LocalKinAILocalKinAI/kinclaw/skills/location/SKILL.md

location

Skill9 starsChanged 6 months agoApache-2.0View on GitHub

Get the user's current GPS location. Auto-detects the best backend for the host OS:

Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

jholhewres/devclaw-skillstheir own version, first seen Oct 9, 2026

Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
jholhewres/devclaw-skills★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- app_open_cleanSkill
- browser_sessionSkill
- cerebellumSkill
- git_commitSkill
- imsg_sendSkill
- learnSkill
- mail_draftSkill
- music_pauseSkill
- music_playSkill
- notes_attach_imageSkill
- notes_checklistSkill
- notes_export_pdfSkill
- notes_formatSkill
- notes_move_to_folderSkill
- notes_pinSkill
- notes_tableSkill
- sttSkill
- summarizeSkill
- translateSkill
- ttsSkill
- weatherSkill
- webSkill

The file

We split this skill into the rules it gives an agent

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

≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
IP fallback: no permission needed because no GPS hardware is queried — ipapi.co geolocates your public IP.
line 299
Distinctive:
If Geoclue2 doesn't return a fix within 10 seconds (often the case on servers / Pi without WiFi positioning), the skill auto-falls-back to …
line 330

≈ “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

location — real-time GPS, cross-platform

Auto-detected backend per OS:

OS	Backend	Accuracy	Permission
macOS	`corelocationcli` (CoreLocation)	cell / WiFi / GPS (meter-level)	System Settings → Privacy & Security → Location
Linux	`gdbus` + Geoclue2	WiFi / Mozilla MLS / kernel-DRM	xdg-desktop-portal dialog (per-app)
any	`curl ipapi.co` fallback	city-level only	none (uses your IP)

Two-tier location story for KinClaw:

Layer	Where	When to use
`{{location}}` substitution	Soul prompt, from `$KINCLAW_LOCATION` env	Persistent context — "user lives in Beijing"
`location` skill (this)	Tool call to OS location service	Real-time GPS — "user is at $current_lat,$lon"

The skill is opt-in: not installed → clear error message + install hint. Already installed → uses the OS's actual location services.

Privacy

macOS: triggers Apple's standard Location Services permission flow. macOS asks ONCE per process; subsequent calls reuse the grant. Revoke via System Settings → Privacy & Security → Location Services.
Linux: Geoclue2 uses xdg-desktop-portal for permission. On GNOME / KDE it prompts via the portal dialog; on Sway/i3 the dialog may not appear (in which case grant via gnome-control-center privacy once).
IP fallback: no permission needed because no GPS hardware is queried — ipapi.co geolocates your public IP. City-level only.

Usage

location                       → "37.7749,-122.4194"
location format=address        → "1 Apple Park Way, Cupertino, CA"
location format=city           → "Cupertino"
location format=full           → multi-line: lat/lon/alt/accuracy/...

The backend is auto-selected at invocation time; the agent doesn't need to know whether it's running on macOS or Linux.

Linux setup (one-time)

# Debian / Ubuntu
sudo apt install geoclue-2.0 curl

# Fedora
sudo dnf install geoclue2 curl

# Arch
sudo pacman -S geoclue curl

# Verify geoclue is running
systemctl --user status geoclue.service  # may be system-wide, try without --user too

If Geoclue2 doesn't return a fix within 10 seconds (often the case on servers / Pi without WiFi positioning), the skill auto-falls-back to IP geolocation. Forge a derivative skill if you want different fallback behavior (e.g. cache last good fix, exponential retry).

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.

Check your setup, free