Skip to main content
Agent skill

Sprite Animation

A pixel / sprite-style animated explainer slide — full-bleed cream stage, bold display year, animated pixel-art mascot (e.g. Hanafuda card, mushroom, or 8-bit console), kinetic Japanese display type, ticking timeline ribbon. Reads like a single frame of an educational motion video — looping CSS keyframes, no JS, ready to be screen-recorded into a vertical video. Use when the brief asks for a "sprite animation", "pixel-art video", "8-bit explainer", "history of X explainer", "kinetic typography history", "Nintendo-style", "精灵图动画", "像素动画", or "复古动画".

Get started

Get the complete skill folder, including its scripts and reference files.

When to use this skill

Use Sprite Animation when an AI agent needs a reusable SKILL.md workflow for this job: A pixel / sprite-style animated explainer slide — full-bleed cream stage, bold display year, animated pixel-art mascot (e.g. Hanafuda card, mushroom, or 8-bit console), kinetic Japanese display type, ticking timeline ribbon. Reads like a single frame of an educational motion video — looping CSS keyframes, no JS, ready to be screen-recorded into a vertical video. Use when the brief asks for a "sprite animation", "pixel-art video", "8-bit explainer", "history of X explainer", "kinetic typography history", "Nintendo-style", "精灵图动画", "像素动画", or "复古动画".

When not to use it

Skip Sprite Animation when the task is outside the creativity category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/sprite-animation
# Save SKILL.md to ~/.claude/skills/sprite-animation/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/sprite-animation/SKILL.md. For a shared project, commit the folder at .claude/skills/sprite-animation/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Sprite Animation skill for this task: Read the active DESIGN.md (injected above). Pick the loudest serif. Confirm any required inputs or files before making changes.

What supports this recommendation?

74/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
82/100
Practical detail
74/100
Source evidence
63/100
Source signals
72/100
Model compatibility evidence
  • claudeuntested

    No model-specific signal or recorded compatibility test was found.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# Sprite Animation Skill

Produce a single animated frame of an educational explainer — the kind you might screen-record into a vertical video. Pixel-art mascots, big year display, looping CSS animations, kinetic Japanese / English display type.

## Workflow

1. **Read the active DESIGN.md** (injected above). Pick the loudest serif token for the year, a sturdy sans for headlines, and a mono token for timeline / index labels. 2. **Pick the topic** from the brief (e.g. "Nintendo · 1889 — Hanafuda"). You always need: a year, a one-line headline, an animated subject (a pixel sprite — character, object, or icon), and a short caption. 3. **Stage** — full-bleed cream / off-white background (`#f5efe2`) with a subtle paper grain. Keep margins generous; this is one beat of a video. 4. **Top bar** — small mono row: - Left: title slug ("名次の/番組" or "EP. 01 / NINTENDO") - Right: progress dots ("01 / 12") and a "REC" stamp 5. **Subject animations** — at least three independent looping animations on the page: - **Big year**: the headline year (e.g. "1889年") fills the lower-left, in a serif display weight. It has a subtle vertical glitch / scanline animation (clip-path keyframes), and a 1-frame "pop" every loop. - **Pixel sprite card**: a 96×128 pixel-art card or character (use an inline SVG with crisp `shape-rendering: crispEdges` rectangles, or a `box-shadow` pixel grid). Subtle bobbing animation (±4px, 1.6s). - **Kinetic kana**: 1–2 Japanese / kanji characters that fade-and-slide in sync with the bob (e.g. "花" — *hana* — flower). - **Tick ribbon**: bottom of the stage, a tape/ribbon with year ticks (1889 · 1907 · 1949 · 1977 · 1985 · 2006 · 2017) sliding left at a slow constant speed. 6. **Caption block** — small mono caption explaining the trivia: "Nintendo started as a Hanafuda playing-card maker in Kyoto, 1889. Mario didn't show up for another ninety-six years." 7. **Write** a single HTML document: - `<!doctype html>` through `</html>`, CSS inline, no external JS. - All animations use `@keyframes` + `animation: ... infinite`. - Stage uses a fixed canvas ratio (e.g. 16:9 letterboxed) so the loop reads as a single frame from a video. - `data-od-id` on stage, year, sprite, caption, and tick ribbon. 8. **Self-check**: - The page is one cohesive scene, not a collage. The eye lands on the year first, then the sprite, then the caption. - At least 3 independent looping animations are visible. - The color palette is restrained (cream + a single accent red + ink). - No external assets — all sprites are inline SVG or CSS.

## Output contract

Emit between `<artifact>` tags:

``` <artifact identifier="sprite-anim-slug" type="text/html" title="Sprite animation — Title"> <!doctype html> <html>...</html> </artifact> ```

One sentence before the artifact, nothing after.

Intended uses

  • Read the active DESIGN.md (injected above). Pick the loudest serif
  • Pick the topic from the brief (e.g. "Nintendo · 1889 — Hanafuda").
  • Stage — full-bleed cream / off-white background (#f5efe2) with a
  • Top bar — small mono row:
  • Left: title slug ("名次の/番組" or "EP. 01 / NINTENDO")
  • Right: progress dots ("01 / 12") and a "REC" stamp
  • Subject animations — at least three independent looping animations
  • Big year: the headline year (e.g. "1889年") fills the lower-left,
  • Pixel sprite card: a 96×128 pixel-art card or character (use an
  • Kinetic kana: 1–2 Japanese / kanji characters that fade-and-slide
  • Tick ribbon: bottom of the stage, a tape/ribbon with year ticks
  • Caption block — small mono caption explaining the trivia:
  • Write a single HTML document:
  • <!doctype html> through </html>, CSS inline, no external JS.
  • All animations use @keyframes + animation: ... infinite.
  • Stage uses a fixed canvas ratio (e.g. 16:9 letterboxed) so the loop
  • data-od-id on stage, year, sprite, caption, and tick ribbon.
  • Self-check:
  • The page is one cohesive scene, not a collage. The eye lands on the
  • At least 3 independent looping animations are visible.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.