Skip to content

0xsline/OpenChatCut / src/agent/skills/image-gen

image-gen

Verified

AI image generation via Fal.ai, gpt-image-2, nano-banana, MiniMax image-01, xAI Grok Imagine, and Agnes Image. Use when the user wants to generate or create an image / picture / still.

FileKindSize
SKILL.mdskill md5.6 KB
references/agnes-image.mdmarkdown871 B
references/fal.mdmarkdown955 B
references/gpt-image-2.mdmarkdown2.3 KB
references/grok-imagine.mdmarkdown1.4 KB
references/image-01.mdmarkdown2.2 KB
references/nano-banana.mdmarkdown1.7 KB

references/nano-banana.md

View on GitHub
# nano-banana (Gemini Pro)

Read this document before generating images with `--model nano-banana`.

## Model

| Model         | Max refs | Strengths                     |
| ------------- | -------- | ----------------------------- |
| `nano-banana` | 14       | Best reference-image fidelity |

## Params

Nano Banana does NOT support `--quality`. Only shared params apply:

| Param      | Values                      | Default | Notes                               |
| ---------- | --------------------------- | ------- | ----------------------------------- |
| `--size`   | `1K`, `2K`, `4K`            | `1K`    | 2K/4K are EXPERIMENTAL, higher cost |
| `--aspect` | 10 ratios (see SKILL.md)    | `16:9`  | —                                   |
| `--input`  | file path or `asset://<id>` | —       | Up to 14 references                 |

## When to Use

- Reference-heavy tasks: "make an image in the style of these examples"
- When the user provides >10 reference images (gpt-image-2's limit)
- Style transfer, character consistency across multiple images
- Compositing multiple source images into one scene

## Prompt Tips

- With reference images: describe the relationship between references and desired output — "combine the style of the first image with the subject of the second"
- Reference images drive the output strongly — keep the text prompt focused on what to change, not what to copy
- For style transfer: "in the style of the reference image" works well
- For composition: describe the scene structure; Gemini follows spatial descriptions but less literally than gpt-image-2
- Gemini handles natural-language descriptions well — conversational prompts can work better than keyword-style prompts
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall