Forgecad Verify Mujoco logo

Forgecad Verify Mujoco

Organization
ForgeCAD
forgecad-verify-mujoco

Verify a ForgeCAD MJCF export in MuJoCo with dynamics, contacts, controls, joint travel, and rendered evidence before calling it simulation-ready.

Overview

PublisherForgeCAD
Repositoryforgecad-public-kit
Skill nameforgecad-verify-mujoco
Stars
942
Forks
104
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ForgeCAD on GitHub. Read the source before you install it.

Installation

Install the Forgecad Verify Mujoco AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ForgeCAD/forgecad-public-kit/tree/mainline/skills/forgecad-verify-mujoco
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ForgeCAD/forgecad-public-kit.git /tmp/forgecad-public-kit
mkdir -p .claude/skills
cp -r /tmp/forgecad-public-kit/skills/forgecad-verify-mujoco .claude/skills/forgecad-verify-mujoco
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Forgecad Verify Mujoco in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Forgecad Verify Mujoco on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Forgecad Verify Mujoco is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Verify MuJoCo

Use this when forgecad export mjcf ... is part of the deliverable. A model is not sim-ready just because forgecad check simready passes or the MJCF file loads: it must be loaded in MuJoCo, stepped under gravity, driven with the intended controls, contact pairs inspected, and rendered from useful views.

Routing: geometry-only visual inspection -> forgecad-inspect-model; model authoring/API questions -> forgecad; building a new model -> forgecad-build-model.

Definition Of Done

  1. Export from the exact source file.
    bash
    rm -rf /tmp/forgecad-mjcf && mkdir -p /tmp/forgecad-mjcf
    forgecad export mjcf path/to/model.forge.js --output /tmp/forgecad-mjcf
  2. Load the generated scene in MuJoCo. Use scene.xml, not only the model XML, so the floor/camera/package context is included.
  3. Check the root behavior. If the model has a free root, it needs real support/contact geometry or an explicit fixed-root export path. Do not hide a floor failure by turning the whole shell into a giant bounding box that blocks moving internals.
  4. Check initial poses numerically. For mechanisms, compute the expected body/link axes from the design source and compare them to MuJoCo xmat/xpos. Joint ref/default and connector frames can disagree with visual intuition.
  5. Keep meaningful collisions. Do not mark moving functional parts Sim.collider.none(...) just to make motion pass. If full visual mesh contact is unstable, use a physically defensible simplified collider or proxy and state what physical surface it represents.
  6. Run the intended control with numeric acceptance criteria. Define the expected signed post-settle joint travel before running the test: e.g. "this drive should rotate the drum -0.04 to -0.06 cycles, then stop near zero velocity" or "this wheel should move at least +1 cycle and keep spinning". Use cycles for revolute/indexing mechanisms when that is easier to reason about, and radians for direct MuJoCo qpos checks. A controller that only jitters, moves the wrong direction, overshoots through a stop, or eventually jams after skipping the intended state is a failure even when the process exits 0.
  7. Inspect contact pairs. Contact names should match the physical story: floor/support, card/card, wheel/ground, stop/follower, etc. Contacts against a filled-in AABB, hidden fixture, or unrelated side plate usually indicate bad collider selection.
  8. Render evidence. Save initial, settled, and driven frames from views that actually show the moving parts. If the model orientation is not obvious, generate a labeled camera preview grid first, inspect it, then rerun with the azimuth/elevation that shows the functional face. Do not report GIFs/frames before visually confirming they are not from the back, underside, or an occluded side.

Helper Script

This skill ships a MuJoCo smoke verifier:

bash
uv run --python 3.11 --with mujoco --with pillow \
  python <this-skill-dir>/scripts/mujoco_verify.py /tmp/forgecad-mjcf \
  --settle-seconds 2 \
  --seconds 8 \
  --actuator drum_velocity=-0.75 \
  --watch-joint drum_joint \
  --expect-drive-cycles drum_joint=-0.06:-0.03 \
  --expect-final-qvel drum_joint=-0.02:0.02 \
  --render-dir /tmp/forgecad-mjcf/verify \
  --camera-preview-grid

Use --actuator name=value more than once for multi-actuator models. Use --expect-drive-cycles joint=min:max to assert signed final-minus-settled revolute travel in cycles/turns. Use --expect-drive-delta joint=min:max when you want raw MuJoCo qpos units instead. Use --expect-final-qvel joint=min:max to assert terminal velocity when the mechanism should stop or continue at a bounded speed. The script prints JSON with root drift, initial-to-final joint delta, post-settle drive delta, derived cycle counts, final velocities, expectation ranges, and top contact pairs, then writes PNG frames if --render-dir is supplied.

Prefer explicit travel envelopes over loose "it moved" checks:

  • Stops/latches: assert a signed drive cycle or delta range and a near-zero final velocity range.
  • Continuous drives: assert the signed drive cycle/delta is large enough over the run and final velocity remains in the expected direction/range.
  • Indexing mechanisms: assert the expected cycle step size, not just eventual stall. If the mechanism reaches a stop only after skipping several indices, treat that as failure.
  • Gravity-settling mechanisms: evaluate functional travel with post-settle drive delta, not initial-to-final delta.

When rendered orientation matters, start with --camera-preview-grid, open camera_preview_grid.png, pick the azimuth that shows the mechanism face or contact interface, then rerun with --camera-azimuth <deg> and any needed --camera-lookat, --camera-distance, or --camera-elevation adjustment. For mechanism evidence, prefer front/front-quarter views for user-facing GIFs and add a side/contact view only when it explains a collision better.

Contact Debugging Rules

  • In MuJoCo UI, enable contact visualization with Rendering -> Contact points and Contact forces; use the right-side perturb/visualization panels if available in your build.
  • If rotation is blocked, list contacts during the stall and sort by repeated pairs. The blocker is usually the pair that appears every step while the driven joint velocity trends to zero.
  • If a body falls through the floor, inspect the exported geoms. Visual geoms have contype="0" conaffinity="0" and cannot support anything; collision geoms are usually group 3.
  • Bounding boxes are fast but dangerous for hollow frames, windows, handles, and side plates. They collide as the filled AABB, not the visible object.
  • Mesh collision on complex moving parts can be too exact or solver-hostile. Prefer simple physical proxies for contact-critical moving bodies, such as a slab for a flap card or cylinders for rolling contact, but keep them colliding.

Reporting

Report the exact export command, the MuJoCo command/script, key numeric results, the most important contact pairs, and the rendered image paths. Say what was not verified. Never say "sim-ready" when only forgecad run, forgecad check simready, or a successful export was executed.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Forgecad Verify Mujoco AI skill do?

Verify a ForgeCAD MJCF export in MuJoCo with dynamics, contacts, controls, joint travel, and rendered evidence before calling it simulation-ready.

Why use Forgecad Verify Mujoco on TypingMind?

Because you install it once and use it with any model. Forgecad Verify Mujoco is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Forgecad Verify Mujoco in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ForgeCAD/forgecad-public-kit/tree/mainline/skills/forgecad-verify-mujoco. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Forgecad Verify Mujoco?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Forgecad Verify Mujoco?

As many as you like. As long as a model supports skills, you can use Forgecad Verify Mujoco with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Forgecad Verify Mujoco AI skill free?

Yes. It is published on GitHub by ForgeCAD under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇