 auth

Examples (replace UPPERCASE tokens with real values; 'declick describe iphone --verb <verb>' prints one verb's flags and what it returns):

iphone screen-info --dry-run
iphone tap X --x X --y Y --dry-run
iphone tap-text TEXT --text TEXT --dry-run

If 'iphone' is not on PATH, run every command as: declick run iphone <verb> ... (same output, same exit codes). Every verb: --json (default when piped) --fields a,b --limit N; mutating verbs accept --dry-run. Success: {"ok":true,"data":...,"meta":{"count":N,"truncated":false}}. Failure: {"ok":false,"error":"...","exit":N}. Exit 2 means the verb is not in the server tools list, 3 blocked by governance. Every verb starts mcp:python C:/Projects/phone-claude/scripts/phone_mcp.py, calls one tool and exits, so the server does not have to be running first.

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.