Sample of using a Gemini Managed Agent to do anything
This repository also configures its own agents. See what gemini-anything-agent tells them →
LyalinDotCom/gemini-anything-agent
Skill Claude CodeCodex
Use this skill when the user asks you to open or navigate a website in a real browser, interact with a page, test a user flow, take a webpage screenshot, inspect browser console or network activity, emulate a device, save browser state, mock a request, or collect a browser trace, video, or PDF.
LyalinDotCom/gemini-anything-agent
Skill Claude CodeCodex
Supply the visual grammar and scene plan for an original, detailed Dr. Seuss inspired world using the generic large-image skill. Apply only when this world example or style is requested.
LyalinDotCom/gemini-anything-agent
Skill Claude CodeCodex
Generate images, video, speech or music, transcribe media, and manage Gemini files or delegated agents through Google's official Gemini API CLI.
LyalinDotCom/gemini-anything-agent
Skill Claude CodeCodex
Create genuinely large, detailed images by generating coordinated regions with the official Gemini API CLI and composing them with native tools. Use for large illustrations, panoramas, murals and explorable worlds; apply a separate world pack only when requested.
LyalinDotCom/gemini-anything-agent
Skill Claude CodeCodex
Create a full-circle photographic 3D View from Gemini-generated views inside the managed Linux agent, preserving identity and transparency and packaging in Blender and GLB.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: