Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Image OCR, text recognition, extract text from image, scan document, read image text, invoice OCR, receipt OCR, contract recognition, table extraction, business card OCR, ID recognition, screenshot text extraction, document digitization. Runs locally on Windows using the GLM-OCR model, supports mixed Chinese/English text, prioritizes Intel iGPU inference, no cloud API calls.
AI-powered video generation skill. Use when the user wants to generate videos from text descriptions, browse video recipes, upload assets, or manage video creation workflows.
Generate images, edit existing images, create short videos, run inpainting/outpainting and object-focused edits, use reference images as provider inputs, batch related media jobs from a manifest, and fetch returned media from URLs/HTML/JSON/data URLs/base64. Use when working on AI image generation, AI image editing, mask-based inpainting, outpainting, reference-image workflows, short AI video generation, product-shot variations, or reusable media-production pipelines.
MinerU document extraction CLI that converts PDFs, images, and web pages into Markdown, HTML, LaTeX, or DOCX via the MinerU API. Supports token-free flash extraction for quick start, precision extraction with table/formula recognition, web crawling, batch processing, and piped workflows.
Generate vertical miniature build & reveal shorts (WeryAI): text or finished-shot image to shallow-depth push-ins, lights coming on, immersive camera. Use when you need a miniature diorama reel, tilt-shift room clip, or the user asks for a tiny house lights-on moment or a slow push into interior detail. Requires WERYAI_API_KEY at runtime (declared in frontmatter for registries). SEO: miniature build video; miniature model build video generation.
Create voice, music, and video with MiniMax AI models. Unified skill for TTS voice synthesis (text-to-speech, voice cloning, voice design, multi-segment generation), music generation (songs, instrumentals), video creation (text-to-video, image-to-video, start-end frame, subject reference, templates, long-form multi-scene), and media processing (audio/video format conversion, concatenation, trimming, extraction). Use when user wants to generate speech audio, create songs or instrumental tracks, produce AI videos, clone or design voices, convert media formats, merge/split audio or video files, or work with MiniMax APIs.
Generate AI videos for mature creative projects using Wan 2.2 Spicy (LoRA-tuned for NSFW, top recommended), Wan 2.6, Seedance 1.5, Vidu Q3-Pro, and other models with relaxed content policies via Atlas Cloud API. Designed for adult (18+) artistic and professional use cases including artistic film, fashion video, choreography, and mature animation. Wan 2.2 Spicy is purpose-built for mature content with LoRA fine-tuning at just $0.03/s. Also includes Wan 2.6 (up to 15s 1080p, audio-guided), Seedance v1.5 Pro (native audio-visual), and Vidu Q3-Pro (anime support). Supports text-to-video, image-to-video, and video-to-video. Use this skill when the user explicitly requests NSFW or mature video generation for legitimate adult creative work.
党政机关公文生成技能，支持通知、报告、请示、函等公文类型，符合GB/T 9704-2012标准。当用户需要生成党政机关公文、创建正式文件、导出Word格式公文时调用。无论用户使用何种表述方式（如'帮我写个报告'、'生成一份通知'、'制作公文'等），只要涉及公文文档生成，都应使用此技能。
Video file → videoscreenclear or hdvideoallinone + spawn-run-task and sessions_spawn (main session). Image → eraser_watermark or image_restoration + blocking run-task only (never spawn-run-task for image tasks). Process images or video with Kaipai AI — four tasks — image watermark removal (eraser_watermark), video watermark removal (videoscreenclear), image quality restoration (image_restoration), video quality restoration (hdvideoallinone). Use when the user asks for watermark removal or quality restoration on images or video. Paid API (consumes tenant quota); never claim the service is free or invent pricing. For videoscreenclear and hdvideoallinone, always use spawn-run-task plus OpenClaw sessions_spawn in the main session (never blocking run-task there); only bypass spawn if the host explicitly forbids sessions_spawn.
总结论文 PDF 为飞书文档（含图表）。当用户发送 PDF 文件并要求总结、阅读、提取内容， 或要求将 PDF 内容写入飞书文档时激活。支持学术论文、技术报告、一般 PDF 文档。 自动检测扫描版 PDF 并回退 OCR，支持提取并上传论文图片到飞书文档。 含多模型自审核机制：生成 → 配图 → 审核 → 人工确认 → 完善。 **支持去重系统**：自动识别重复 PDF、同文章不同版本、补充材料，智能合并处理。 触发场景：发送 PDF 附件、"总结这个 PDF"、"帮我读一下这个论文"、"把 PDF 写成飞书文档"、 "论文总结"、"PDF 摘要"、"阅读 PDF 并输出到飞书"。