图像视频 技能与专家

Generate images using Cloudflare Workers AI flux-1-schnell model. Use when user requests image generation with text-to-image using Cloudflare Workers API.

OCR text recognition using DeepSeek-OCR model. Use when user asks for OCR, text recognition, image text extraction, screenshot recognition, or converting ima...

Upload and publish video content to YouTube using the Publora API. Use this skill when the user wants to upload or schedule YouTube videos via Publora.

Bulk download TikTok videos from a text file of URLs using yt-dlp. Use when a user asks to download many TikTok videos at once, process a URL list file, or s...

即梦 Seedance 视频创意工作台。用户发图+文案时自主完成看图分析→文案扩写→运镜匹配→质量验证→API生成。触发词：即梦、Seedance、seedance、视频生成、视频提示词、AI视频、运镜、短剧、广告视频、视频延长、图生视频。

Generate short-lived, mobile-friendly ngrok preview links for local artifacts and share them in Telegram. Use when OpenClaw produces images/charts/generated...

PDF扫描件转Word文档。支持中文OCR识别，自动裁掉页眉页脚，保留插图，彩色章节封面页保留为图片。使用百度OCR API（免费额度1000次/月）。当用户要求把扫描PDF转成文字/Word时触发。

Use DualGap for dual-domain research gap analysis: turn two paper collections, PDF folders, arXiv downloads, or research directions into reviewer-checked lit...

OpenClaw virtual companion skill. Use it to bootstrap runtime files (SOUL and base image), guide user personalization, learn and store style prompts from upl...

Convert Markdown files to PDF with full LaTeX math formula rendering and CJK (Chinese/Japanese/Korean) support. Use when the user asks to convert markdown to...

Nano Banana 2 — AI image generation powered by Google Gemini 3.1 Flash. Fast, versatile text-to-image and image editing via Evolink API. One API key.

Send a public video URL directly to a Google Gemini model for analysis. Use when Codex must summarize a video, answer questions about video content, or extra...

Perform privacy-focused web searches via DDGS metasearch for webpages, news, images, videos, or books with no tracking and no API key required.

Generate a minimalist terrain-style animated driving route video (MP4) from a list of stops (cities/POIs) without Remotion. Uses OSRM for road-following geom...

Use when user asks to analyze an image, describe image contents, or answer questions about a picture. iFlytek Image Understanding (图片理解) — analyze and answer...

将视频、字幕文件或大型课程目录转换为结构化图文笔记。仅当用户明确要求执行完整的视频转文章工作流，例如下载视频、生成图文文章、写入 Obsidian 或批量导入课程时使用；如果用户只想做摘要、问答、术语提取或轻量分析，应优先采用只读分析流程。

Generate depth maps from images using each::sense AI. Create depth estimation for 3D effects, parallax animations, VR/AR applications, focus effects, and ste...

Generate promo video plan with 30-45s script, shot-by-shot storyboard, and optional Remotion/Montage-tool config. Use when user says "create video", "promo v...

Index YouTube channel videos and transcripts for semantic search. Use when user says "index YouTube", "add YouTube channel", "update video index", or "index...

Analyze any webpage URL for SEO issues and get actionable recommendations. Checks title tags, meta descriptions, heading structure, keyword density, image al...

Analyzes images to detect AI generation, extract metadata, identify artifacts, and perform content moderation using local and cloud-based tools.

Automated daily news video downloader with AI subtitle proofreading. Downloads CBS Evening News and BBC News at Ten from YouTube, extracts and proofreads sub...

Configure and use snipgrapher to generate polished code snippet images

视频理解与分析能力 - 让 AI 能够理解视频内容、提取关键信息。当用户要求分析视频、理解视频内容、总结视频、提取视频要点时触发此技能。