agentsclimarketplace

Locate remembered object

Skill sumitaich1998/jarvisvr/skills/perception/locate-remembered-object

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 locate-remembered-object

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

  • 1 stars1 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

Remember where an object is, and later recall its last-seen location with a marker and a navigation arrow. Use for "remember where my keys are", "where did I leave my phone?", "where are my glasses?", or pinning a spot for later. Triggers: where did I leave, where are my, remember where, find my, last seen, mark this spot.

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

2.9 KB, as published. Nobody here has run it

Locate Remembered Object

Two directions: store a spatial memory ("remember my keys are here") and recall one ("where did I leave my keys?"). Locations come from explicit user intent, gaze hit point, or a focused object in the current frame.

Remember (store)

  1. Resolve the position: explicit position, else perception.gaze.hit_point, else the focused object in view.
  2. Call remember_object{name, position?, anchor?}. It writes to spatial memory and drops a vision_annotation/scene_label marker at the spot.
  3. Confirm: "Got it — I'll remember where your keys are. I marked the spot."

Marker (drop_scene_label → scene_label):

{ "widget_type": "scene_label",
  "transform": { "anchor": "world", "position": [1.2,0.95,0.4], "billboard": true },
  "props": { "text": "Keys", "icon": "pin", "color": "#FF5252", "pin": true } }

Recall (find)

  1. Call find_object{name}. If found, it returns the position and spawns a marker plus a navigation_arrow pointing to it; if not, it says it hasn't seen the item recently.
  2. Narrate via agent.observation, render the marker + arrow.

agent.observation + navigation_arrow (show_navigation):

{ "text": "Your keys should be right here — I've marked the spot.", "final": true,
  "annotations": [ { "label": "keys", "position": [1.2,0.95,0.4], "anchor": "world" } ] }

{ "widget_type": "navigation_arrow",
  "props": { "target_label": "keys", "direction": [0.75,0.0,0.66], "distance_m": 2.4, "style": "arrow" } }

Edge cases

  • Never seen / not remembered → "I haven't seen your keys recently." Offer to start watching ("tell me when you set them down").
  • Stale memory → mention how long ago it was last seen; offer a fresh look via describe-surroundings.
  • Ambiguous name ("my bag" but two are known) → ask which, or list known matches (use clarify-intent).
  • Position unknown but item known → confirm you remember it without a marker: "I remember your keys, but I didn't note exactly where."
  • Travel, not in-room → if the destination is a place not an object, hand to navigation-agent (wayfind / remember-location).

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.