Automates Gemini web interactions through MCP tools, including image generation, text conversations, model switching, image uploads and downloads, session management, and troubleshooting.
通过 Gemini 官网（gemini.google.com）执行生图、对话等操作。用户提到"生图/画图/绘图/nano banana/nanobanana/生成图片"等关键词时触发。操作方式分三级优先级：首选 MCP 工具 → 次选 Skill 脚本 → 最次连接 Skill 浏览器手动操作（需用户授权）。禁止自行启动外部浏览器访问 Gemini。
Enables AI agents to automate browsers through the gsd-browser CLI, including navigation, form interaction, screenshots, live viewing, data extraction, assertions, testing, and ne…
Enables AI agents to navigate and interact with websites, fill forms, inspect pages, extract data, take screenshots, run assertions, and test web applications through the gsd-brow…
Guides agents in building an in-app, DEBUG-only SwiftUI capture system for reproducible marketing screenshots across locales, devices, appearances, full screens, and isolated comp…
Orchestrates parallel API workers for long-running or multi-turn batch tasks, with automatic worker, stagger, and batch sizing plus optional tiered model delegation and checkpoint…
Converts WeChat Official Account articles into clean Markdown files with YAML metadata, locally downloaded images, preserved code blocks, and extracted audio or video references.
Operates a Transistor.fm account through its v1 API, including show and episode browsing, draft-to-publish workflows, audio uploads, download analytics, private subscribers, and w…
Send and diagnose transactional email through Twilio SendGrid, inspect bounces and spam reports, and verify Signed Event Webhook signatures using a guarded, standard-library CLI.
Provides a Python CLI for browser-backed GET and POST requests, readiness checks, and FlareSolverr session management when sites present Cloudflare or DDoS-GUARD challenges.
