← Search

PositionGuard Skill for Muse
Productivity 🧪 Install ran in our test sandbox · Nov 11, 2026 📌 Pinned version: commit d3948b4
Install test only, on the date shown. This does not guarantee the code is safe.
🔎 Install prompt analysis · 2026-10-13 : uses API keys or tokens
⚙ Needs: A PositionGuard account (install the PositionGuard…

PositionGuard Skill for Muse

Family presence answers from Muse — where members are, area-level only, consent-gated.

At a glance
What
Family presence answers from Muse — where members are, area-level only, consent-gated.
Cost
Free
Needs
A PositionGuard account (install the PositionGuard app and set up your family group) plus an Assistant API key from dev.positionguardai.com (type Assistant, scopes presence:read, counts:read, groups:read — never grant areas:read). Family members must opt in ("Let AI agents see whether I'm at an area") or the skill sees nothing about them. Free tiers unverified — check PositionGuard's pricing before relying on it. Never paste your API key into chat — use the secure credential flow.
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

p
Created by: positionguard
✓ Claimed by creator

Quick answer

PositionGuard Skill for Muse is a free Muse skill that answers family presence questions against the PositionGuard API, such as where members are, who is in an area, and how many are there. Answers are consent-gated and area-level only, never coordinates, and read-only, with your API key passing through a secure connect flow, never in chat.

⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit d3948b4

Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: A PositionGuard account (install the PositionGuard app and set up your family group) plus an Assistant API key from dev.positionguardai.com (type Assistant, scopes presence:read, counts:read, groups:read — never grant areas:read). Family members must opt in ("Let AI agents see whether I'm at an area") or the skill sees nothing about them. Free tiers unverified — check PositionGuard's pricing before relying on it. Never paste your API key into chat — use the secure credential flow. Install "PositionGuard Skill for Muse" for me. A free, open-source (MIT) skill by @positionguard (ChristerLundin) that gives Muse consent-gated access to your PositionGuard family presence: ask "where is Hanna?" or "who is at the lake house?" and get area-level answers (Home, Lake House) — never coordinates, never guesses, read-only, and unknown means unknown. Repository: https://raw.githubusercontent.com/positionguard/positionguard-muse-skill/d3948b483aca5af3205457cbc4afc89c03baee71/SKILL.md Pinned version: install the code at commit d3948b483aca5af3205457cbc4afc89c03baee71 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone the repo into a temporary folder (public HTTPS clone — no account needed) and look inside. 2. Safety check: briefly review SKILL.md and bin/pg.py for anything suspicious (network calls to unexpected hosts, shell commands, credential harvesting). The skill calls the PositionGuard API with an API key — that's by design; it must stay read-only (no writes, no history, no messages) and never expose coordinates. Never paste secrets into chat; use the secure credential flow. If you see a red flag, stop and tell me before going further. 3. Set up everything you can: install the skill into my Muse skills folder and configure the non-secret parts. Then give me the exact remaining manual steps (usually: I create the Assistant API key myself at dev.positionguardai.com with the exact scopes above, then I say "Connect my PositionGuard account" and provide the key through the secure credential flow — never ask me to paste it into chat). Known issue from the creator: key validation can fail even for valid keys (their Cloudflare config blocks the validator) — if that happens, tell me and retry later instead of minting new keys. 4. Verify with a safe dry run: confirm SKILL.md and bin/pg.py are in place in my skills folder, with no live API calls. Do not look up any family member's presence without my explicit confirmation. 5. Report: what you installed, where, and anything still left for me to do myself (or confirm there's nothing left). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it (e.g. authenticated clone); otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me. Never reveal, guess, or store anyone's location; presence lookups always need my confirmation first.

🔒 Security, provenance and what this touches
🧭 What this touches
  • It works with an API key or a token that you provide.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit d3948b4 · 2026-10-13
🧪 Install ran in our test sandbox · Nov 11, 2026
👁 Observed during the install test · Nov 11, 2026 : no network contact
🔎 Install prompt analysis · 2026-10-13 : uses API keys or tokens
What the scan found — excerpts from the install prompt
  • uses API keys or tokens — Prerequisites: A PositionGuard account (install the PositionGuard app and set up your family group) plus an As · 2. Safety check: briefly review SKILL.md and bin/pg.py for anything suspicious (network calls to unexpected ho · 3. Set up everything you can: install the skill into my Muse skills folder and configure the non-secret parts.
🔎 Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
d3948b4 · 2026-10-13
Sandbox install test
Install ran in our test sandbox · Nov 11, 2026
Creator identity
Not verified
Fingerprint watch
Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : uses API keys or tokens

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.