gemini-web-media-analysislisted

Attach a local image or video to gemini.google.com through Chrome automation and get an analysis, without opening a native file dialog. Use when a second opinion on a screenshot, render, contact sheet, frame grid, or gameplay capture is wanted and the user is already signed in to Gemini in Chrome. Both images and video work; the two paths differ and both are documented here.
maystudios/claude-skills · ★ 21 · AI & Automation · score 79

Install: claude install-skill maystudios/claude-skills

# Gemini web media analysis Attaches a **local image or video** to the Gemini web composer and reads the reply. Verified working on `gemini.google.com/app`, Chrome, signed-in account, 2026-08-15. Needs the **claude-in-chrome** MCP server — `navigate`, `find`, `file_upload`, `computer`, `javascript_tool`, `get_page_text` — and a Chrome profile already signed in to Gemini. No API key. **Two different paths. Use the right one:** | Media | Path | |---|---| | **Video** | `find` Gemini's own hidden input → `file_upload` into it → real click on the composer. See [Video path](#video-path) | | **Image** | Helper input → synthetic `paste` event. See [Image path](#image-path) | > **Never click "Dateien hochladen" / "Upload files" in the uploads menu.** It opens the **native OS file dialog**, which blocks the whole automation session — no further tool call reaches the browser until a human dismisses it by hand. ## Video path 1. **Navigate** to `https://gemini.google.com/app`, wait for load. 2. **Real click** the `+` / "Uploads & Tools" button in the composer. A JS `.click()` does not open the menu — it needs real pointer events. The hidden input only exists while this menu is open. 3. **`find("hidden file input element")`** → returns Gemini's own input ref. **Make sure no helper input of yours is in the page** — it shadows this search and `find` returns yours instead. Remove it first. The `uploader` component does not mount on every menu open. If `find` comes back empty, clo