anymove — Claude Code skill: what it does, how to install
anymove is a Claude Code skill that orchestrates creature motion capture from AI video. Runs when animating dragons, wolves, or monsters and routes through each step of the pipeline.
Apache-2.0 ★ 653 updated 2026-11-13
/plugin marketplace add patch-gg/anymove
/plugin install anymove@anymoveWhat anymove does
The skill guides the capture pipeline from mesh preparation to the final GLB export. An AI model renders the rigged creature from front and side orthographic views within a single frame. A DINOv2 model trained on the creature detects joints across both perspectives, locking 3D positions along the shared vertical axis.
Hardware requirements include an NVIDIA GPU with CUDA (at least 12 GB VRAM, with 24 GB recommended), Blender 5.x, and Python 3.11. Generating video clips via MiniMax H3 Max requires a FAL_KEY token. The pipeline handles large isolated gestures; it does not support bird wings, lying down, or eight-legged locomotion.
What it helps with
- animate non-human creatures from generated AI video clips
- track creature joints across two camera views using DINOv2
- fit forward kinematics rigs and export animated GLB files
- route the next stage between rigging, filming, tracking, and packing
Example prompts for the agent
- How do I animate a dragon using the anymove pipeline?
- What step comes after anymove-reader for the wolf model?
- Solve the motion keyframes from the captured clip into a GLB
How to install anymove
1Plugin marketplace
/plugin marketplace add patch-gg/anymove/plugin install anymove@anymoveThis installs the whole anymove plugin with all its skills
2Skills CLI (Vercel)
npx skills add patch-gg/anymove --skill anymove -a claude-code3Manually: put the files in place
~/.claude/skills/anymove/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/anymove/
1Skills CLI (Vercel)
npx skills add patch-gg/anymove --skill anymove -a codex2Manually: put the files in place
.agents/skills/anymove/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add patch-gg/anymove --skill anymove -a cursor2Manually: put the files in place
.cursor/skills/anymove/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install patch-gg/anymove skills/anymove2Manually: put the files in place
.github/skills/anymove/SKILL.md1Skills CLI (Vercel)
npx skills add patch-gg/anymove --skill anymove -a gemini-cli2Platform CLI
gemini skills install https://github.com/patch-gg/anymove --path skills/anymoveManually: put the files in place
.devin/skills/anymove/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about anymove
How to install anymove in Claude Code?
Add the marketplace via /plugin marketplace add patch-gg/anymove, then install the skill with /plugin install anymove@anymove.
What does anymove do?
It routes creature motion capture across dedicated steps, converting dual-angle AI video frames into fitted 3D skeletal movements.
What is required to run anymove?
You need an NVIDIA GPU with CUDA and at least 12 GB VRAM, Blender 5.x, Python 3.11, and a valid fal.ai API key for video generation.
Source text
SKILL.md · Apache-2.0
--- name: anymove description: Motion capture for any creature from one AI video, with the anymove repo. A video model films a rigged 3D creature from two cameras in one frame, a DINOv2 joint reader trained on that creature finds every joint in both views, and the rig is fitted to them and exported as a GLB. Use when someone wants to animate a non-human creature (dragon, spider, wolf, monster) from a text prompt or an AI video, asks how anymove works, or needs to know which step comes next; it routes to anymove-rig, anymove-film, anymove-reader, anymove-capture, anymove-pack and anymove-lora. license: Apache-2.0 compatibility: Needs an NVIDIA GPU with CUDA (12 GB to train a reader, 24 GB is safer), Blender 5.x, Python 3.11, and a fal.ai key for video generation. Runs on Linux and on Windows in Git Bash. --- # anymove Animate any rigged creature from one AI video. The trick is the frame: one image holds two orthographic views of the creature at the same scale, front on the left and side on the right, sharing the vertical axis. A joint sits on the same pixel row in both halves, so the front view gives left-right and height, the side view gives front-back and height, and together they pin the joint in 3D. The method is @CanItCode's; the LoRA step is @Graalitoo's idea. ## The pipeline | step | once per | what happens | skill | |---|---|---|---| | 1. mesh | creature | a textured 3D model (Tripo H3.1 from one image, or your own GLB), facing -Y, real size | anymove-rig | | 2. skeleton | creature | joints placed in `assets/<c>/rig.json`, rig built and skinned in Blender | anymove-rig | | 3. limb colours | creature | each limb painted its own colour so left and right never swap | anymove-rig | | 4. two cameras | move | the painted reference frame plus a strict prompt go to MiniMax H3 Max on fal | anymove-film | | 5. teach a reader | creature | 2,200 random poses rendered with known joints; DINOv2 learns this creature | anymove-reader | | 6. read every joint | clip | the reader finds every joint in both views, every frame | anymove-capture | | 7. two views, 3D | clip | shared heights tie the views; the pair gives each joint in 3D | anymove-capture | | 8. the rig follows | clip | forward kinematics in torch fitted to both views; GLB out | anymove-capture | | 9. the pack | creature | score the takes, keep the best, cut loops and root motion; one GLB with every move | anymove-pack | | optional | creature | a MiniMax H3 LoRA that keeps the two-camera layout and colours more reliably | anymove-lora | ## Before anything 0. **Check it's the right tool.** If the person only wants a creature, look in Patch's Assets first: nine are ready. anymove suits big single gestures, and doesn't do eight-legged walking, lying down, bird wings or tail swipes (see the README). Check there's an NVIDIA card before anything else; without one, stop and say so. 1. Work in an anymove checkout. If the working directory has no `tools/capture.sh`, clone it: `git clone https://github.com/Patch-gg/anymove && cd anymove`. 2. Set up once: `python3.11 -m venv .venv`, then `.venv/bin/pip install torch==2.11.0 --index-url https://download.pytorch.org/whl/cu128` and `.venv/bin/pip install -r requirements.txt`. Blender 5.x must be on PATH, or set `BLENDER=/path/to/blender`. **On Windows,** run everything in Git Bash, use `py -3.11 -m venv .venv` and `.venv/Scripts/` where these say `.venv/bin/`, and set `BLENDER`. `tools/*.sh` handle the rest. If you call Blender yourself rather than through them, give it absolute paths: on Windows it reads a relative output path from the drive root. 3. For video generation and LoRA training, put `FAL_KEY=...` in `.env` (git ignores it) or export it. Never print it. 4. Every command takes a creature name; its config is `assets/<c>/creature.json` and every output lands in `runs/<c>/` (reference frame, dataset, `reader.pt`, videos, clips). The scripts set `MOCAP_CREATURE` for you; when you run a `python -m mocap...` module by hand, set `MOCAP_CREATURE=assets/<c>` first, or the wolf's layout applies. ## Which step next - No `assets/<c>/model.glb`: make or fetch the mesh. Examples: `tools/fetch_examples.sh <c>` (wolf, dragon, spider, demon). New creature: anymove-rig. - No `assets/<c>/rigged/rigged.blend` or `runs/<c>/ref/ref.png`: `tools/prep.sh <c>` then `tools/rig.sh <c>` (anymove-rig). - No `runs/<c>/reader.pt`: anymove-reader (about 45 min on one RTX 4090), or `tools/fetch_examples.sh <c> --readers`. - No clip for the move: anymove-film (about $0.26 a 5 s clip, and about 7 clips for a usable move). - A clip: anymove-capture, `tools/capture.sh <c> <video.mp4> <name>`. - Several good takes: anymove-pack, `tools/pack.sh <c>`. - The pack is in a game that runs: offer to publish it on Patch (anymove-pack, last section). - Clips keep swapping limb colours or the halves drift apart: anymove-lora. ## Try it without a GPU The repo carries the dragon's roar as read by its reader. Fit it on the CPU in about a minute and a half: ```bash mkdir -p runs/dragon/clips/roar MOCAP_CREATURE=assets/dragon .venv/bin/python -m mocap.solve examples/dragon_roar/det.npz \ assets/dragon/rigged/rig_info.json runs/dragon/clips/roar/motion.json ``` It prints the paw agreement (about 0.93) and the reprojection error per view; `motion.json` holds the keyframes. ## Costs and time (October 2026, one RTX 4090) **Quote the all-in numbers, not the price of one clip:** about $3 for a usable move, and about $17 and a couple of hours for a new creature with about 5 moves (about $11 of AI services on the person's own card). A move took about 7 clips on average ($1.80), and 58% of captured clips passed the checks. - Tripo H3.1 mesh with HD texture: $0.40. MiniMax H3 Max clip: about $0.26 for 5 s (H3: $0.30). - Dataset and reader training: about 75 min on one RTX 4090. Reading a clip: about 12 s. Fitting: about 45 s. GLB and renders: about 3 min. - A LoRA: $0.01 a training step, so 1,200 steps cost about $12 and take about 2 h on fal. Say what a step will cost before calling fal, and confirm with the person before spending on a batch.
© Patch · Apache-2.0 · patch-gg/anymove