Agent skill · Media & Video

video2dsprite

Grok Build ONLY. Turn a 2D character still into smooth animation sprites via image_gen/image_edit base → image_to_video (6s/10s run-in-place) → ffmpeg frames → magenta chroma-key → dense sampled sprites (strip/grid/GIF). Use when the user wants video-to-sprite, motion capture from generated video, smoother run/walk cycles from dense frames, or runs /video2dsprite. Do NOT use on Codex/Claude — only Grok Build has image_to_video. Prefer generate2dsprite for crisp pixel sheets without video.

0x0funkygithub.com/0x0funkyGitHub ↗
codexclaude-codeships scriptsMIT
Install
npx skills add 0x0funky/agent-sprite-forge --skill video2dsprite --agent codex

Same command for any agent — swap --agent for claude-code, cursor, copilot.

Facts
Files in the skill folder: 5
SKILL.md size: 8 KB
Bundled scripts: yes
Path: skills/video2dsprite/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 3,616
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Video2dsprite (Grok Build only) Convert a **base 2D character image** into **dense animation sprites** using Grok Build's native video tools. ```text base still → image_to_video (in-place motion) → extract frames → chroma key → sample/normalize → strip / grid / GIF ``` ## Platform gate (read first) | Runtime | Supported? | | --- | --- | | **Grok Build** (xAI) | **Yes** — requires `image_gen` / `image_edit` + `image_to_video` (or `reference_to_video`) | | Codex / Claude / other agents | **No** — they lack Grok video tools. Tell the user this skill is Grok Build only and offer `$generate2dsprite` instead | If `image_to_video` is missing from the tool list, **stop** and explain. Do not fake motion with code-drawn frames. This skill is an **optional denser-motion path**. It does **not** replace `$generate2dsprite`: | Use `$generate2dsprite` when… | Use `$video2dsprite` when… | | --- | --- | | Crisp pixel sheets, fixed grids, identity-critical heroes | User wants denser intermediate poses / smoother feeling loops | | Attack/cast body sheets, prop packs, engine atlases | Experimenting with video-sourced run/walk/idle motion | | Production default for most game sprites | User explicitly

What's inside
Steps it walks through
  1. Platform gate (read first)
  2. Parameters
  3. Agent rules
  4. Workflow
  5. 1. Plan
  6. 2. Build the base still
  7. 3. Animate with imagetovideo
  8. 4. Extract + chroma + sample (local script)
  9. 5. QC
  10. 6. Deliver
  11. Defaults
  12. Tradeoffs (tell the user once)
  13. Resources
  14. Relationship to other skills
Ships with 4 files
  • agents/openai.yaml
  • references/pipeline.md
  • references/prompt-rules.md
  • scripts/video2dsprite.py
Commands it runs
python skills/video2dsprite/scripts/video2dsprite.py process \
python skills/video2dsprite/scripts/video2dsprite.py sample \
More from agent-sprite-forge
All skills →
About this skill
What does the video2dsprite skill do?

Grok Build ONLY. Turn a 2D character still into smooth animation sprites via image_gen/image_edit base → image_to_video (6s/10s run-in-place) → ffmpeg frames → magenta chroma-key → dense sampled sprites (strip/grid/GIF). Use when the user wants video-to-sprite, motion capture from generated video, smoother run/walk cycles from dense frames, or runs /video2dsprite. Do NOT use on Codex/Claude — only Grok Build has image_to_video. Prefer generate2dsprite for crisp pixel sheets without video.

How do I install it?

Run `npx skills add 0x0funky/agent-sprite-forge --skill video2dsprite --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From 0x0funky/agent-sprite-forge, a repository with 3,616 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going