AI Agent Skills

Codex Skill for writing Zelda-style image prompts

Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images

Generate and edit 2D image assets for Three.js games with Google's Gemini image API: concept sheets, image-to-3D inputs, texture and material references, sky and backgro…

Agent skill for OpenAI-compatible image generation, editing, and batch workflows.

User wants a 海报, flyer, campaign visual, event one-pager, hiring poster, webinar poster, comic-as-visual, or a single designed poster they will click-edit in Paw Work De…

User wants @截图 / @图片 of a competitor poster, ad, or UI shot remade as a click-editable Design board (real text + cropped photo). Do NOT trigger for a new original 海报 wit…

User wants selected product cards, catalog rows, or an admin list turned into a live comparison workbook (image, title, price, link). Do NOT trigger for a general spread…

Multi-vendor AI image generation with authentication-aware parallel dispatch. Routes to Codex (gpt-image-2 via ChatGPT OAuth), Antigravity (Gemini-family "nano-banana" i…

Generate AI images using Volcengine Seedream model. Supports text-to-image (T2I), image editing (I2I), multi-image fusion, and web-search-based generation. Use this skil…

用 ByteDance Seedream 4.0 API（经 Segmind）生成 AI 图像。当用户要从文字描述生成营销素材、海报、产品图、概念图、社交媒体配图等高质量图像，且环境配有 SEGMIND_API_KEY 时使用。支持 2K/4K、多比例、单次最多 15 张批量、最多 3 张参考图控风格。不用于：修改/编辑已有图片（用图像…

OpenCode plugin: image generation via your ChatGPT subscription or OpenAI API

Generate images using AI (OpenAI GPT Image or Stability AI). Use when the user asks to generate an image, create an AI image, make an illustration, or produce artwork fr…

HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation​

Free AI Image Generation API using Cloudflare Workers

Generate and download images through APIMart's asynchronous GPT-Image-2 API. Use when Codex needs APIMart image generation, GPT-Image-2 text-to-image, image-to-image wit…

用于处理写书过程中的章节截图与插图工作流。适用于：梳理某一章需要哪些截图、逐步给出 Claude Code 实操提示词、规定截图文件名与图号映射、回填本地 Markdown 中的图片位置、清理作者备注为读者版正文、以及把章节和图片按正确位置同步到 Feishu 文档。用户如果提到“书的截图”“章节配图”“图号对应”“放到原文里”“上传飞…