<Devsly/>
NotebookLM Watermark Remover
Remove the NotebookLM watermark from PDF slide exports — free, unlimited, and 100% in your browser.
View
NotebookLM Video Watermark Remover
Remove the NotebookLM watermark from every frame of your MP4 and auto-trim the end card — free and unlimited.
View
Gemini Watermark Remover
Remove the Gemini (Veo) sparkle watermark from every frame of your AI-generated MP4 — free and unlimited.
View
MCP https://devsly.io/mcp MCP Tools Best Skills API Docs

Keyboard Shortcuts

Navigation

Quick Search
⌘ / Ctrl + K
Toggle Dark Mode
⌘ / Ctrl + D
Close Dialogs
Esc

Tool Actions

Execute / Process
⌘ / Ctrl + Enter
Clear Input
⌘ / Ctrl + Shift + C
Copy Output
⌘ / Ctrl + Shift + X

Editor

Select All
⌘ / Ctrl + A
Undo
⌘ / Ctrl + Z
Redo
⌘ / Ctrl + Shift + Z

Updated 2d ago

by google-deepmind

robotics-antigravity-plugin

GDM Robotics Skills for agentic robotics workflows across simulation and real robots.

  • New — Created in the last 30 days
  • Active — Updated in the last 14 days
Works with
  • Gemini
View on GitHub (opens in a new tab)

197 GitHub stars (197)

+197 in 6 days

Stars gained per day · daily snapshots since Nov 18
Stars gained per day, Nov 18 to Nov 22: +173 in total; the busiest day was Nov 20 with +66 stars.Nov 19: +46 starsNov 20: +66 starsNov 21: +37 starsNov 22: +24 stars
Stars gained between daily snapshots
PeriodNew stars
Nov 19+46
Nov 20+66
Nov 21+37
Nov 22+24
  • 18 skills (18 skills found in its SKILL.md files)
  • 19 forks (19 forks)
  • 2d ago last update (Last updated 2d ago)

Install

Skills CLI

npx skills add google-deepmind/robotics-antigravity-plugin

Asks which skills and agents to install. Just one: npx skills add google-deepmind/robotics-antigravity-plugin --skill blender-creation — add -g for every project.

Claude Code

git clone https://github.com/google-deepmind/robotics-antigravity-plugincp -r "robotics-antigravity-plugin/plugins/robotics/skills/blender-creation" ~/.claude/skills/

Copies the blender-creation skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.

Plugin

/plugin marketplace add google-deepmind/robotics-antigravity-plugin

Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.

Skills can run code on your machine — read the SKILL.md first.

What it does

In the author's own words, from each skill's SKILL.md.

  • blender-creation

    Creates physically calibrated, articulated, PBR-textured 3D MuJoCo assets (MJCF model.xml, .mjz, mjSpec) from scratch using headless Blender (bpy, bmesh, blender_mesh_utils, asset_build_utils), convex collision synthesis, 10-scenario auditing, and Studio preview. Use only when asked to create, model, or build a 3D MuJoCo object from a URL, image, or text description, or when blender-creation is n…

    plugins/robotics/skills/blender-creation/SKILL.md on GitHub (opens in a new tab)
  • fr3-duo-control

    Franka Duo robot only (Franka Research 3 / FR3 Duo dual-arm cell with Robotiq 2F-85 grippers, ZED Mini and RealSense D405 cameras). Brings up, homes, and controls it via pylibfranka on hardware or in MuJoCo sim. Use only when the user names Franka Duo, FR3 Duo, or fr3_duo.

    plugins/robotics/skills/fr3-duo-control/SKILL.md on GitHub (opens in a new tab)
  • i2rt-yam-bringup

    Checks and installs the I2RT YAM SDK (i2rt), configures Linux socketcan or macOS gs_usb CAN bringup for I2RT YAM robot arms, and provides a wave smoke test (wave.py). Use only before bringing up or programming a physical or simulated I2RT YAM robot arm, or when asked to run a wave gesture on an I2RT YAM robot. Don't use for non-YAM CAN bus debugging (e.g. automotive OBD-II or industrial PLC CAN n…

    plugins/robotics/skills/i2rt-yam-bringup/SKILL.md on GitHub (opens in a new tab)
  • i2rt-yam-ik

    Solves 6-DOF inverse kinematics for the I2RT YAM and YAM Pro robot arm using Mink + DAQP on combined YAM + gripper MJCF. Use only when computing joint targets or local Cartesian moves on an I2RT YAM or YAM Pro robot arm. Don't use for non-YAM inverse kinematics, general quadratic programming (QP) solvers, or non-robotics tasks.

    plugins/robotics/skills/i2rt-yam-ik/SKILL.md on GitHub (opens in a new tab)
  • iteration

    Staged execution and video-based debugging workflow for physical or MuJoCo simulated robots: splitting a robot manipulation task into stages, testing each stage with one script, reviewing rollout videos, and verifying physical completion after release and settle. Use only when writing code that makes a physical or simulated robot act and move. Don't use for non-robotics software engineering, UI/W…

    plugins/robotics/skills/iteration/SKILL.md on GitHub (opens in a new tab)
  • motion-planning

    Plans collision-free 6-DoF grasped-object paths, coupled robot arm+object joint trajectories, and Cartesian contact strokes for manipulation arms (SO-101, I2RT YAM, ALOHA, or MuJoCo robots) with stereo triangulation, clearance diagnostics, and camera overlay checks. Use when planning robot arm trajectories near tabletop obstacles, containers, doors, or apertures. Don't use for eye-in-hand servoin…

    plugins/robotics/skills/motion-planning/SKILL.md on GitHub (opens in a new tab)
  • mujoco-audit

    Audits, validates, and remediates MuJoCo 3D assets (MJCF model.xml, .mjz archives, or mjSpec models) using the 7-point static/PBR/mesh hygiene checker (--static_only), the 10-scenario physical test suite (audit_scenarios.py with --scenarios and --thresholds_json), and Before-vs-After comparison sheets. Use only when the user explicitly names MuJoCo, MJCF, .mjz, or mjSpec to audit, validate, or fi…

    plugins/robotics/skills/mujoco-audit/SKILL.md on GitHub (opens in a new tab)
  • mujoco-playground-rl

    Authors, inspects in MuJoCo Studio, audits, trains, and deploys GPU-accelerated RL tasks on MuJoCo Playground and MuJoCo Menagerie 3D robots using PyTorch/Warp reaf-sim flat_scene (DeviceLayer / TaskLayer) and RSL-RL. Use by default when creating a MuJoCo Playground RL environment, training or evaluating locomotion/manipulation RL policies, or deploying RSL-RL checkpoints. Don't use for non-RL co…

    plugins/robotics/skills/mujoco-playground-rl/SKILL.md on GitHub (opens in a new tab)
  • mujoco-playground

    Runs and zero-shot transfers robot controllers across MuJoCo Playground sim and physical SO-101 or I2RT YAM DeviceLayers (plus sim G1 and Trossen WXAI) via PlaygroundSim2Real and setup_scene(spec), composing Studio, perception, IK, motion-planning, and visual-servoing skills. Use by default for SO-101, YAM, G1, or WXAI sim or sim-to-real controllers. Don't use for custom raw drivers, GPU RL train…

    plugins/robotics/skills/mujoco-playground/SKILL.md on GitHub (opens in a new tab)
  • mujoco-showcase-shot

    Renders a studio-lit 360-degree turntable showcase video (.mp4) and keyframe sheet for a MuJoCo asset (MJCF model.xml, .mjz, or mjSpec/MjModel) using MuJoCo's Filament PBR renderer (mjrf), sweeping articulated joints, pulsing collision geoms, and drawing a HUD overlay. Use only when rendering a showcase turntable video for a MuJoCo MJCF, .mjz, mjSpec, or MjModel asset. Don't use for non-MuJoCo tu…

    plugins/robotics/skills/mujoco-showcase-shot/SKILL.md on GitHub (opens in a new tab)
  • mujoco-studio-sidecar

    Runs the MuJoCo Studio Web sidecar (studiod daemon) to stream a live, hot-reloading MuJoCo simulation into the Antigravity aux pane. Use only when MuJoCo or mujoco_studio is used to launch studiod, scaffold a Studio workspace (messages.py, sim_plugin.py, viewer_plugin.py, scene.xml), check /_studio/status, or read captured SimHistory frames; load with mujoco-studio. Don't use for non-MuJoCo simul…

    plugins/robotics/skills/mujoco-studio-sidecar/SKILL.md on GitHub (opens in a new tab)
  • rgb-object-localization

    Localizes metric 3D object coordinates and principal orientation axes of manipulation targets for robot arms (SO-101, I2RT YAM, ALOHA, or MuJoCo tabletop scenes) from RGB-only workspace cameras using gemini-4-hydrogen (or VLM + segmentation fallback), plane projection, or two-view stereo. Use when localizing graspable objects for a robot arm without a depth sensor. Don't use for non-robotics comp…

    plugins/robotics/skills/rgb-object-localization/SKILL.md on GitHub (opens in a new tab)
  • share-example

    Packages a real-robot or simulation demo (compact transcript.jsonl, final files, videos under 10 MB) into a scrubbed bundle with a pre-filled Show and tell GitHub Discussions URL. Use only when sharing a robotics example to GitHub Discussions. Don't use for creating repos, PRs, or issues.

    plugins/robotics/skills/share-example/SKILL.md on GitHub (opens in a new tab)
  • sim2real-gauntlet

    Verifies a robot manipulation controller in MuJoCo simulation (robosim_gauntlet) across perturbation tiers T0-T4 with .mcap logging, physical safety grading, and paired Common Random Numbers before real-robot deployment. Use only when verifying, hill-climbing, or debugging a MuJoCo robot manipulation controller, auditing a task scene/goal predicate, or forking a failed episode. Don't use for RL t…

    plugins/robotics/skills/sim2real-gauntlet/SKILL.md on GitHub (opens in a new tab)
  • sim2real-iteration

    Guides disciplined MuJoCo robotics sim-to-real controller iteration using robosim_gauntlet verification, preflight scene/goal audits, deterministic episode forking, paired Common Random Numbers, and adversarial robotics critic reviews. Use only when iterating on MuJoCo robot manipulation controllers, triaging contact/safety failures, or comparing controller candidates. Don't use for RL training (…

    plugins/robotics/skills/sim2real-iteration/SKILL.md on GitHub (opens in a new tab)
  • so101-bringup

    Guides physical SO-101 6-DOF robot arm bring-up from plug-in to Stage 3 Hello World motion and video: uv install, port/camera discovery (Stages 0-1), Feetech STS3215 joint calibration and abort-retreat checks (Stage 2), Hello World (Stage 3), and workspace USB bandwidth/frame checks (Stage 4). Use only when setting up, calibrating, checking, or operating an SO-101 robot arm and cameras. Don't use…

    plugins/robotics/skills/so101-bringup/SKILL.md on GitHub (opens in a new tab)
  • so101-calibration

    Stage 5 3D hand-eye projection and tabletop surface height (z_table) calibration for the physical SO-101 6-DOF robot arm with a fixed/overhead workspace camera: fixed-camera check, two-cue gripper marker verification, guarded 3 mm vertical touch-down probing, and 3x4 projective hand-eye least squares. Use only after SO-101 Stage 3 bring-up when calibrating a physical SO-101 arm to a fixed camera.…

    plugins/robotics/skills/so101-calibration/SKILL.md on GitHub (opens in a new tab)
  • visual-servoing

    Aligns an eye-in-hand physical or simulated robot arm end-effector (SO-101, I2RT YAM, or MuJoCo robot grippers) and grasp orientation to sub-millimeter precision using robot IBVS (analytical hover-plane ray alignment or CPU OpenCV feature-matching IBVS). Use only for closed-loop eye-in-hand robot gripper visual servoing before grasping or manipulation. Don't use for non-robot microscope, telescop…

    plugins/robotics/skills/visual-servoing/SKILL.md on GitHub (opens in a new tab)

Review before you install

A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.