image-gen
AI image generation via Fal.ai, gpt-image-2, nano-banana, MiniMax image-01, xAI Grok Imagine, and Agnes Image
Install / Use
npx skills add 0xsline/OpenChatCut --skill image-genInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
AI & Machine LearningSupported Platforms
Our assessment of image-gen
image-gen scores 83/100 on our quality scale, 686th of 950 AI & Machine Learning skills we index.
Its SKILL.md is 5.3 KB long, well organised into 8 sections with 1 code example: a solid amount of guidance for an agent.
With 1,986 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so image-gen is actively maintained.
- Our last check on 2026-11-07 found the source still online.
- It is released under AGPL-3.0, a copyleft license: you can use it, but modified versions you distribute must carry the same license.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit β read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-01. Automated pattern scan on 2026-10-01. It catches known dangerous patterns, not every risk β read a skill before letting an agent act on it.
image-gen compared with similar skills
All 4 of these similar skills score higher than image-gen; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| image-gen (this skill)by 0xsline | 83 | 2.0k | 56d ago | SKILL.md |
| claude-memby thedotmack | 100 | 117.6k | today | CLAUDE.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| Understand-Anythingby Egonex-AI | 100 | 92.8k | 1d ago | CLAUDE.md |
| headroomby headroomlabs-ai | 100 | 79.8k | today | CLAUDE.md |
Frequently asked questions
- How do I install image-gen?
- Run
npx skills add 0xsline/OpenChatCut --skill image-gen. The install tabs above show the steps for each supported agent. - Which AI agents does image-gen work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is image-gen safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is AGPL-3.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is image-gen still maintained?
- The repository was last updated about 2 months ago, so image-gen is actively maintained.
Skill content
View source on GitHubname: image-gen description: | AI image generation via Fal.ai, gpt-image-2, nano-banana, MiniMax image-01, and xAI Grok Imagine. Use when the user wants to generate or create an image / picture / still. user-invocable: true
Image Gen
Generate AI images via submit_image (configured provider keys only). Prefer one clear still per request unless the user asked for variants.
Model Selection
| Model | Reference | Strengths | Max refs |
| --- | --- | --- | --- |
| fal + falModel | references/fal.md | Explicit Fal catalog; see tool schema for per-model limits | Model-specific |
| gpt-image-2 | references/gpt-image-2.md | Best text rendering, strongest prompt adherence | 16 |
| nano-banana | references/nano-banana.md | Strongest reference-image fidelity | 14 |
| image-01 | references/image-01.md | MiniMax stills / live style; one subject reference via R2 | 1 |
| grok-imagine | references/grok-imagine.md | xAI Grok Imagine; text-to-image, β€4 outputs, 1K/2K | 0 |
- If Fal.ai is selected or requested, use
model: "fal"and the requestedfalModelor saved Fal default from capabilities. Ask if none is selected. Native-provider defaults and controls below do not apply to Fal. - Default:
gpt-image-2when that key is on. - Reference-heavy β
nano-banana. - User named MiniMax / only MiniMax image key on β
image-01. - Respect capabilities: do not call a model whose vendor is not configured.
IMPORTANT: Before generating, READ the chosen model's reference.
Tool Params
| Param | Values | Default |
| ------------------- | ----------------------------------------------------------------------- | ------- |
| aspectRatio | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 21:9 | 16:9 |
| imageSize | 512px, 1K, 2K, 4K (model-specific) | 1K |
| width / height | GPT Image: 512β3840, /16; MiniMax: 512β2048, /8 | β |
| quality | low, medium, high, auto (gpt-image-2 only) | high |
| referenceAssetIds | Array of project asset ids β backend resolves bytes server-side | β |
| name | Short descriptive asset name shown in the library | β |
| count | Number of images to generate (1β10; image-01 max 9) | 1 |
| promptOptimizer | MiniMax image-01 only β prompt_optimizer | false |
| seed | MiniMax image-01 only | β |
| maskAssetId, background, moderation, inputFidelity | GPT Image edit/output controls | β |
| outputFormat, outputCompression | GPT Image PNG/JPEG/WebP controls | PNG |
Defaults
- Aspect ratio: 16:9. If the project composition is not 16:9, ASK the user which aspect ratio they want before generating.
- Size: 1K.
Ask Before Submit
- Never auto-upgrade size.
- Only pass
imageSize: "2K"or"4K"when the user explicitly asks. Warn that 2K/4K are EXPERIMENTAL and may be slower.
Reference Images
Use when the user provides source material to edit, blend, or use as visual guidance (e.g. "change the background", "combine these into a poster").
- Pass project asset ids via
referenceAssetIds. The backend fetches and encodes them server-side β never pull the asset bytes yourself. - When the user @-references an image asset, pass its id directly in
referenceAssetIds. - Formats accepted by backend: png, jpeg, webp, svg (auto-rasterized to png), heic, heif. Each β€ 50MB.
Run
// Basic generation
submit_image({
model: "gpt-image-2",
prompt: "a cute orange cat",
name: "Cat",
});
// With quality (gpt-image-2 only)
submit_image({
model: "gpt-image-2",
prompt: "hero poster with bold title",
quality: "high",
name: "Hero Poster",
});
// With reference images β pass project asset ids; backend resolves bytes
submit_image({
model: "gpt-image-2",
prompt: "change background to beach",
referenceAssetIds: ["<assetId>"],
name: "Beach Edit",
});
// Reference-heavy with nano-banana
submit_image({
model: "nano-banana",
prompt: "composite poster",
referenceAssetIds: ["<id1>", "<id2>"],
name: "Composite",
});
// Multiple images
submit_image({
model: "gpt-image-2",
prompt: "product shots",
count: 3,
name: "Product",
});
// MiniMax (optional single subject reference; R2 must be configured for refs)
submit_image({
model: "image-01",
prompt: "matte product bottle on marble, soft studio light",
name: "Bottle still",
promptOptimizer: false,
});
OpenChatCutβs submit_image may return completed pool assets synchronously depending on the provider path. If a jobId is returned, use track_progress; otherwise treat the asset ids in the result as done.
Rules
- Always provide
namewith a short descriptive asset name. - Before submitting, briefly tell the user what you're about to generate β especially when generating multiple images.
- Only call models whose vendor key is configured (capabilities prompt).
Related Skills
claude-mem
117.6kPersistent Context Across Sessions for Every Agent β Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
Understand-Anything
92.8kGraphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
headroom
79.8kCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit β see the Safety scan above for what the skill file itself contains.
