findmy-location
Track a shared contact's location via Apple Find My with street-level accuracy. Returns address, city, and context (home/work/out) by reading map landmarks. Supports configurable known locations and vision fallback for unknown places.
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- findmy-location
- description
- Track a shared contact's location via Apple Find My with street-level accuracy. Returns address, city, and context (home/work/out) by reading map landmarks. Supports configurable known locations and vision fallback for unknown places.
03 SKILL.md 正文
Find My Location
Track shared contacts via Apple Find My with street-corner accuracy.
Requirements
- macOS 13+ with Find My app
- Python 3.9+
- iCloud account signed in on your Mac (for Find My access)
- Location sharing enabled from the contact you want to track
- peekaboo - screen reading CLI (GitHub)
- Hammerspoon (optional) - for reliable UI clicking (hammerspoon.org)
Prerequisites
1. iCloud & Find My Setup
Your Mac must be signed into an iCloud account with Find My enabled:
- System Settings → Apple ID → iCloud → Find My Mac (enabled)
- The person you want to track must share their location with this iCloud account via Find My
2. Install peekaboo
brew install steipete/tap/peekaboo
Grant Accessibility and Screen Recording permissions when prompted (System Settings → Privacy & Security).
3. Install Hammerspoon (optional but recommended)
Hammerspoon provides reliable clicking that works across all apps. Without it, clicks may occasionally go to the wrong window.
brew install hammerspoon
open -a Hammerspoon
Add to ~/.hammerspoon/init.lua:
local server = hs.httpserver.new(false, false)
server:setPort(9090)
server:setCallback(function(method, path, headers, body)
local data = body and hs.json.decode(body) or {}
if path == "/click" then
hs.eventtap.leftClick({x=data.x, y=data.y})
return hs.json.encode({status="clicked", x=data.x, y=data.y}), 200, {}
end
return hs.json.encode({error="not found"}), 404, {}
end)
server:start()
Reload config (Hammerspoon menu → Reload Config), then create ~/.local/bin/hsclick:
#!/bin/bash
curl -s -X POST localhost:9090/click -d "{\"x\":$2,\"y\":$3}"
chmod +x ~/.local/bin/hsclick
Installation
git clone https://github.com/poiley/findmy-location.git
cd findmy-location
./install.sh
Or via ClawdHub:
clawdhub install findmy-location
Configuration
Create ~/.config/findmy-location/config.json:
{
"target": "John",
"known_locations": [
{
"name": "home",
"address": "123 Main St, City, ST",
"markers": ["landmark near home"]
},
{
"name": "work",
"address": "456 Office Blvd, City, ST",
"markers": ["landmark near work"]
}
]
}
| Field | Description |
|---|---|
target |
Contact name to track (optional - defaults to first shared contact) |
known_locations |
Array of places you want labeled with addresses |
markers |
Landmarks visible on the Find My map when at that location |
Usage
findmy-location # Human-readable output
findmy-location --json # JSON output
Example Output
123 Main St, City, ST (home) - Now
{
"person": "contact@email.com",
"address": "Main St & 1st Ave",
"city": "Anytown",
"state": "WA",
"status": "Now",
"context": "out",
"screenshot": "/tmp/findmy-12345.png",
"needs_vision": false
}
| Field | Description |
|---|---|
context |
home, work, out, or unknown |
needs_vision |
If true, use AI vision on screenshot to read street names |
screenshot |
Path to captured map image |
How It Works
- Opens Find My app and selects target contact
- Captures map and reads accessibility data
- Matches visible landmarks against configured known locations
- Returns address and context, or flags for vision analysis
Troubleshooting
| Issue | Solution |
|---|---|
| Clicks go to wrong window | Install Hammerspoon (see prerequisites) |
| "No person found" | Ensure location sharing is enabled in Find My |
Always shows needs_vision: true |
Add markers for frequently visited places |
| Permission errors | Grant peekaboo Accessibility + Screen Recording access |
License
MIT
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.