AI Agent Skills

根据用户描述生成高质量绘图 prompt，并按通用、roadmap、schematic 模式通过 BenszAPI 直接完成 gpt-image-2 或 Nano Banana/Gemini 出图、编辑和多轮迭代；这是自包含的图片生成工作流，选中后不得调用或依赖 imagegen，除非用户明确要求同时使用 imagegen。

Develop art direction for image generation with curated style cards distilled from Open Image Prompts. Use when choosing or comparing visual directions, improving an exi…

This skill should be used when the user asks to "make an audiobook", "narration script", "narrator", "ACX", "Findaway", "pronunciation guide", "how long is the audiobook…

Use this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to edit, retouch, or restyle an existing…

Use this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to create polished product photography an…

Develop and evaluate logo concepts when the explicit design problem is semantic fusion: two or more brand meanings must share a contour, stroke, negative space, glyph sk…

Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, wx.cloud apps). Covers generateText and streamText with callbacks (onText, onEvent, onFinish); str…

Create customer journey maps, service blueprints, experience maps, empathy maps, and other alignment diagrams. Guides diagram type selection, content structure, illustra…

Run Phase Publish — image generation sub-pipeline (provider-pluggable: relay primary + official OpenAI fallback, realtime-forced) + WordPress publish with RankMath meta…

Use this skill when an agent must generate or edit raster images through Codex, especially from Claude Code or another harness without native image generation. Activates…

Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, wx.cloud apps). Covers generateText and streamText with callbacks (onText, onEvent, onFinish); str…

Turn travel or lifestyle photos into 4:5 memory-diary pages pairing real photography with a watercolor and colored-pencil interpretation of the same moment. Use for edit…

Turn travel photos into 3:4 nostalgic editorial posters as either a photo-and-drawing comparison or a full-canvas minimal illustration.

Generate images using Google Gemini via Chrome browser automation. This skill should be used when the user wants to create, generate, or produce images with Gemini, Goog…

Reverse-engineer reference images into actionable recreation prompts or transferable visual styles. Use for recreating references, adapting templates to new subjects, ch…

AI大模型专家｜AI 海报生成与编辑｜中文文字与商业设计。帮助品牌市场、广告创意、平面设计和社交媒体运营团队直接完成“AI 海报生成与编辑｜中文文字与商业设计”：既可从文字生成，也可加入参考图帮助控制主体、构图和视觉风格；通过 AI Hive 使用时，生成前自动上传参考图，提交后自动保存任务、查询进度并下载图片。适用于电商主图、商品详情…