Secure home

Skill sumitaich1998/jarvisvr/skills/smart-home/secure-home

An AI agentic operating system for mixed reality on the Meta Quest 3 — your own J.A.R.V.I.S. Multi-agent orchestration, multimodal perception (sight/hearing/gaze), 42 holographic widgets, 20 LLM providers.

Install

npx -y skills add sumitaich1998/jarvisvr --skill secure-home

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Check and control home security — locks, cameras, and sensors — with explicit confirmation for anything that reduces security. Use for "lock the front door", "is the door locked?", "show the front camera", or "arm the house". Triggers: lock, unlock, door, security, camera, sensor, arm, disarm, is it locked.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.8 KB, 588 tokens by cl100k_base, as published. Nobody here has run it

Secure Home

Manage lock, camera, and sensor devices on a smart_home_panel. Security is sensitive: locking is safe to do directly; unlocking/disarming always requires explicit confirmation.

Steps

Classify the request. Read (status), increase-security (lock/arm), or reduce-security (unlock/disarm).
Status / lock / arm → apply directly, render the panel, confirm.
Unlock / disarm → do not act yet: raise a confirmation notification_toast (notify) and only proceed on the user's explicit tap.
Render the security devices with show_smart_home; react to controls.

Output

smart_home_panel (security scope):

{ "widget_type": "smart_home_panel",
  "props": { "room": "Entry",
             "devices": [
               { "id": "lock_1", "name": "Front Door", "type": "lock", "state": { "locked": true } },
               { "id": "cam_1", "name": "Front Camera", "type": "camera", "state": { "on": true } },
               { "id": "sensor_1", "name": "Garage Sensor", "type": "sensor", "state": { "on": true } } ] },
  "interactions": ["tap","grab","toggle"] }

Confirmation gate before unlocking (notify → notification_toast):

{ "widget_type": "notification_toast",
  "props": { "title": "Unlock front door?", "body": "This will unlock the front door.",
             "severity": "warning", "source": "Security",
             "actions": [ { "id": "confirm_unlock", "label": "Unlock" }, { "id": "cancel", "label": "Cancel" } ],
             "auto_dismiss_ms": 0 } }

Only a client.interaction{value:{action_id:"confirm_unlock"}} performs the unlock (holo.update locked:false).

Edge cases

Unlock without confirmation → never. Re-prompt if the tap times out.
Status query → answer from state, no change ("The front door is locked.").
Camera view → a live camera feed beyond status overlaps perception's vision_feed; here just report on/off unless a stream integration exists.
"Arm the house" → set sensors/cameras on and lock doors as a secure scene (run-home-scene with a "leaving" scene).
Alarm/sensor tripped → raise an error-severity toast immediately.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most security skills give in 588 tokens

Counted across 648 of the 828 authors here whose files we hold, read 2026-08-07

Parameterize all database queriesin 68 of 648, across 51 files
Hash passwords using bcrypt, scrypt, or argon2in 49 of 648, across 36 files
Apply rate limiting to authentication endpointsin 48 of 648, across 24 files
Configure security headersin 35 of 648, across 19 files
Validate all inputsin 32 of 648, across 24 files
Validate all external input at the system boundaryin 29 of 648, across 19 files
Run containers as a non-root userin 28 of 648, across 15 files
Use httponly secure samesite cookies for sessionsin 26 of 648, across 15 files
Run dependency audits before every releasein 21 of 648, across 10 files
Encode output to prevent cross-site scriptingin 21 of 648, across 11 files
Copy dependencies before source codein 20 of 648, across 9 files
Store secrets in environment variablesin 20 of 648, across 18 files

Said here and by no other author read

classify the request as read, increase-security, or reduce-security
apply lock or arm actions directly
raise a confirmation toast before unlocking
proceed with unlock only on explicit tap
render security devices with show_smart_home
react to control interactions

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.