Give your agent eyes — capture screenshots, voice, and annotations from any screen, monitor, or device via MCP.
Complex document parsing with PaddleOCR. Intelligently converts complex PDFs and document images into Markdown and JSON files that preserve the original stru...
Facilitates structured multi-agent debates with opposing expert views, a referee moderator, and 9 specialized AI council votes for balanced decision-making.
Complete genviral Partner API automation. Create and schedule posts (video + slideshow) across TikTok, Instagram, and any supported platform. Includes slides...
Driven Intent Negotiation — Contract-Oriented Deterministic Executable Runtime IMPORTANT: > - **Using Claude Code?** → Install the [Plugin](#-claude-code-plugin-recommended-for-claude-code) (eas
Enables AI agents to develop independent, evolving personas through organic memory growth, self-reflection, and layered memory management.
Fetch articles from Karpathy's curated 93 RSS feeds and generate a Chinese tech daily newsletter. Triggers: RSS 日报、RSS 简报、karpathy-curated-rss-brief、每日简报、Kar...
Detect and remove AI fingerprints from AI-generated images. Strip metadata, add film grain, recompress, and bypass AI image detectors. Works with Midjourney,...
Assist startups in securing venture capital from top-tier VCs by evaluating potential, crafting narratives, identifying and ranking investors, and managing o...
Build, inspect, adapt, and validate color systems, palettes, tokens, contrast, color-space choices, and cross-surface color behavior for UI, branding, charts...
Intelligently recommends optimal AI models based on task requirements. Dynamically reads the user's OpenCLAW configuration and provides context-aware model s...
智谱 GLM-4.6V 多模态视觉模型集成插件。支持本地图像解析（Base64）及公网链接读取。优先提供 zai SDK 接入，并包含 cURL 原生降级方案。
AI-powered avatar accessory synthesis — automatically analyzes art style, lighting, and angle to seamlessly add hats and headwear to any avatar image.
Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents
One-click business proposal package generator. Takes a brief project/service description and generates a COMPLETE ready-to-send package: proposal (.docx), pi...
自动分析视频内容，提取关键帧进行AI视觉分析。支持 Windows、macOS 和 Linux。首次使用自动从GitHub下载对应平台的工具脚本。
Passive journaling skill that scans daily conversations via cron to generate markdown journals using semantic understanding. Use when: - User requests journa...
Production-grade OCR with intelligent engine selection. Tesseract (lightweight, fast) and PaddleOCR (high accuracy, Chinese-optimized). Use when extracting t...
Extract brand identity (colors, typography, visual style, imagery) from any website URL. Scrapes the site, analyzes CSS/images with K-means and VLM, and retu...
Control the Linux desktop GUI using xdotool, wmctrl, and dogtail. Use when you need to interact with non-browser applications, simulate mouse/keyboard input, manage windows, or inspect the UI hierarch
Access to RDK X5 /app folder resources including GPIO, multimedia, AI samples. Invoke when user wants to run embedded demos or control hardware on RDK X5.
Document intelligence: categorize, autofill forms, analyze contracts, scan receipts/invoices, analyze bank statements, parse resumes/CVs, scan IDs/passports...
Caravo is the first service marketplace built for autonomous AI agents — featuring 200+ ready-to-use services across categories: AI Models, Search, Data & An...
自动遍历下载文件夹或桌面，利用视觉模型“看”文件内容并重命名，最后归档到指定分类目录。