发现优质的 AI Agent 技能

**Other tools need perfect images. CellCog turns ideas into 3D models.**

Turn screenshots and images into polished demo videos with Ken Burns pan/zoom effects, crossfade transitions, and text overlays. Built for hackathon teams and OSS projects that need showcase content without video editing software.

Generate images from the same prompt across multiple models and compare results. Tracks costs, generation time, and quality for informed model selection.

Batch export Feishu documents to markdown or PDF format, features: - Batch export entire folders - Preserve document structure and formatting - Export images as local files - Support nested folder hierarchy

- Run in text-only mode by default. - Avoid image-led critiques, dashboards, or visual redesign directions unless explicitly requested. - Prioritize decisions that improve completion quality, error recovery, accessibility, and trust.

Patiently AI simplifies medical documents for patients. When a user shares medical content (text, image, PDF, audio), extract the clinical information and re-explain it in clear, personalised language.

来自 openclaw/skills

Generate images and videos using Venice AI APIs. Venice is an uncensored AI platform with competitive pricing.

Analyze, convert, and manipulate image files.

Generate QR codes from text, URLs, or local images. Perfect for sharing links, contact information, or small images via scannable codes.

Generate new images or edit existing ones using Google's Nano Banana Pro API (Gemini 3 Pro Image).

Lightweight HTTP file server for sharing agent-generated media (screenshots, images, documents) with users on the local network.