Generate Motion logo

Generate Motion

Organization
SummerEngine
generate-motion

Attach a library animation clip (idle, walk, run, attack) to a rigged character via AnimationPlayer.

Overview

PublisherSummerEngine
Repositorysummer
Skill namegenerate-motion
Stars
91
Forks
8
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 SummerEngine on GitHub. Read the source before you install it.

Installation

Install the Generate Motion 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/SummerEngine/summer/tree/main/library/skills/generate-motion
  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/SummerEngine/summer.git /tmp/summer
mkdir -p .claude/skills
cp -r /tmp/summer/library/skills/generate-motion .claude/skills/generate-motion
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Generate Motion 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 Generate Motion 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 Generate Motion 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.

Generate Motion — Curated Meshy Library

Picks a clip from a curated mocap library by name and wires it onto a Meshy-rigged humanoid. Fast (~30s), and it looks good because it is real mocap. The five short aliases that always work are idle, walk, run, jump, attack; anything else must be an exact library name — see the Reference card before you invent one.

The target must be a Meshy-rigged humanoid — a rigAssetId from a prior assets.generate_3d({ kind: "image-to-3d", imageUrl: "...", rig: true }) call. The finished job's result includes rigAssetId. If the user points at a non-rigged mesh, stop and route to asset-strategy (or directly call assets.generate_3d with rig: true) before generating motion.

Custom or non-humanoid motion (e.g. "drops to one knee, draws bow", a nodding flower, a creature) goes to the text-to-motion skill (backend: "text-to-motion") when the server has it enabled; otherwise fall back to hand-authoring in Summer Engine or importing from Mixamo.

When to use this skill

  • "Add a walk animation to the goblin."
  • "I need an idle, a run, and an attack on this character."
  • "Death animation for the enemy when HP hits zero."
  • The user has a rigged character and zero animations on it.

When NOT to use this skill

  • The user wants to apply an existing animation to a new model — use retarget instead. Don't regenerate.
  • The user wants state-machine wiring (idle → walk → run blend) — generate the clips here, then hand off to animation-tree.
  • The user wants facial / lipsync animation — that's facial-and-lipsync.
  • The mesh isn't rigged. Rig first; never call assets.generate_motion on a static .glb.
  • The user wants procedural look-at, IK, foot placement — that's procedural-animation.
  • The user described a custom signature move that isn't on the curated list — use text-to-motion; if the server answers backend_unavailable, use the manual-authoring fallback below.

Steps

1. Verify the target is a rigged humanoid

assets.search({ query: "<character name>", assetType: "3d_model", scope: "mine" })

The rigged model's assetId is its rigAssetId (the id the rig job's result named rigAssetId). Search results do not say whether a model is rigged: the dry run in step 2 checks it, and a model that is not rigged is refused there with invalid_input on rigAssetId. Then stop, propose assets.generate_3d({ kind: "image-to-3d", imageUrl: "...", rig: true }) first (the finished job's result includes rigAssetId), or route to asset-strategy.

2. Confirm with the user before spending

I'm about to generate a "run" animation on goblin_rigged via meshy-library — about 30s, and it uses credits. OK?

dryRun: true on the call below returns the credits (estimate) and checks the rig is the person's and rigged; clips the rig already has cost nothing, so the estimate is the most it can cost.

3. Call the operation

assets.generate_motion({
  rigAssetId: "<id>",
  backend: "meshy-library",   // curated library (default)
  motionNames: ["run"]        // exact names from the curated list — see Reference card
})
jobs.wait({ jobId: "<job.id>", timeoutSeconds: 50 })   // again until finished

assets.generate_motion answers at once with a job; jobs.wait follows it until finished is true, and the finished job's result has animationAssetId in it. When the rig already has every clip asked for, the answer is done at once with reused (nothing new was made or charged). Don't assume any other field is present — resolve the asset to get stable file/download metadata:

assets.get({ assetId: "<animationAssetId>" })

4. Attach to the character's AnimationPlayer

summer_inspect_node(path="./World/Goblin")        // confirm it has an AnimationPlayer child
summer_add_node(scenePath="res://main.tscn", parent="./World/Goblin", type="AnimationPlayer", name="AnimationPlayer")  // only if missing
summer_set_resource_property(
  scenePath="res://main.tscn",
  nodePath="./World/Goblin/AnimationPlayer",
  resourceProperty="libraries/default",
  subProperty="<motion_name>",
  value="<animationAssetId>"
)
summer_save_scene(scenePath="res://main.tscn")

scenePath is required on summer_add_node, summer_set_resource_property and summer_save_scene. summer_inspect_node takes only path — it has no scenePath and reads the currently-edited scene.

If the character will use multiple clips, leave the AnimationPlayer in place — every subsequent generation appends to the same library. State-machine wiring belongs to animation-tree, not here.

Confirmation gates

  • Before generation: state the motion name and that it uses credits. Wait for OK.
  • Before attaching: state which AnimationPlayer and which library slot. Wait for OK.
  • After generation: if the user hasn't seen the preview, link previewUrl and ask "land or regenerate?" before wiring it into the scene.

Reference card

Curated motion library — what motionNames actually accepts

There are five short canonical aliases, and only five:

idle, walk, run, jump, attack

Everything else must be an exact raw Meshy library name (or its display name, or its numeric action id 0–696). The library is 678 entries, and its naming is nothing like a tidy snake_case scheme — real names look like Walking_Woman, Jump_Run, Run_02, Hit_Reaction, Roll_Dodge, Block1, Dead, Stand_Dodge, Triple_Combo_Attack, Wave_One_Hand, Chair_Sit_Idle_F, Lean_Forward_Sprint.

Plausible-looking names that do not resolve, verified against the resolver: attack_sword, hit_react, death, sprint, block, dodge_left, crouch_idle, walk_back, run_strafe_left, jump_land, idle_combat, wave, dance, sit_idle. They resolve to nothing and the call errors. For a sword attack, use attack.

So: if the user asks for something outside the five aliases, do not guess a snake_case name. Either use one of the five, quote an exact raw library name you have actually seen, or route to the manual-authoring fallback.

Pitfalls

  • Invented motionNames entries fail. "run_fast", "attack_sword", "death" all resolve to nothing and the call errors. Name resolution is exact — five aliases, or a real library name / display name / numeric id. Do not extrapolate a naming scheme.
  • Locomotion clips have a forward bias. Meshy's run translates the root forward by ~5m. Either the code drives movement (then the baked root translation causes a lunge-and-snap every loop — strip it) or the clip does via root_motion_track + get_root_motion_position() — never both. The full root-motion setup and its playtest verification live in character-animation-wiring.
  • Rig pose mismatch. If your rig was rigged with a non-T-pose reference image, the limbs may bend wrong. Re-rig from a T-pose mannequin (see asset-strategy) before re-generating.
  • Rig still preparing. New rigs need ~3 minutes after the rig job completes before the animation library is ready. Called too early, assets.generate_motion answers in_progress with retry: "after" and details.retryAfterSeconds (about 180). Wait and retry.

Anti-patterns

  • Calling assets.generate_motion on a .glb that wasn't rigged — the call is refused; a dry run says so first.
  • Generating the same clip twice because you forgot to save the animationAssetId from the first call. Search the asset library first: assets.search({ query: "goblin run", assetType: "animation", scope: "mine" }).
  • Wiring clips into an AnimationTree inside this skill. That's the next skill's job. Generate, attach, hand off.
  • Asking the model to invent a motion name that isn't on the list. Quote from the list verbatim, or fall back to manual authoring.

Edge cases

  • Custom signature move (e.g. "drops to one knee, draws bow"). The custom prompt-driven route is text-to-motion. If it is unavailable, workarounds: hand-author the clip in Summer Engine's animation panel, import a licensed clip as an AnimationLibrary, or compose curated clips in an AnimationTree OneShot blend.
  • Quadruped rig. Meshy library is humanoid-only. For quadrupeds and other non-humanoid rigs use text-to-motion, or hand-author / import an external library.
  • Character is < 1m tall (child / dwarf). Library clips assume a ~1.8m humanoid. Apply the clip; the proportions retarget but stride length looks long. Either accept it or tune playback_speed on the AnimationPlayer track.
  • Character has wings / tail. The library ignores the extra bones — they sag. Hand-author additive overlays for the extra bones, or accept the visual hit.

Without Summer Engine

In a session without Summer Engine tools (the assets profile; the summer-assets skill has the whole loop), do steps 1-3 and skip step 4 (the AnimationPlayer). Save the clip where the person asked with out on jobs.wait (the summer-assets skill says how), and tell them the path and format.

Fallback (no MCP)

The user can upload to Meshy directly at meshy.ai, generate through the dashboard, download .glb, and import it as an AnimationLibrary in Summer Engine.

Handoff

  • After generating locomotion clips, suggest character-animation-wiring — the end-to-end wiring path (inspect what landed, idle/walk/run state machine with blend times, footstep method tracks, root motion, playtest proof). For blend spaces and attack/hit overlays on top, animation-tree.
  • After generating a one-shot (death, hit-react), suggest design-npc to fire it from the behavior state machine.
  • For first-person hand animations on a player, use this skill on a hands-only rig and then fps-controller for the wiring.
  • If the user wants to apply these clips to a second character, hand off to retarget.

See also

  • asset-strategy — how to get a Meshy-rigged character in the first place.
  • animation-tree — wire the generated clips into a state machine.
  • retarget — re-use one library across many characters without regenerating.

From a shell

No Summer MCP tools in this session? Run each one as a command; when summer --version is missing or below 4.0, use npx -y summer-engine@latest in place of summer. Fields are flags in kebab-case (--scene-path res://main.tscn) or one --input '<json>', and summer ops describe <op> prints the exact input. The summer-cli skill has the rest.

In this skillCommand
assets.generate_3dsummer assets generate-3d
assets.generate_motion, summer_assets_generate_motionsummer assets generate-motion
summer_assets_getsummer assets get
assets.search, summer_assets_searchsummer assets search
summer_add_nodesummer engine add-node
summer_get_scene_treesummer engine get-scene-tree
summer_inspect_nodesummer engine inspect-node
summer_inspect_resourcesummer engine inspect-resource
summer_save_scenesummer engine save-scene
summer_set_propsummer engine set-prop
summer_set_resource_propertysummer engine set-resource-property
jobs.wait, summer_jobs_waitsummer jobs wait

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 Generate Motion AI skill do?

Attach a library animation clip (idle, walk, run, attack) to a rigged character via AnimationPlayer.

Why use Generate Motion on TypingMind?

Because you install it once and use it with any model. Generate Motion 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 Generate Motion in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SummerEngine/summer/tree/main/library/skills/generate-motion. 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 Generate Motion?

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 Generate Motion?

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

Is the Generate Motion AI skill free?

Yes. It is published on GitHub by SummerEngine 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 👇