Sprite Gen
aldegad/sprite-gen
Generates images and game sprites through GPT or Grok with guided provider choices, separate saved defaults, automatic cleanup and optional curation.
Use Retro Diffusion for pixel-art image generation, img2img edits, spritesheets, and animation experiments such as platformer walk cycles, turnarounds, and action sheets from reference images.
Install Retro Diffusion
$ npx skills add chongdashu/vibejam-starter-pack --skill retro-diffusion -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install chongdashu/vibejam-starter-pack retro-diffusion --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/chongdashu/vibejam-starter-pack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/retro-diffusion .claude/skills/retro-diffusion && 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 "retro-diffusion" agent skill from https://github.com/chongdashu/vibejam-starter-pack/tree/main/.agents/skills/retro-diffusion into .claude/skills/retro-diffusion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retro-diffusion", 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/chongdashu/vibejam-starter-pack/tree/main/.agents/skills/retro-diffusionType 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 chongdashu/vibejam-starter-pack --skill retro-diffusion -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install chongdashu/vibejam-starter-pack retro-diffusion --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chongdashu/vibejam-starter-pack.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/retro-diffusion .agents/skills/retro-diffusion && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "retro-diffusion" agent skill from https://github.com/chongdashu/vibejam-starter-pack/tree/main/.agents/skills/retro-diffusion into .agents/skills/retro-diffusion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retro-diffusion", 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 chongdashu/vibejam-starter-pack --skill retro-diffusion -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install chongdashu/vibejam-starter-pack retro-diffusion --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chongdashu/vibejam-starter-pack.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/retro-diffusion .cursor/skills/retro-diffusion && 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 "retro-diffusion" agent skill from https://github.com/chongdashu/vibejam-starter-pack/tree/main/.agents/skills/retro-diffusion into .cursor/skills/retro-diffusion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retro-diffusion", 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/chongdashu/vibejam-starter-pack.git --path .agents/skills/retro-diffusion--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 chongdashu/vibejam-starter-pack --skill retro-diffusion -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install chongdashu/vibejam-starter-pack retro-diffusion --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chongdashu/vibejam-starter-pack.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/retro-diffusion .gemini/skills/retro-diffusion && 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 "retro-diffusion" agent skill from https://github.com/chongdashu/vibejam-starter-pack/tree/main/.agents/skills/retro-diffusion into .gemini/skills/retro-diffusion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retro-diffusion", 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 chongdashu/vibejam-starter-pack retro-diffusionInstalls 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 chongdashu/vibejam-starter-pack --skill retro-diffusion -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/chongdashu/vibejam-starter-pack.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/retro-diffusion .github/skills/retro-diffusion && 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 "retro-diffusion" agent skill from https://github.com/chongdashu/vibejam-starter-pack/tree/main/.agents/skills/retro-diffusion into .github/skills/retro-diffusion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retro-diffusion", 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 chongdashu/vibejam-starter-pack --skill retro-diffusion -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install chongdashu/vibejam-starter-pack retro-diffusion --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chongdashu/vibejam-starter-pack.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/retro-diffusion .opencode/skills/retro-diffusion && 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 "retro-diffusion" agent skill from https://github.com/chongdashu/vibejam-starter-pack/tree/main/.agents/skills/retro-diffusion into .opencode/skills/retro-diffusion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "retro-diffusion", 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
retro-diffusion- GitHub stars
- 149
- Token cost
- ~3.4k tokens
- SKILL.md length
- 1,781 words
- Files
- 17 (incl. scripts, references, assets)
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- None found
At a glance
Use Retro Diffusion for pixel-art image generation, img2img edits, spritesheets, and animation experiments such as platformer walk cycles, turnarounds, and action sheets from reference images.
- Works in 6 steps: Style first, prompt second: in Retro… → Respect size contracts:… → Reference cleanliness matters:… → …
- Tasks that involve Sprites and pixel art
- SKILL.md covers Philosophy: Match The Style To…, What This Skill Provides, Working With Retro Diffusion and Scripts, plus 6 more sections
- Runs Python scripts from its folder; reaches api.retrodiffusion.ai
What it does
Retro Diffusion is an agent skill from chongdashu/vibejam-starter-pack. Use Retro Diffusion for pixel-art image generation, img2img edits, spritesheets, and animation experiments such as platformer walk cycles, turnarounds, and action sheets from reference images.
Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 20 other files, including scripts, reference files and assets (for example `assets/model-presets.json`, `references/animation-workflows.md` and `references/api-and-styles.md`).
It sits in Game Development, covering Sprites and pixel art and Image generation. The repository describes itself as: Free Vibe Jam starter pack — battle-tested ThreeJS and Phaser agent skills, starter projects, and prompts.
When your agent uses it
- Tasks that involve Sprites and pixel art
- Tasks that involve Image generation
Example prompts
- “/retro-diffusion”
Requirements
- Python 3
- A credential in YOUR_API_KEY
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Style first, prompt second: in Retro Diffusion, prompt_style is the mode selector, not just a flavor tweak.
- Respect size contracts: animationfour_angle_walking is a 48x48 workflow, animation8_dir_rotation is 80x80, and advanced animations should…
- Reference cleanliness matters: input_image should be RGB with no transparency, and the prompt should describe the reference rather than…
- Capture the sheet, not just the preview: for sprite work, prefer return_spritesheet: true so downstream analysis stays deterministic.
- Prompt shorter than you think: for advanced animations, keep prompts extremely terse. The service expands action text internally, and long…
- Treat completion as artifact-based, not CLI-message-based: a run can succeed even if the local wrapper times out, drops the final…
What it can do on your machine
Read from SKILL.md and the folder at commit 6793771. 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
Ships 5 files in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
api.retrodiffusion.ai
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
Retro Diffusion loads about 3.4k tokens when it runs, and up to ~6k if it reads all its reference files. Until then it costs about 52 tokens; SKILL.md has 1,781 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); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 1,781 words (~3,449 tokens).
“Use this skill when the user wants to generate pixel-art images or animation sheets through Retro Diffusion, especially when the task involves reference-image-driven character work like side-view platformer walks, turnarounds, or action cycles.”
- name
- retro-diffusion
- metadata.short-description
- Retro Diffusion image and animation workflows.
Files
SKILL.md and 16 other files (scripts, references, assets) in .agents/skills/retro-diffusion of chongdashu/vibejam-starter-pack.
- SKILL.md
- assets/model-presets.json
- assets/prompt-profiles/character-isometric-8turn-from-sw-v1.txt
- assets/prompt-profiles/character-isometric-cardinals-from-sw-v1.txt
- assets/prompt-profiles/character-isometric-diagonals-from-cardinals-v1.txt
- assets/prompt-profiles/character-isometric-sw-walk-v1.txt
- assets/prompt-profiles/character-side-battle-sprites-v1.txt
- assets/prompt-profiles/character-side-punch-any-animation-v1.txt
- assets/prompt-profiles/character-side-running-any-animation-v1.txt
- assets/prompt-profiles/character-side-walk-v1.txt
- references/animation-workflows.md
- references/api-and-styles.md
- scripts/_retro_common.py
- scripts/extract_rd_sheet_frames.py
- scripts/prepare_reference_image.py
- scripts/retro_experiment_matrix.py
- scripts/retro_inference_run.py
Open the folder on GitHubat commit 6793771
Compare with similar skills
Retro Diffusion 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 |
|---|---|---|---|---|---|---|
| Retro Diffusion this skillchongdashu/vibejam-starter-pack | 149 | — | ~3.4k | Automated safety check: Pass | None | |
| Sprite Genaldegad/sprite-gen | 2.6k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| Hatch PethAcKlyc/MyAgents | 918 | 2 repos | ~9.5k | Automated safety check: Pass | Apache-2.0 | |
| 2D Sprite Generator0x0funky/agent-sprite-forge | 4.3k | — | ~3.6k | Automated safety check: Pass | MIT | |
| Img Gen Avatar4thfever/cultivation-world-simulator | 2.1k | — | ~641 | Automated safety check: Pass | Custom licence | |
| Hatch Petnexu-io/open-design | 100k | — | ~6k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Hatch Pet
hAcKlyc/MyAgents
Create, repair, validate, visually QA, and package MyAgents/Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual…
2D Sprite Generator
0x0funky/agent-sprite-forge
Produces game-ready 2D characters, creatures, props, icons and effects as master stills, sheets or clips, and exports frames for common game engines.
Img Gen Avatar
4thfever/cultivation-world-simulator
A skill your agent uses when working on tools/imggen avatar image generation, OpenAI-compatible image API config, human or yaoguai portrait prompts, qi-refining base generation, image-to-image realm…
Hatch Pet
nexu-io/open-design
Create, repair, validate, preview, and package Codex-compatible animated pet spritesheets from character art, screenshots, generated images, or visual references.
Game Asset Generator
htdt/godogen
Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.
More from chongdashu/vibejam-starter-pack
All 11 skills in this repoPlaywright Testing
chongdashu/vibejam-starter-pack
Plan, implement, and debug frontend tests: unit/integration/E2E/visual/a11y.
Playwright Testing
chongdashu/vibejam-starter-pack
Plan, implement, and debug frontend tests: unit/integration/E2E/visual/a11y.
Phaser Gamedev
chongdashu/vibejam-starter-pack
Build 2D games with Phaser 3 framework. An agent skill from chongdashu/vibejam-starter-pack.
Phaser4 Gamedev
chongdashu/vibejam-starter-pack
Build 2D browser games with Phaser 4: WebGL-first rendering, scenes, filters, lighting, shaders, DynamicTexture and RenderTexture, tilemaps, SpriteGPULayer, TilemapGPULayer, and Phaser 3 to 4…
Threejs Builder
chongdashu/vibejam-starter-pack
Design and implement lightweight Three.js (r150+) ES-module scenes—hero sections, interactive product viewers, particle backdrops, GLTF showcases, or quick prototypes—whenever prompts mention…
Tinyswords Tilemap
chongdashu/vibejam-starter-pack
Build tilemaps using Tiny Swords asset pack. An agent skill from chongdashu/vibejam-starter-pack.
Related
Categories
Questions about Retro Diffusion
What does Retro Diffusion do?
Use Retro Diffusion for pixel-art image generation, img2img edits, spritesheets, and animation experiments such as platformer walk cycles, turnarounds, and action sheets from reference images. Retro Diffusion is an agent skill from chongdashu/vibejam-starter-pack. Use Retro Diffusion for pixel-art image generation, img2img edits, spritesheets, and animation experiments such as platformer walk cycles, turnarounds, and action sheets from reference images.
When should I use Retro Diffusion?
Retro Diffusion fits situations like: tasks that involve Sprites and pixel art; tasks that involve Image generation.
How do I install Retro Diffusion in Claude Code?
Run `npx skills add chongdashu/vibejam-starter-pack --skill retro-diffusion -a claude-code`. Or copy the skill folder (.agents/skills/retro-diffusion in chongdashu/vibejam-starter-pack) into .claude/skills/retro-diffusion in your project. Claude Code loads it when a task matches its description.
How do I install Retro Diffusion in Codex?
Run `npx skills add chongdashu/vibejam-starter-pack --skill retro-diffusion -a codex`. Or copy the skill folder (.agents/skills/retro-diffusion in chongdashu/vibejam-starter-pack) into .agents/skills/retro-diffusion in your project. Codex loads it when a task matches its description.
Can I use Retro Diffusion 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 chongdashu/vibejam-starter-pack --skill retro-diffusion -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/retro-diffusion, .gemini/skills/retro-diffusion, .github/skills/retro-diffusion and .opencode/skills/retro-diffusion in your project.
What does Retro Diffusion need to run?
Going by SKILL.md and its folder, Retro Diffusion needs Python for the scripts in its folder. Our summary lists: Python 3; A credential in YOUR_API_KEY.
Does Retro Diffusion access the network?
SKILL.md names 1 domain. In commands or code: api.retrodiffusion.ai; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Retro Diffusion 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Retro Diffusion use?
No licence was found for Retro Diffusion or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Retro Diffusion use?
About 3.4k tokens (SKILL.md is roughly 14k 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 2.6k tokens, read only when the agent opens those files.
What are the alternatives to Retro Diffusion?
Skills that share tags, products or a category with Retro Diffusion: Sprite Gen (aldegad/sprite-gen, 2.6k stars), Hatch Pet (hAcKlyc/MyAgents, 918 stars), 2D Sprite Generator (0x0funky/agent-sprite-forge, 4.3k stars) and Img Gen Avatar (4thfever/cultivation-world-simulator, 2.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Retro Diffusion?
chongdashu (a GitHub user) maintains it in chongdashu/vibejam-starter-pack, which has 149 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on April 15, 2026.
Source: chongdashu/vibejam-starter-pack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.