agentleFS
omarshahineomarshahine/findmy-cli/skills/findmy/SKILL.md

findmy

Skill62 starsChanged 11 days agoMITView on GitHub

Query Find My friend locations on macOS. Returns name, coarse location, staleness, and distance for everyone in the FindMy.app People sidebar. Use when the user asks "where is X", "is X home", "how far is X", or wants a location refresh for a friend. macOS only; requires the display to be awake (the skill self-wakes via caffeinate) and Screen Recording granted to the host process.

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use touchdesigner-mcp, teams-meeting-pipeline and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 7 projects that use this

  • john-data-chenSkill

    teams-meeting-pipeline

    Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.

    Also in 10 projects that use this

  • Tommy-ywSkill

    songwriting-and-ai-music

    Songwriting craft, AI music generation prompts (Suno focus), parody/adaptation techniques, phonetic tricks, and lessons learned. These are tools and ideas, not rules. Break any of them when the art calls for it.

    Also in 12 projects that use this

  • mae616Skill

    p5js

    p5.js(クリエイティブコーディング)のProcessing由来「コードでスケッチ」思想を軸に、setup/drawループ・座標系・インタラクション・パフォーマンス最適化を整理する。p5.js、Processing、クリエイティブコーディング、ジェネラティブアート、インタラクティブ表現、ビジュアルプログラミング、Canvas描画、パーティクル、フラクタル、ノイズ表現に関する相談で必ず使うこと。ユーザーが「コードでアート」「動くビジュアル」「インタラクティブな描画」と言った場合にも適用する。

    Also in 13 projects that use this

  • aivrarSkill

    competitor-news-monitor

    Watch named companies for material news; cited digests.

    Also in 6 projects that use this

  • aivrarSkill

    blocked-page-recovery

    Recover blocked/paywalled/WAF'd pages via fallbacks.

    Also in 6 projects that use this

  • +3 more from aivrar

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    After granting, fully quit and relaunch the host — TCC is read once at process start.

    line 83

“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “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

Find My Location Query

Wraps the findmy CLI bundled with this plugin. The CLI drives FindMy.app: activates it, switches to the People tab, screencaptures the window, runs Vision OCR, and parses the sidebar.

When to use

  • "Where is Omar?"
  • "Is Sarah home yet?"
  • "How far away is Mike?"
  • "Anyone near downtown?"

Run

# List everyone in the sidebar (default: human-readable table)
bash "${CLAUDE_PLUGIN_ROOT}/scripts/findmy.sh" people

# Same, as JSON — best for programmatic follow-up
bash "${CLAUDE_PLUGIN_ROOT}/scripts/findmy.sh" people --json

# Lookup a single friend (name match is case-insensitive, substring OK)
bash "${CLAUDE_PLUGIN_ROOT}/scripts/findmy.sh" person "Omar Shahine" --json

The wrapper auto-builds bin/findmy and bin/findmy-helper on first run via make (needs Go 1.22+ and Xcode Command Line Tools). Subsequent runs just exec the binary.

Output shape (JSON)

[
  {
    "name": "Omar Shahine",
    "location": "Redmond, WA",
    "staleness": "Paused",
    "distance": "7 mi"
  }
]
  • name — display name as shown in the FindMy sidebar
  • location — city, state (or device label when sharing from a device)
  • staleness — "Now", "X min. ago", "X hr. ago", "Paused", "" (live)
  • distance — distance from this Mac if FindMy shows it (e.g. "7 mi", "1,971 mi")

Caveats — surface these when relevant

  • staleness: "Paused" means the friend has paused location sharing. The reported location is the last known position, possibly hours or days old. Lead with this when reporting the result.
  • Display sleep: the CLI wakes the display via caffeinate -u -t 3 before each capture. If running on a truly headless Mac, ensure a display (real or dummy USB-C plug) is attached — FindMy.app needs WindowServer compositing.
  • Focus steal: each invocation briefly raises FindMy.app to the front.
  • Back-to-back races: two findmy invocations within ~5s can fail with "could not create image from window" — space them out.
  • No coordinates: this is OCR of the sidebar text; lat/lon is not available. Apple doesn't expose friend locations through any public API.

Permission requirements (one-time)

Grant to the terminal emulator (or to the host process running this skill):

  • Screen Recording — System Settings → Privacy & Security → Screen Recording
  • Accessibility — only needed if a future version starts clicking rows (not used today)

After granting, fully quit and relaunch the host — TCC is read once at process start. The CLI's findmy-helper permissions subcommand can verify:

"${CLAUDE_PLUGIN_ROOT}/bin/findmy-helper" permissions
# → {"accessibility":true,"screenRecording":true}

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.