Agent skill

Seedance 3D Cartoon

by LearnPrompt in LearnPrompt/awesome-seedance

One small anthropomorphic character carries the whole film. An agent skill from LearnPrompt/awesome-seedance.

MITAuto-check passedMedia & Creative

Install Seedance 3D Cartoon

skills CLI
$ npx skills add LearnPrompt/awesome-seedance --skill seedance-3d-cartoon -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LearnPrompt/awesome-seedance seedance-3d-cartoon --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LearnPrompt/awesome-seedance.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/skills/seedance-3d-cartoon .claude/skills/seedance-3d-cartoon && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
seedance-3d-cartoon
GitHub stars
1.9k
Token cost
~1.9k tokens
SKILL.md length
974 words
Files
2 (incl. references)
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

One small anthropomorphic character carries the whole film. An agent skill from LearnPrompt/awesome-seedance.

  • Works in 5 steps: Collect inputs. Ask only for what is… → Pick one anchor case. Read… → Fill the structure block by block. Every… → …
  • The user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (3D cartoon character short
  • SKILL.md covers Use when, Workflow, Guidance (from the cases) and Pitfalls, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Seedance 3D Cartoon is an agent skill from LearnPrompt/awesome-seedance. One small anthropomorphic character carries the whole film. Spell out its looks part by part, write the style as render settings you can measure, and cut the timeline so each block holds a single action goal. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (3D cartoon character short; 中文触发词: 3D 卡通角色短片, 3D 卡通, 皮克斯, 黏土, 卡通角色), or asks how published cases of this type were prompted. Read references/cases.md before drafting.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/cases.md`).

It sits in Media & Creative, covering AI video generation. It works with Seedance. The repository describes itself as: 🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 600+ cases traced to original posts, 260+ cross-model retest runs with public verdicts, 25 copy-ready templates, 50+… The licence is MIT.

When your agent uses it

  • The user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (3D cartoon character short
  • 中文触发词: 3D 卡通角色短片
  • Asks how published cases of this type were prompted

Example prompts

  • “/seedance-3d-cartoon”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Collect inputs. Ask only for what is missing: subject or product, setting, duration, aspect ratio, whether reference images / audio exist…
  2. Pick one anchor case. Read references/cases.md, choose the case closest to the request, and name it in the reply. One anchor, never an…
  3. Fill the structure block by block. Every block below must be present in the final prompt; an empty block is where prompts go vague.
  4. Apply the guidance and check the pitfalls (next two sections) before returning anything.
  5. Return the finished prompt as one copy-pasteable block, the anchor case link, and a three-line checklist of what to verify in the…

What it can do on your machine

Read from SKILL.md and the folder at commit 859e148. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • goodcase.ai
    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Seedance 3D Cartoon loads about 1.9k tokens when it runs, and up to ~7.1k if it reads all its reference files. Until then it costs about 119 tokens; SKILL.md has 974 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~119
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LearnPrompt/awesome-seedance at commit 859e148, republished under its MIT licence (© LearnPrompt). 974 words, ~1,872 tokens.

Download SKILL.mdSave it as .claude/skills/seedance-3d-cartoon/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
seedance-3d-cartoon
description
One small anthropomorphic character carries the whole film. Spell out its looks part by part, write the style as render settings you can measure, and cut the timeline so each block holds a single action goal. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (3D cartoon character short; 中文触发词: 3D 卡通角色短片, 3D 卡通, 皮克斯, 黏土, 卡通角色), or asks how published cases of this type were prompted. Read references/cases.md before drafting.

3D cartoon character short · 3D 卡通角色短片

One small anthropomorphic character carries the whole film. Spell out its looks part by part, write the style as render settings you can measure, and cut the timeline so each block holds a single action goal.

This Skill carries one prompt structure distilled from 29 human-verified Seedance cases on goodcase.ai. It is a sibling of seedance-prompt-library (all templates in one Skill); install this one when you only want this kind of clip. Do not invent structure from general video-generation knowledge: follow the structure below and ground the draft in one anchor case from references/cases.md.

Use when

  • Pixar-flavoured animated shorts with a cute lead: animal chefs, baby dragons, clay-textured characters that still move smoothly.
  • 中文:皮克斯味的动画短片,主角是个可爱角色:动物厨师、幼龙、黏土质感但运动平滑的小家伙。

Workflow

  1. Collect inputs. Ask only for what is missing: subject or product, setting, duration, aspect ratio, whether reference images / audio exist, and which language the final prompt should be in.
  2. Pick one anchor case. Read references/cases.md, choose the case closest to the request, and name it in the reply. One anchor, never an average of several.
  3. Fill the structure block by block. Every block below must be present in the final prompt; an empty block is where prompts go vague.
    1. Opening line that fixes the format: duration, 3D animated short, aspect ratio, overall tone
    2. Character paragraph: looks part by part, outfit, personality, then one line that holds it steady
    3. Body split by seconds or by SCENE, one location and one action goal per block
    4. Inside each block, micro-actions and expression changes that carry the emotion
    5. Visual and render paragraph: fur, depth of field, lighting, materials, bokeh
    6. Camera and mood paragraph: push-in, tracking, close-up, plus a line of mood words
    7. Exclusion list to close: appearance changes, face distortion, extra characters, flickering, text and watermark
  4. Apply the guidance and check the pitfalls (next two sections) before returning anything.
  5. Return the finished prompt as one copy-pasteable block, the anchor case link, and a three-line checklist of what to verify in the generated video.

Guidance (from the cases)

  • Write the character as a parts list, then add one line that freezes it. The frog chef spells out skin, eyes, mouth, cheeks, webbed feet and chef jacket, then follows with Keep the exact same frog appearance, outfit, proportions; the otter adventure uses Maintain the exact same character design, proportions, fur pattern.
  • Turn the style word into render settings. The sofa bunny case asks for soft realistic fluffy fur, cinematic depth of field and creamy bokeh, then adds premium Pixar-like quality without copying any specific existing character.
  • Cut the body into labelled blocks. The frog chef runs 0–5 SEC — THE RESTAURANT through 27–30 SEC — THE PAYOFF; the otter adventure uses SCENE 1 — Meadow Chase and names a place and a mood for each block.
  • Write emotion as a physical beat the model can animate. The frog chef gets He moves one tiny vegetable approximately one millimeter and His eyes narrow, and the reveal reads The hedgehog's ears shoot upward, which lands better than saying the animals are amazed.
  • Close with an exclusion list aimed at animation failures. The butterfly case ends on No character changes, face distortion, extra characters, outfit changes, flickering, deformed hands, and the ice-cream otter adds no distorted anatomy, no extra characters.
Show full SKILL.md (423 more words)Show less

Pitfalls

  • Dropping the word Pixar and stopping there. The model hands back generic CG; follow the bunny case and list fur, depth of field, lighting and bokeh one by one.
  • Locking the character only once at the top. The look drifts by the middle of the film, so re-name the identifying item at the start of every scene, like the blue scarf or the oversized chef hat.
  • Packing more scenes than the duration holds. The otter short puts nine scenes into 40 seconds, under five seconds each, so the actions only skim past. Cut scenes first and keep one action goal per block.
  • Asking for fine hand work with no guard. Moves like the frog chef placing a herb with tweezers are where extra fingers appear; put deformed hands in the exclusion list or switch to a whole-paw grab.

Language

Reply in the user's language. The prompt itself can stay in English when that is what the user's Seedance workflow expects; ask if unclear. The Chinese version of this structure follows.

中文:3D 卡通角色短片

一个拟人小角色撑起整条片子。外形逐项写死并全程复述,画风写成能测量的渲染项,时间轴切成一段一个动作目标。

结构:

  1. 开篇一句定片型:时长、3D 动画短片、画幅、整体调性
  2. 角色段:外形逐项、服装、性格,末尾加一句保持不变
  3. 正文按秒或按 SCENE 切段,每段一个地点加一个动作目标
  4. 段内写微动作和表情变化,让情绪靠动作出来
  5. 视觉与渲染段:毛发、景深、光线、材质、焦外
  6. 镜头与情绪段:推镜、跟拍、特写,再加一行 mood 词
  7. 排除清单收尾:外形变化、脸崩、多余角色、闪烁、文字水印

要点:

  • 角色写成零件清单,再补一句把它冻住。青蛙大厨那条把皮肤、眼睛、嘴、脸颊、蹼足、厨师服逐项写出来,然后跟一句 Keep the exact same frog appearance, outfit, proportions;水獭冒险那条用的是 Maintain the exact same character design, proportions, fur pattern。
  • 把风格词换成渲染项。沙发萌兔那条要的是柔软真实的绒毛、电影景深、奶油焦外,再补一句 premium Pixar-like quality without copying any specific existing character。
  • 正文切成带标题的段。青蛙大厨从 0–5 SEC — THE RESTAURANT 一路排到 27–30 SEC — THE PAYOFF;水獭冒险用的是 SCENE 1 — Meadow Chase,每段点名地点和情绪。
  • 情绪写成能动起来的身体动作。青蛙大厨那条写 He moves one tiny vegetable approximately one millimeter 和 His eyes narrow,揭晓那拍写 The hedgehog's ears shoot upward,比写一句大家很惊讶更容易落地。
  • 收尾放一份针对动画翻车的排除清单。小蝴蝶那条以 No character changes, face distortion, extra characters, outfit changes, flickering, deformed hands 收尾,冰淇淋水獭那条补的是 no distorted anatomy, no extra characters。

常见坑:

  • 只丢一个皮克斯风就收尾。模型还给你的是通用 CG,照萌兔那条把绒毛、景深、光线和焦外一项项写出来。
  • 角色只在开头锁一次。片子走到中段外形就开始漂,每个场景开头重提识别物,比如蓝围巾、过大的厨师帽。
  • 场景数量超过时长能装的。水獭那条 40 秒塞了 9 个场景,每段不到五秒,动作只能一滑而过。先砍场景,一段留一个动作目标。
  • 让角色做精细手部操作又不设防。青蛙大厨用镊子摆香草这种动作最容易长出多余手指,把 deformed hands 写进排除清单,或者改成整只爪子抓。

Copy-ready lead-in / 可复制引导语

For users who would rather paste into a chat model than run this Skill, hand them this line above the structure:

I want a 3D cartoon animated short. [The lead is a small hedgehog in a red scarf, round eyes, waddling when it walks.] [The story: on a rainy night it guides a lost firefly back home.] Using the prompt template below, rewrite it into one ready-to-use Seedance video prompt for me:

我要做一条 3D 卡通动画短片,【主角是一只戴红围巾的小刺猬,圆眼睛,走路一摇一摆】,【故事是它在雨夜给一只迷路的萤火虫带路回家】。请根据下面这个提示语模板,帮我改写成一条可以直接用的 Seedance 视频提示语:

Notes

  • references/cases.md is generated from data/ in LearnPrompt/awesome-seedance and refreshed daily; do not hand-edit an installed copy.
  • Prompts in the reference file belong to their creators (linked on every card). Transfer the structure; do not present a close copy as original work.
  • For the full library across every model, install the goodcase Skill from LearnPrompt/goodcase-lite.

© LearnPrompt, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in agents/skills/seedance-3d-cartoon of LearnPrompt/awesome-seedance.

  • SKILL.md
  • references/cases.md

Open the folder on GitHubat commit 859e148

Compare with similar skills

Seedance 3D Cartoon next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Seedance 3D Cartoon compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Seedance 3D Cartoon this skillLearnPrompt/awesome-seedance1.9k—~1.9kAutomated safety check: PassMIT
Seedancesongguoxs/seedance-prompt-skill2.9k1 repos~2.5kAutomated safety check: PassNone
SN Motion HTMLOpenSenseNova/SenseNova-Skills5.7k—~2.2kAutomated safety check: NotesMIT
Seedance Prompt Endexhunter/seedance2-skill4.2k—~3.8kAutomated safety check: PassMIT
Seedance Japanese Prompt ExamplesEmily2040/seedance-2.07.6k1 repos~898Automated safety check: PassMIT
Seedance 2 5 Video Directorliyue-aigc/seedance-2-5-video-director599—~3.5kAutomated safety check: PassMIT

Similar skills

  • Seedance

    songguoxs/seedance-prompt-skill

    This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成"…

    2.9k GitHub starsUsed in 1 repo~2.5k tokens
    Media & CreativeAuto-check passed
  • SN Motion HTML

    OpenSenseNova/SenseNova-Skills

    Builds HTML stories where one continuous camera journey advances with page progress, using researched structure, AI stills, Seedance video clips and browser QA.

    5.7k GitHub stars~2.2k tokensUpdated 2 days ago
    Media & CreativeAuto-check: notes
  • Seedance Prompt En

    dexhunter/seedance2-skill

    Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation.

    4.2k GitHub stars~3.8k tokensUpdated 21 days ago
    Media & CreativeAuto-check passed
  • Seedance Japanese Prompt Examples

    Emily2040/seedance-2.0

    Provides Japanese prompt patterns and safe example rewrites for Seedance 2.0 video generation, with reference tags kept intact and each example labeled by risk.

    7.6k GitHub starsUsed in 1 repo~898 tokens
    Media & CreativeAuto-check passed
  • Seedance 2 5 Video Director

    liyue-aigc/seedance-2-5-video-director

    Design, derive, optimize, diagnose, and rewrite scripts or copy-ready prompts specifically for Dreamina/即梦 Seedance 2.5.

    599 GitHub stars~3.5k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Seedance Prompt Zh

    dexhunter/seedance2-skill

    为即梦 Seedance 2.0 多模态AI视频生成模型撰写高质量提示词。当用户需要使用文本、图片、视频、音频等多模态输入创作视频提示词时触发。涵盖@引用语法、运镜复刻、特效模仿、视频延长、视频编辑、音乐卡点、电商广告、短剧创作、科普教育等场景。

    4.2k GitHub stars~1.9k tokensUpdated 21 days ago
    Media & CreativeAuto-check passed

More from LearnPrompt/awesome-seedance

All 15 skills in this repo
  • Seedance Production Workflow

    LearnPrompt/awesome-seedance

    Plan and carry a Seedance video from brief through references, storyboard, generation handoff, shot-level review, and targeted repair.

    1.9k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Seedance Car Vehicle

    LearnPrompt/awesome-seedance

    The machine has to stay one machine while the camera does all the work.

    1.9k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Seedance Epic Fantasy Scifi

    LearnPrompt/awesome-seedance

    Monsters, dragons, world reveals. An agent skill from LearnPrompt/awesome-seedance.

    1.9k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Seedance Fashion Lookbook

    LearnPrompt/awesome-seedance

    One person, one look, a handful of places. An agent skill from LearnPrompt/awesome-seedance.

    1.9k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Seedance Food Asmr

    LearnPrompt/awesome-seedance

    Cooking close-ups, mukbang and eating vlogs. An agent skill from LearnPrompt/awesome-seedance.

    1.9k GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Seedance Game UI Livestream

    LearnPrompt/awesome-seedance

    The screen itself is the shot: a fake gameplay capture, livestream or desktop recording.

    1.9k GitHub stars~2.1k tokensUpdated today
    Auto-check passed

Works with

Questions about Seedance 3D Cartoon

What does Seedance 3D Cartoon do?

One small anthropomorphic character carries the whole film. An agent skill from LearnPrompt/awesome-seedance. Seedance 3D Cartoon is an agent skill from LearnPrompt/awesome-seedance. One small anthropomorphic character carries the whole film.

When should I use Seedance 3D Cartoon?

Seedance 3D Cartoon fits situations like: the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (3D cartoon character short; 中文触发词: 3D 卡通角色短片; asks how published cases of this type were prompted.

How do I install Seedance 3D Cartoon in Claude Code?

Run `npx skills add LearnPrompt/awesome-seedance --skill seedance-3d-cartoon -a claude-code`. Or copy the skill folder (agents/skills/seedance-3d-cartoon in LearnPrompt/awesome-seedance) into .claude/skills/seedance-3d-cartoon in your project. Claude Code loads it when a task matches its description.

How do I install Seedance 3D Cartoon in Codex?

Run `npx skills add LearnPrompt/awesome-seedance --skill seedance-3d-cartoon -a codex`. Or copy the skill folder (agents/skills/seedance-3d-cartoon in LearnPrompt/awesome-seedance) into .agents/skills/seedance-3d-cartoon in your project. Codex loads it when a task matches its description.

Can I use Seedance 3D Cartoon in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LearnPrompt/awesome-seedance --skill seedance-3d-cartoon -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/seedance-3d-cartoon, .gemini/skills/seedance-3d-cartoon, .github/skills/seedance-3d-cartoon and .opencode/skills/seedance-3d-cartoon in your project.

What does Seedance 3D Cartoon need to run?

SKILL.md names no scripts, command-line tools or credentials: Seedance 3D Cartoon is instructions for the agent only.

Does Seedance 3D Cartoon access the network?

SKILL.md names 2 domains. As links in the text: goodcase.ai and github.com. This is read from the text; nothing was executed.

Is Seedance 3D Cartoon safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Seedance 3D Cartoon use?

Seedance 3D Cartoon is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Seedance 3D Cartoon use?

About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.2k tokens, read only when the agent opens those files.

What are the alternatives to Seedance 3D Cartoon?

Skills that share tags, products or a category with Seedance 3D Cartoon: Seedance (songguoxs/seedance-prompt-skill, 2.9k stars), SN Motion HTML (OpenSenseNova/SenseNova-Skills, 5.7k stars), Seedance Prompt En (dexhunter/seedance2-skill, 4.2k stars) and Seedance Japanese Prompt Examples (Emily2040/seedance-2.0, 7.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Seedance 3D Cartoon?

LearnPrompt (a GitHub user) maintains it in LearnPrompt/awesome-seedance, which has 1,947 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 11, 2026.

Source: LearnPrompt/awesome-seedance on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.