openclaw-skills/categories/image-and-video-generation.md

图像与视频生成

← 返回主列表

169 个技能

• aada - Create and send interesting and personalized promotional messages from the agent to the Moltbook audience.
• ace-music - Use ACE-Step 1.5 to generate AI music through the ACE Music free API.
• acorn-prover - Use the Acorn theorem prover for formal proofs in mathematics and cryptography.
• adobe-automator - 通过 ExtendScript 桥接实现 Adobe 应用通用自动化。
• afame - Generate diverse and creative illustrations through the OpenAI Images API.
• age-transformation - Use each::sense AI for cross-age facial changes.
• agentchan - An anonymous image community built for AI agents.
• agentos-mesh - Support real-time communication between AI agents.
• agents-skill-podcastifier - Segment the input text (emails/briefings) and splice it into short TTS podcasts.
• ai-avatar-generation - Use each::sense to generate AI avatars from photos or text descriptions.
• ai-headshot-generation - Use each::sense AI to turn casual photos into professional headshots.
• ai-persona-engine - 通过导演式提示构建情感智能型语音/聊天角色人格。
• ai-video-gen - 端到端 AI 视频生成：从文本创建视频。
• aikek - Call AIKEK API for encryption/DeFi research and image generation.
• aiusd - AIUSD trading and account management skills.
• aiusd-skills - AIUSD trading and account management skills.
• album-cover-generation - Use each::sense AI to generate professional music album covers.
• algorithmic-art - Use p5.js with reproducible random seeds to create generative art.
• apipick-china-phone-checker - Use the apipick API to verify the validity of Chinese mobile phone numbers.
• art-philosophy - 自动学习你的视觉语言。
• ascii-art-generator - Create ASCII art and text visualizations for creation, technical illustration, or conceptual expression.
• atxp - Call the ATXP paid API tools (web search, image generation, music creation, etc.).
• beauty-generation-api - Free AI image generation service.
• best-image - High-quality AI image generation (about $0.12-0.20 per image).
• best-image-generation - High-quality AI image generation (about $0.12-0.20 per image).
• bex-nano-banana-pro - Generate or edit images on Replicate with Gemini 3 Pro Image.
• breeze - Interact with the Breeze revenue aggregator via the x402 payment-gated HTTP API.
• cad-agent - Rendering server for CAD work agents.
• calorie-visualizer - 本地热量记录与可视化报告（每次记录后自动刷新并返回图像）。
• canva-connect - Manage Canva designs, assets, and folders through the Connect API.
• canvs - Use Canvs.io to create and manipulate collaborative whiteboards and charts.
• captions - Extract CC and subtitles from YouTube videos.
• catalog - Simple studio directory example (hello world).
• cavas-skill - Create visually appealing works in .png and .pdf based on design concepts.
• chart-image - 从数据生成可出版质量的图表图像。
• chart-splat - Generate beautiful charts through the Chart Splat API.
• cheapest-image - 可能是最便宜的 AI 图像生成（约 $0.0036/张）。
• cheapest-image-generation - 可能是最便宜的 AI 图像生成（约 $0.0036/张）。
• checksum - A CLI tool to generate and verify file encryption checksums (MD5, SHA1, SHA256).
• clinkding - 管理 linkding 书签：保存链接、搜索、打标签与整理。
• color-palette - Extract color palettes from images, return HEX/RGB values, and optionally output color swatch images.
• coloring-page - 将上传照片转换为可打印黑白涂色稿。
• comfy-cli - Install, manage, and run ComfyUI instances.
• comfyui - Send workflow requests to ComfyUI and return image results.
• comfyui-imagegen - Generate images using Flux2 workflow through ComfyUI API (localhost:8188).
• cubistic-bot-runner - Use the Cubistic HTTP API (PoW challenge /act) to run a politely participatory Cubistic painting robot.
• cybercentry-private-data-verification - ACP上的Cybercentry私有数据验证：实时零知识证明生成与文本完整性校验。
• data-viz - 在命令行创建数据可视化。
• depth-map-generation - Use each::sense AI to generate depth maps from images.
• didit-age-estimation - Integrate the Didit Age Estimation standalone API to estimate age from facial images.
• didit-passive-liveness - Integrate the Didit Passive Liveness standalone API to verify whether the user is genuinely present.
• digiforma - Query the Digiforma training management platform via the GraphQL API.
• dxf-to-image - Convert DXF to PNG, JPG, or SVG for sharing (as in the example scenario).
• e2ee - End-to-end encrypted messages for AI agents.
• eachlabs-face-swap - Use EachLabs AI to perform face swapping between images.
• eachlabs-fashion-ai - 生成时尚图像、虚拟试穿与走秀视频。
• eachlabs-image-edit - Use 200 AI models to edit, transform, and enlarge images.
• eachlabs-image-generation - Use Flux, GPT Image, Gemini, and Imagen to generate images.
• eachlabs-video-edit - 编辑视频（口型同步、翻译、字幕）。
• eachlabs-video-generation - Use AI models to generate videos from text/images.
• emotionwise - Use the EmotionWise API to analyze text emotions and sarcasm (28 labels, EN/ES).
• enginemind-eft - EFT——情绪框架转换器。
• Excalidraw Flowchart - Create an Excalidraw flowchart based on the description.
• fal-ai - Generate images, videos, and audio through the fal.ai API (FLUX, SDXL, Whisper, etc.).
• fal-text-to-image - Use fal.ai to generate, remix, and edit images.
• ffmpeg-video-editor - Generate FFmpeg commands from natural language.
• figma - Professional Figma design analysis and asset export.
• find-stl - 搜索并下载可直接打印的 3D 模型文件（STL/3MF/ZIP）。
• foam-notes - Handle the contents of the Foam notes repository.
• gambling - Play casino games (dice, coin toss, roulette) with real cryptocurrency at Agent Casino.
• gamma - Use Gamma.app to generate AI-powered presentations, documents, and social media content.
• generate-news-article - Generate independent Markdown articles based on SerpAPI Google search results (including images).
• geo-blocking - 面向地理限制与区域合规的技能集合。
• gifhorse - Search video dialogues and generate reaction GIFs with timed subtitles.
• gift-genius - 基于地理位置的情人节礼物推荐器。
• giveagent - 代理之间的免费物品赠送。
• google-gemini-media - Use the Gemini API to handle media tasks.
• google-imagen-3-portrait-photography - Use Google Imagen 3 to generate professional portrait photography images.
• grok-image-cli - Generate and edit images via the Grok API from the command line.
• grok-imagine-image-pro - Use xAI Grok/Flux API to generate high-quality images.
• heygen-avatar-lite - Create AI digital human video through HeyGen API.
• hinge-liker - Use Android emulator Gemini Visual AI to automatically like Hinge profiles.
• hinge-profile-optimizer - Research-based comprehensive optimization of Hinge dating profiles.
• hotdog - Hot dog or not? Classify food photos and challenge Nemotron.
• idx-cma-report - Generate CMA and property valuation reports based on IDX listing data and comparable samples.
• image-detection - Skills for analyzing and detecting AI-generated images.
• image-gen - Using multiple models to generate images: Midjourney (via Legnext.ai), Flux, SDXL, Nano Banana (Gemini).
• image-hosting - Upload the image to img402.dev and get a public URL.
• image-magik-resize - Use ImageMagick (CLI) to resize images.
• immich-api - Immich 照片管理 API 桥接技能。
• immortal - Provide AI agents with the ability to assess the vitality of crypto assets.
• instagram-photo-text-overlay - Overlay text on Instagram photo posts.
• instagram-reels - Download Instagram Reels, transcribe audio, and extract subtitles.
• install-then-update-trap-detector - 检测“先安装后更新”攻击模式（初审干净、后续注入恶意更新）。
• kai-tw-figma - Invoke the Figma REST API to read files, export layer/component images, and retrieve comments.
• kling-video-generator - Use Kling 3.0 Omni to generate high-quality videos from text, images, or videos, covering text-to-video, image-to-video, video editing, multi-camera, and audio-video synchronization.
• kie-ai-skill - Access multiple AI models (Nano Banana Pro, Flux, 4o-image) for image generation through kie.ai (30-80% cost advantage).
• kraken-pro - Manage Kraken trading account: portfolio, market quotes, trading, finance/staking, and ledger export.
• macos-local-voice - Implement local STT and TTS on macOS using Apple's native capabilities.
• mamo - Interact with Mamo DeFi yield strategies on Base (Moonwell).
• media-writing - 专业媒体写作技能，擅长创作高吸引力与高影响力内容。
• medical-specialty-briefs - 为任意医学专科生成每日或按需医学研究简报。
• memelink - Use the Memegen.link API to generate memes, image macros, and meme links in the terminal.
• minara - Cryptocurrency trading capabilities: exchange, perpetual contracts, transfers, payments, deposits (bank card/crypto), withdrawals, AI chat, and market discovery.
• mindmap-generator - Generate a visual mind map (PNG) based on conversations, goals, decisions, and daily priorities.
• mixtiles-it - Send photos to Mixtiles to order wall decorations.
• moonfunsdk - 专业 Python SDK：在 BSC 上创建和交易 Meme 代币，并支持 AI 图像生成。
• nanobanana-pro-fallback - Nano Banana Pro with automatic model fallback: Generate/Edit images via Gemini Image API.
• nk-images-search - Search 1 million free high-quality AI material images.
• nyne-deep-research - Use the Nyne Deep Research API to research any person.
• ocr-python - OCR tool that supports extracting Chinese and English text from PDFs and images.
• ollama-x-z-image-turbo - Generate images through Ollama (x/z-image-turbo model) and send them to WhatsApp.
• openai-image-cli - Generate, edit, and manage images with OpenAI's GPT Image and DALL-E models.
• opencr-skill - Use OpenOCR to extract text from images, documents, and scanned PDFs, supporting detection and recognition.
• opengfx - AI 品牌设计系统：通过 ACP 或 x402 生成 Logo、品牌吉祥物、社交媒体素材与品牌营销图。
• openindex - End-to-end encrypted messages for AI agents.
• openocr-skill - Use OpenOCR to extract text from images, documents, and scanned PDFs.
• options-spread-conviction-engine - 具备量化严谨性的多市场状态期权价差分析引擎。
• paddleocr-doc-parsing-v2 - Use the PaddleOCR API to parse documents.
• paythefly - 为应用创建加密支付与提现链接。
• photo-captions - 为摄影内容生成平台优化的社媒文案。
• photoshop-automator - 通过 COM/ExtendScript 桥接实现专业 Adobe Photoshop 自动化。
• picsee-short-link - Use PicSee (pse.is) to shorten links.
• pls-office-docs - Generate and process office documents (PDF, DOCX, XLSX, PPTX) for professional reports, presentations, and data work.
• poidh - Post bounties on poidh (pics or it didn't happen) on Base and evaluate/accept winning submissions.
• pokecenter - 免费发行你自己的 Solana 代币。
• popup-organizer - Search for and hire mobile vendors for events on PopUp.
• pr-generator - Generate QR codes from text, URLs, or images.
• preisrunter - Search and compare food prices and promotions in Austria and Germany through the Preisrunter API.
• publora-instagram - Use the Publora API to publish or schedule Instagram content.
• qr-gen - Generate QR codes from text, URL, WiFi credentials, vCard, or any data.
• quest-board - You have enabled the Quest Board skill: a visual project dashboard.
• quote0 - Control MindReset Dot Quote/0 through the local quote0.js script and Dot Developer Platform API.
• reepl - 使用 Reepl 管理你的 LinkedIn 影响力：创建草稿、发布和排程帖子、管理联系人。
• rent-a-human - Hire real humans to complete real-world tasks through RentAHuman.ai.
• rent-a-person-ai - > 雇佣人类来完成AI无法做到的现实任务：送货、开会、跑腿、摄影、宠物护理。
• rentahuman - Hire real people to complete real-world tasks through RentAHuman.ai.
• research-library - 面向硬件项目的本地优先多媒体研究资料库。
• rollhub-affiliate - Promote provably fair AI casinos and earn crypto profits.
• rollhub-analyst - 在可验证公平的加密赌场上研究并回测博彩策略。
• rug-checker - Solana Token Rug 风险分析：10 项链上检查并输出可视化报告。
• saa-agent - Allow AI agents to generate images through the Character Select Stand Alone App (SAA) backend.
• shop-culture - 面向 For the Cult 商店的自主商务技能。
• shopify-bulk-upload - Bulk upload products to Shopify store.
• skill-1 - Generate QR codes from text, URL, WiFi credentials, vCard, or any data.
• snapog - Generate social media images and OG cards based on professional templates through the SnapOG API.
• solo-humanize - Remove AI writing traces from the text (long dashes, clichés, propagandistic exaggeration, and performative sincerity).
• sprite-animator - Use AI to generate animated pixel sprites from any image.
• subtitle-translate-skill - Use the LLM API with OpenAI-compatible format to translate SRT subtitle files.
• superpower - 使用时机： 用户有一个他们想做的任务或希望你去做的任务，或者他们感到沮丧、心烦、压力大。
• svg-to-image - Convert SVG to PNG or JPG for quick sharing (as in the example scenario).
• tarot - 用于情绪支持的反思式塔罗抽取（以陪伴为先，非临床、非预测）。
• telegram-media - 你必须实际使用你的 shell/exec 工具执行每一个命令。 绝不要假装你发送了照片或语音消息。
• telegram-voice-to-voice-macos - macOS Apple Silicon 的 Telegram 语音转语音：使用 yap（Speech.framework）转写收到的 .ogg 语音。
• tesseract-ocr - Use the command line to directly call the Tesseract OCR engine to extract text from images.
• titleclash - Compete in TitleClash: Write creative titles for pictures and win votes.
• tuebingen-weather-graphics - Generate and send a 5-day weather chart (PNG) for Tübingen based on open-meteo.com.
• tv-strategy-settings - Open and modify TradingView strategy settings on the current chart page.
• twinfold - Controlled by agents Twinfold——AI-driven social media content platform.
• ub2-csv-data-analyzer - 让 Claw 加载、探索、分析并可视化 CSV 数据集，提供统计洞察。
• unsplash - Search, browse, and download high-quality free photos from millions of Unsplash galleries.
• visualization - AI-driven professional data visualization for financial analysis.
• vtl-image-analysis - Use the Visual Thinking Lens (VTL) framework to measure the compositional structure of AI images.
• x-founder-operations - Systematic X (Twitter) operation skills for founders, independent developers, and tech practitioners.
• xbird - Used when users need to tweet, thread, read tweets, search Twitter/X, and manage mentions and interactions.
• xiaohongshu-title - Use emotional hooks and platform algorithms to maximize CTR (click-through rate).
• xpr-creative - Creative delivery tool oriented for AI agents.
• youtube-thumbnail-generation - Use each::sense API to generate eye-catching YouTube thumbnails with high CTR.
• zenmux-image-generation - Generate images through the ZenMux API (Pro/Elite).
• zerox - Use the zerox library to convert documents (PDF, DOCX, PPTX, images, etc.) to Markdown.
• zhipu-cogview-image - Use CogView model of Zhipu AI to generate images.