agentleFS
mirzaaghazadehmirzaaghazadeh/iwsdk-webxr-skills/skills/iwsdk-official/iwsdk-grab/SKILL.md

iwsdk-grab

Skill1 starsChanged 32 days agoMITView on GitHub

Use emulated XR controllers to verify proximity grabbing for OneHandGrabbable and TwoHandsGrabbable objects. Use for pick up, move, release, or regression-test requests involving near-hand grab with the squeeze button.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this workflow only for OneHandGrabbable or TwoHandsGrabbable.

    line 9
  2. Distinctive:

    Check XR session state and enter XR only when inactive.

    line 14
  3. Distinctive:

    If movement was requested, animate the held controller to the destination.

    line 30
  4. Very specific:

    Do not use trigger index 0, xr select, or teleport-style device mutation for proximity grab.

    line 35
  5. Distinctive:

    Prefer measured ECS state over screenshots.

    line 41
  6. Very specific:

    When the request names an artifact path, save it directly with npx @iwsdk/cli browser screenshot --output-file <path>.

    line 46
  7. Very specific:

    Stop once the requested grab/move/release path and final state are proven.

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

IWSDK Proximity Grab

Use this workflow only for OneHandGrabbable or TwoHandsGrabbable. A DistanceGrabbable uses the ray/trigger path instead.

Execute the requested path

  1. Check XR session state and enter XR only when inactive.
  2. Find the named live entity and query its components and transform. If it is absent, list nearby grabbable matches once and stop with the evidence.
  3. Confirm it has OneHandGrabbable or TwoHandsGrabbable. Do not guess the interaction type from its name.
  4. Animate the requested controller to the object. Default to the right controller only when the user did not choose a hand.
  5. Press and hold squeeze/grip button index 1:

    {"device":"controller-right","buttons":[{"index":1,"value":1}]}
  6. Query the entity for Grabbed or another requested observable state. If the grab did not qualify, make one focused correction to controller position and retry once.
  7. If movement was requested, animate the held controller to the destination.
  8. Release squeeze with index 1, value 0, then query the final transform or state. Move the controller away only when overlap would interfere with the result.

Do not use trigger index 0, xr select, or teleport-style device mutation for proximity grab. Do not edit source merely to make an existing named entity easier to locate; report missing runtime identity when that is the actual defect.

Evidence and stopping

Prefer measured ECS state over screenshots. Capture one runtime image only when the user requested visual evidence or placement must be judged. Batch related queries and avoid repeating session, hierarchy, or transform discovery after a successful read.

When the request names an artifact path, save it directly with npx @iwsdk/cli browser screenshot --output-file <path>. A screenshot returned only to model context does not satisfy a requested file deliverable.

Stop once the requested grab/move/release path and final state are proven. Leave the controller released and the XR session in the state the user requested.

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.