SVG Character Animation
calesthio/OpenMontage
Animate SVG character rigs with GSAP, CSS transforms, Remotion frame control, and HyperFrames-compatible browser previews.
Generate original fluffy, poofy 3D animation characters in a cohesive collectible-avatar family: monolithic plush body, inset smooth face, tiny limbs, restrained expression, tactile materials…
MITAuto-check passed
Install Fluffy Poofy 3D Characters
$ npx skills add agentara/skills --skill fluffy-poofy-3d-characters -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agentara/skills fluffy-poofy-3d-characters --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/aigc/fluffy-poofy-3d-characters .claude/skills/fluffy-poofy-3d-characters && rm -rf skills-srcUse ~/.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/
Install the "fluffy-poofy-3d-characters" agent skill from https://github.com/agentara/skills/tree/main/skills/aigc/fluffy-poofy-3d-characters into .claude/skills/fluffy-poofy-3d-characters/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fluffy-poofy-3d-characters", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/agentara/skills/tree/main/skills/aigc/fluffy-poofy-3d-charactersType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add agentara/skills --skill fluffy-poofy-3d-characters -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agentara/skills fluffy-poofy-3d-characters --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/aigc/fluffy-poofy-3d-characters .agents/skills/fluffy-poofy-3d-characters && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fluffy-poofy-3d-characters" agent skill from https://github.com/agentara/skills/tree/main/skills/aigc/fluffy-poofy-3d-characters into .agents/skills/fluffy-poofy-3d-characters/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fluffy-poofy-3d-characters", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agentara/skills --skill fluffy-poofy-3d-characters -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agentara/skills fluffy-poofy-3d-characters --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/aigc/fluffy-poofy-3d-characters .cursor/skills/fluffy-poofy-3d-characters && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "fluffy-poofy-3d-characters" agent skill from https://github.com/agentara/skills/tree/main/skills/aigc/fluffy-poofy-3d-characters into .cursor/skills/fluffy-poofy-3d-characters/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fluffy-poofy-3d-characters", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/agentara/skills.git --path skills/aigc/fluffy-poofy-3d-characters--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add agentara/skills --skill fluffy-poofy-3d-characters -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agentara/skills fluffy-poofy-3d-characters --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/aigc/fluffy-poofy-3d-characters .gemini/skills/fluffy-poofy-3d-characters && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "fluffy-poofy-3d-characters" agent skill from https://github.com/agentara/skills/tree/main/skills/aigc/fluffy-poofy-3d-characters into .gemini/skills/fluffy-poofy-3d-characters/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fluffy-poofy-3d-characters", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install agentara/skills fluffy-poofy-3d-charactersInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add agentara/skills --skill fluffy-poofy-3d-characters -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/aigc/fluffy-poofy-3d-characters .github/skills/fluffy-poofy-3d-characters && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "fluffy-poofy-3d-characters" agent skill from https://github.com/agentara/skills/tree/main/skills/aigc/fluffy-poofy-3d-characters into .github/skills/fluffy-poofy-3d-characters/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fluffy-poofy-3d-characters", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agentara/skills --skill fluffy-poofy-3d-characters -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agentara/skills fluffy-poofy-3d-characters --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentara/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/aigc/fluffy-poofy-3d-characters .opencode/skills/fluffy-poofy-3d-characters && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "fluffy-poofy-3d-characters" agent skill from https://github.com/agentara/skills/tree/main/skills/aigc/fluffy-poofy-3d-characters into .opencode/skills/fluffy-poofy-3d-characters/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fluffy-poofy-3d-characters", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
fluffy-poofy-3d-characters- GitHub stars
- 603
- Token cost
- ~1.5k tokens
- SKILL.md length
- 772 words
- Files
- 4 (incl. assets)
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- MIT
At a glance
Generate original fluffy, poofy 3D animation characters in a cohesive collectible-avatar family: monolithic plush body, inset smooth face, tiny limbs, restrained expression, tactile materials…
- Works in 6 steps: Silhouette → Face Architecture → Material Contrast → …
- SKILL.md covers Core Design Language, Variation Rules, Generation Workflow and Default Prompt Block, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Fluffy Poofy 3D Characters is an agent skill from agentara/skills. Generate original fluffy, poofy 3D animation characters in a cohesive collectible-avatar family: monolithic plush body, inset smooth face, tiny limbs, restrained expression, tactile materials, strong silhouettes, and high variation without losing the shared design language.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including assets.
The repository describes itself as: Original and practical skills for AI builders. The licence is MIT.
Example prompts
- “/fluffy-poofy-3d-characters”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 950e1bf. 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
No URLs in SKILL.md.
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
Fluffy Poofy 3D Characters loads about 1.5k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 772 words of instructions outside code blocks.
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 agentara/skills at commit 950e1bf, republished under its MIT licence (© agentara). 772 words, ~1,523 tokens.
Download SKILL.mdSave it as
.claude/skills/fluffy-poofy-3d-characters/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- fluffy-poofy-3d-characters
- description
- Generate original fluffy, poofy 3D animation characters in a cohesive collectible-avatar family: monolithic plush body, inset smooth face, tiny limbs, restrained expression, tactile materials, strong silhouettes, and high variation without losing the shared design language.
Fluffy & Poofy 3D Characters
Use this skill whenever the user asks to create, vary, expand, or art-direct characters in this avatar family.
Core Design Language
One-line rule: monolithic poofy body + smooth inset face + tiny limbs + restrained expression + tactile plush material + unmistakable silhouette.
1. Silhouette
- One dominant rounded body mass; head and torso often merge into one shape.
- Short, heavy, simplified limbs; no anatomical fingers or toes unless specifically requested.
- A character must remain recognizable as a solid silhouette.
- Proportions should feel toy-like and huggable rather than human or mascot-costume realistic.
2. Face Architecture
- Face is a clean, smooth, matte panel embedded inside the fuzzy body, like a small opening in a plush shell.
- Keep the face visually quieter than the body.
- Default features: two small black dot eyes, tiny curved mouth, subtle blush, no visible nose.
- Expressions are calm and low-amplitude; avoid exaggerated emoji faces.
3. Material Contrast
- Body: dense short fur, fleece, velvet, boucle, shag, or another tactile soft surface.
- Face: smooth matte material with warm skin/ivory tone.
- The contrast between fuzzy shell and clean face is a defining feature.
- Avoid glossy plastic CGI, hard rubber, or metallic toy surfaces unless explicitly requested.
4. Shape Language
- Rounded, continuous, low-detail geometry.
- No sharp mechanical segmentation.
- Ears, horns, tails, fins, antennae, sprouts, wings, etc. should be simplified into soft toy-like primitives.
- Species inspiration is allowed, but the result should feel like its own creature rather than a literal animal costume.
5. Color
- Soft, coherent palettes: cream, oatmeal, muted brown, dusty pink, sage, pale blue, lavender, warm yellow, charcoal, muted terracotta.
- Stronger colors are allowed as accents, not as neon lighting.
- Keep the face slightly warmer and smoother than the body.
6. Rendering
- Premium 3D animation / collectible-plush quality.
- Soft diffused studio light, subtle ambient occlusion, gentle floor shadow.
- Clean white or very light neutral background by default.
- Front-facing or small natural pose variation; avoid dramatic camera distortion.
- No text unless requested.
Variation Rules
When generating multiple characters, make each character structurally different, not just recolored.
Vary across these axes:
- silhouette: tall, squat, pear-shaped, egg-shaped, wide, narrow, top-heavy, bottom-heavy
- fur: short plush, long fluffy, shaggy, boucle, velour, curly wool
- face opening: rounded rectangle, oval, arch, bean, shallow trapezoid, asymmetric soft cutout
- appendages: rounded ears, floppy ears, horns, antennae, fins, tiny wings, tail, sprout, mane
- proportions: face-to-body ratio, limb length, shoulder width, belly size, leg spacing
- motifs: stripes, spots, belly patch, gradient, seasonal detail, tiny scarf, bow, hood nub
- expression: neutral smile, sleepy, curious, shy, content, surprised-but-subtle
Do not create 36 near-identical bodies with different animal ears. Change the underlying body architecture too.
Show full SKILL.md (343 more words)Show less
Generation Workflow
- Read the user's requested count, aspect ratio, grid, subject, and variation constraints.
- Use
assets/reference-avatar.pngas the primary design-language reference. - If available, use
assets/character-grid.pngonly as a diversity reference, not as a set to copy. - Build a variation plan before generation so neighboring characters do not repeat silhouette, species cue, color, or accessory.
- Generate with image generation using the reference image(s).
- Inspect the result for:
- correct number of characters
- unique silhouettes
- consistent face architecture
- fuzzy-shell / smooth-face contrast
- no duplicated characters
- no malformed limbs or accessories
- no text artifacts
- cohesive lighting and scale
- If diversity is weak, regenerate with stronger structural variation rather than adding random accessories.
Default Prompt Block
Use this wording as the base and adapt it to the user's request:
Create original premium 3D animation characters in one coherent collectible family. Each character has a monolithic rounded plush body, a small smooth matte face panel embedded inside the fuzzy shell, tiny simplified limbs, restrained dot-eye facial features, subtle blush, tactile soft materials, and a strong readable silhouette. Keep geometry low-detail, rounded, and huggable. Every character must be structurally unique through silhouette, proportions, fur treatment, face-opening shape, appendages, motifs, and color—not merely recolored. Preserve a consistent design language across the entire set. Use soft diffused studio lighting, subtle contact shadows, and a clean white or very light neutral background. Avoid glossy CGI, literal mascot costumes, over-detailed anatomy, exaggerated emoji expressions, generic kawaii duplication, neon gradients, text, and AI-slop artifacts.
Grid Defaults
For character-sheet requests:
- default to a strict equal-cell grid
- exactly one character per cell
- full body visible
- consistent visual scale
- generous breathing room
- light or invisible separators
- no labels unless requested
For 36 characters, use a strict 6 × 6 grid.
Negative Direction
Avoid:
- generic Funko-like vinyl heads
- chibi human proportions
- literal furry animal suits
- big anime eyes
- oversized mouths
- glossy plastic or clay-only look
- hard-surface mecha details
- random accessories used as the only source of uniqueness
- repeated identical body meshes
- excessive rainbow/neon palettes
- fake text, watermarks, or UI
- over-rendered cinematic backgrounds unless requested
© agentara, 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 3 other files (assets) in skills/aigc/fluffy-poofy-3d-characters of agentara/skills.
- SKILL.md
- assets/.placeholder
- assets/character-grid.png
- assets/reference-avatar.png
Open the folder on GitHubat commit 950e1bf
Compare with similar skills
Fluffy Poofy 3D Characters 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Fluffy Poofy 3D Characters this skillagentara/skills | 603 | — | ~1.5k | Automated safety check: Pass | MIT | |
| SVG Character Animationcalesthio/OpenMontage | 66k | — | ~421 | Automated safety check: Pass | MIT | |
| Character Animation QAcalesthio/OpenMontage | 66k | — | ~389 | Automated safety check: Pass | MIT | |
| Cohesivitysickn33/agentic-awesome-skills | 47k | 1 repos | ~4.8k | Automated safety check: Pass | MIT | |
| Animejs Animationsickn33/agentic-awesome-skills | 47k | 2 repos | ~681 | Automated safety check: Pass | MIT | |
| HyperFrames Animationheygen-com/hyperframes | 60k | 3 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Character Animation QA
calesthio/OpenMontage
Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.
Cohesivity
sickn33/agentic-awesome-skills
Provision headless backend services for AI agents through Cohesivity: hosting, databases, storage, LLMs, and third-party APIs over one HTTP API.
Animejs Animation
sickn33/agentic-awesome-skills
Advanced JavaScript animation library skill for creating complex, high-performance web animations.
HyperFrames Animation
heygen-com/hyperframes
Collects motion rules, scene blueprints, transitions and runtime adapters for HyperFrames video compositions, with GSAP as the default animation runtime.
Character Rigging
calesthio/OpenMontage
Build data-driven 2D character rigs for local animation: parts, pivots, layers, constraints, views, and reusable rig packages.
More from agentara/skills
All 20 skills in this repoWorld Cup Predictor
agentara/skills
Predict FIFA World Cup matches, full tournament paths, and champion probabilities through Codex-native subagents that analyze live news, weather, injuries, markets, Polymarket, tactics, and…
Presentation Design
agentara/skills
Generate a premium 6-slide presentation design board as one single composite image.
Publish Research Site
agentara/skills
Turn a thesis, proposition, trend, question, or explainer topic into a citation-backed, image-rich, interactive website and deploy it with Vercel CLI.
Portrait Clone
agentara/skills
Turn any n reference images (with at least one person) into one exhaustively locked, always de-slopped, JSON-only AIGC image prompt whose every variable is pinned so each generation is nearly…
Torn Paper Collage Poster
agentara/skills
Create AI image-generation prompts and image-generation workflows for torn-paper editorial collage style posters with layered ripped paper, rough typography, stamps, tape, stickers, cutout subjects…
Article To HTML
agentara/skills
Render a markdown draft / any document in the conversation context into a single-file "paper proposal" HTML — serif body, monospace meta, numbered sections, inline SVG figures, callouts, tables…
Questions about Fluffy Poofy 3D Characters
What does Fluffy Poofy 3D Characters do?
Generate original fluffy, poofy 3D animation characters in a cohesive collectible-avatar family: monolithic plush body, inset smooth face, tiny limbs, restrained expression, tactile materials…. Fluffy Poofy 3D Characters is an agent skill from agentara/skills. Generate original fluffy, poofy 3D animation characters in a cohesive collectible-avatar family: monolithic plush body, inset smooth face, tiny limbs, restrained expression, tactile materials, strong silhouettes, and high variation without losing the shared design language.
How do I install Fluffy Poofy 3D Characters in Claude Code?
Run `npx skills add agentara/skills --skill fluffy-poofy-3d-characters -a claude-code`. Or copy the skill folder (skills/aigc/fluffy-poofy-3d-characters in agentara/skills) into .claude/skills/fluffy-poofy-3d-characters in your project. Claude Code loads it when a task matches its description.
How do I install Fluffy Poofy 3D Characters in Codex?
Run `npx skills add agentara/skills --skill fluffy-poofy-3d-characters -a codex`. Or copy the skill folder (skills/aigc/fluffy-poofy-3d-characters in agentara/skills) into .agents/skills/fluffy-poofy-3d-characters in your project. Codex loads it when a task matches its description.
Can I use Fluffy Poofy 3D Characters 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 agentara/skills --skill fluffy-poofy-3d-characters -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fluffy-poofy-3d-characters, .gemini/skills/fluffy-poofy-3d-characters, .github/skills/fluffy-poofy-3d-characters and .opencode/skills/fluffy-poofy-3d-characters in your project.
What does Fluffy Poofy 3D Characters need to run?
SKILL.md names no scripts, command-line tools or credentials: Fluffy Poofy 3D Characters is instructions for the agent only.
Does Fluffy Poofy 3D Characters access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Fluffy Poofy 3D Characters 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 Fluffy Poofy 3D Characters use?
Fluffy Poofy 3D Characters 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 Fluffy Poofy 3D Characters use?
About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Fluffy Poofy 3D Characters?
Skills that share tags, products or a category with Fluffy Poofy 3D Characters: SVG Character Animation (calesthio/OpenMontage, 66k stars), Character Animation QA (calesthio/OpenMontage, 66k stars), Cohesivity (sickn33/agentic-awesome-skills, 47k stars) and Animejs Animation (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Fluffy Poofy 3D Characters?
agentara (a GitHub organization) maintains it in agentara/skills, which has 603 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on September 29, 2026.
Source: agentara/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.