Agent Skills

spritecook-animate-assets

Animation guide for SpriteCook. Use with spritecook-workflow-essentials when importing source images, writing stronger motion prompts, and animating existing assets.

Install

npx skills add https://github.com/spritecook/skills --skill spritecook-animate-assets
SKILL.md

SpriteCook Animate Assets

Use this skill for animation workflows. Pair it with spritecook-workflow-essentials for credits, manifests, safe downloads, and shared defaults.

Requires: SpriteCook MCP server connected to your editor. Set up with npx spritecook-mcp setup or see spritecook.ai.

Tool

animate_game_art

Animate an existing SpriteCook asset into a short pixel-art or detailed animation. The tool returns a job immediately; follow its poll.tool and poll.arguments instead of holding the request open.

Parameter Type Default Description
asset_id string (required) - Existing SpriteCook asset ID to animate
prompt string (required) - Describe the exact motion over time. If auto_enhance_prompt=true, simple prompts like "Idle" or "Attack" are acceptable
auto_enhance_prompt bool true Inspect the source asset and expand short prompts into a fuller animation prompt
edge_margin int 6 Adds spacing on all sides before animation framing
pixel bool null Optional mode override. If omitted, SpriteCook infers the mode from the asset
output_frames int 8 Even frame count. Pixel supports 2-16, detailed supports 2-24
output_format string "webp" "webp", "gif", or "spritesheet"
negative_prompt string null Optional motion/content exclusions
matte_color string "#808080" Hex matte color used before processing transparency
removebg string "Basic" "None", "Basic", or "Pro"
colors int 24 Pixel palette size. Only valid when pixel=true

Workflow

  1. If the user already has a SpriteCook asset, pass its asset_id directly to animate_game_art.
  2. If the user only has a local image file path, use spritecook-upload-assets to call create_asset_upload, upload the bytes, then call finalize_asset_upload.
  3. If the user supplies a small data URL or raw base64 value, call import_asset first and use the returned asset_id.
  4. Use the returned asset_id in animate_game_art.
  5. Keep pixel omitted unless you need to force a mode.

The upload/import step is where the source image enters SpriteCook. It is not the animation call itself. Use MCP asset upload tools when they are available.

Consistency Rules

  • Always animate the exact source asset that represents the intended character or object.
  • If the user asks for multiple motions for one character, run separate animation jobs against the same asset_id for Idle, Walk, Attack, and so on.
  • Do not create a new still image for each motion unless the user explicitly wants different character designs.

Source Rules

  • Pixel animation is the correct choice for assets up to 256x256.
  • Detailed animation is the correct choice for assets between 256x256 and 2048x2048.
  • Do not force a sub-256 source into detailed mode.
  • Keep edge_margin=6 by default. It helps prevent pixel art from crowding the canvas edge.

Prompt Writing

  • Inspect the actual source character before writing the prompt.
  • For pixel art, upscale the source with nearest-neighbor to about 1024x1024 for inspection only.
  • Identify visible character details first: silhouette, armor, visor, weapon, shield, pose, and facing.
  • Only mention details that are actually visible in the source image.
  • Write one short paragraph in plain prose, not a label or keyword list.
  • Describe what moves, how it moves, what stays stable, and how visible props or weapons are used.
  • Keep the motion grounded in the existing character rather than inventing new equipment or effects.
  • Avoid generic prompts like idle animation unless auto_enhance_prompt=true.

Example idle prompt: The armored soldier in purple tactical gear stands in a steady combat stance, subtly bobbing up and down in a rhythmic breathing idle. His yellow visor catches the light while his rifle shifts slightly in his grip, maintaining a high state of readiness.

Example attack prompt: The armored soldier in purple tactical gear raises his rifle and fires several shots, with yellow muzzle flashes appearing at the tip of the barrel. His body recoils with each shot while his head and visor remain focused forward, maintaining a steady combat stance throughout the firing sequence.

If auto_enhance_prompt=true, simple prompts like Idle, Attack, or Walk are valid because SpriteCook can inspect the source asset and expand them automatically.

check_job_status

Use the job_id from animate_game_art with check_job_status. On success, use asset_id plus the canonical sprite_url; use spritesheet_url only when present. If the response reports warning.code="asset_output_unavailable", execute the supplied warning.recovery tool call.

Related skills

video-editgenmedia-labs715KEdit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edit-Video (general restyle / background swap / packaging swap, identity + motion preservation), Kling 2.6 Pro Motion Control (transfer precise motion from a reference video to a target character), or Lucy Edit Restyle (lightweight identity-stable restyle / outfit swap). Bundles each model's documented prompting patterns so the skill gets shai-video-generationgenmedia-labs714KGenerate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1 qualitai-musicgenmedia-labs714KGenerate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model fimage-to-videogenmedia-labs713KAnimate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterat

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers