download-gemini-images — Claude Code skill: pull images out of Gemini
This skill downloads images from an open Gemini chat through your logged-in Chrome session and packages them into a ZIP in thread order.
npx skills add daymade/claude-code-skills --skill download-gemini-images -a claude-codeWhat download-gemini-images does
It opens Gemini image lightboxes and grabs the larger displayed files rather than the thumbnail previews on the page. Everything runs through the Chrome plugin, because Gemini conversations normally need your existing Google session. A fresh unauthenticated browser gets you nowhere here.
The flow: the skill claims the Gemini tab you already have open, or opens the URL you provide, then imports scripts/download_gemini_images.mjs inside a node_repl session and starts the download. Files come out named in thread order — image_01.jpg, image_02.jpg, and so on. Packaging is handled by scripts/package_images.sh, which builds the ZIP, runs zip -T, and checks the archive holds the same ordered files as the directory.
If lightbox automation fails while the page is visibly loaded, there is a fallback through pageAssets. It usually returns 512px preview JPEGs instead of the larger lightbox files, and the skill tells you when it takes that route. Should Gemini ask for a login, the run pauses until you sign in through Chrome.
What it helps with
- pull every image out of a long Gemini thread in one pass
- get the larger displayed files instead of preview thumbnails
- bundle the downloads into a ZIP that keeps thread order
- rename files in sequence instead of leaving random download names
- grab chat images without leaving your Google session
Example prompts for the agent
- download all the images from this Gemini chat and zip them
- export the images from gemini.google.com/app, I expect 20
- save the images from my open Gemini tab in order
How to install download-gemini-images
1Skills CLI (Vercel)
npx skills add daymade/claude-code-skills --skill download-gemini-images -a claude-code2Manually: put the files in place
~/.claude/skills/download-gemini-images/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/download-gemini-images/
1Skills CLI (Vercel)
npx skills add daymade/claude-code-skills --skill download-gemini-images -a codex2Manually: put the files in place
.agents/skills/download-gemini-images/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add daymade/claude-code-skills --skill download-gemini-images -a cursor2Manually: put the files in place
.cursor/skills/download-gemini-images/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install daymade/claude-code-skills download-gemini-images2Manually: put the files in place
.github/skills/download-gemini-images/SKILL.md1Skills CLI (Vercel)
npx skills add daymade/claude-code-skills --skill download-gemini-images -a gemini-cli2Platform CLI
gemini skills install https://github.com/daymade/claude-code-skills --path download-gemini-imagesManually: put the files in place
.devin/skills/download-gemini-images/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add daymade/claude-code-skills --skill download-gemini-images -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about download-gemini-images
How do I install download-gemini-images in Claude?
Run npx skills add daymade/claude-code-skills --skill download-gemini-images -a claude-code. The skill lands at ~/.claude/skills/download-gemini-images/SKILL.md.
What does download-gemini-images do?
It downloads images from a Gemini conversation using your logged-in Chrome session, opening lightboxes to reach the larger files, and packages them into a ZIP named in thread order.
What happens if lightbox automation fails?
The skill falls back to pageAssets and collects previews. Those are usually 512px JPEGs rather than the larger lightbox files, and the skill reports that it used the fallback.
Source text
SKILL.md · MIT
---
name: download-gemini-images
description: Download, export, save, or package images from a Google Gemini conversation/chat/app page, especially uploaded images or generated image previews visible in a Gemini thread. Use when the task needs logged-in Chrome/Gemini state, opening Gemini image lightboxes, downloading the larger displayed image files, renaming them in order, and producing a ZIP archive.
---
# Download Gemini Images
## Overview
Download Gemini conversation images from the user's logged-in Chrome session. Prefer the lightbox image over thumbnail/page-preview assets because Gemini often exposes a larger `blob:` image only after the user opens a preview.
## Workflow
1. Use the Chrome plugin, not a fresh unauthenticated browser, because Gemini conversations usually require the user's existing Google session.
2. Bootstrap Chrome per the Chrome skill, claim the already-open Gemini tab if it exists, or open the user-provided Gemini URL in Chrome.
3. Import and run `scripts/download_gemini_images.mjs` from a `node_repl` JS call after `browser` is available.
4. Package the output directory with `scripts/package_images.sh`.
5. Report the ZIP path, image count, and any lower-resolution fallback.
6. Finalize Chrome control after downloads are complete, keeping the user's original Gemini tab open when appropriate.
## Main Script
Resolve the script path relative to this skill directory, then import it in the same Node REPL session used for Chrome automation:
```js
var { downloadGeminiImagesFromChrome } = await import("/absolute/path/to/download-gemini-images/scripts/download_gemini_images.mjs");
var result = await downloadGeminiImagesFromChrome({
browser,
tabUrlIncludes: "gemini.google.com/app",
expectedCount: 20,
outputDir: `${nodeRepl.homeDir}/Downloads/gemini_conversation_images_${new Date().toISOString().slice(0, 10).replaceAll("-", "")}`
});
nodeRepl.write(JSON.stringify(result, null, 2));
```
Set `expectedCount` only when the user gave a specific count. Omit it to download every visible `Show the uploaded image in a lightbox` button.
## Packaging
After the main script returns `outputDir`, run:
```bash
/absolute/path/to/download-gemini-images/scripts/package_images.sh "$outputDir" "$HOME/Downloads/gemini_conversation_images.zip"
```
The packaging script creates the ZIP, runs `zip -T`, and verifies that the archive contains the same ordered image files as the directory.
## Fallback
If lightbox automation fails but the page is visibly loaded, use the tab `pageAssets` capability:
```js
var pageAssets = await tab.capabilities.get("pageAssets");
var inventory = await pageAssets.list();
var uploaded = inventory.assets.filter(a => a.kind === "image" && a.url.includes("lh3.googleusercontent.com/gg/"));
var bundle = await pageAssets.bundle({ inventoryId: inventory.id, assetIds: uploaded.map(a => a.id) });
nodeRepl.write(JSON.stringify(bundle, null, 2));
```
This usually captures 512px preview JPEGs, not the larger lightbox files. Tell the user when this fallback is used.
## Notes
- Do not inspect browser cookies, local storage, passwords, or session stores.
- Downloading files is an inbound transfer and does not require confirmation by itself.
- If Gemini asks the user to log in, pause and ask the user to complete login in Chrome.
- If the user wants the images in the same order as the thread, use the script's ordered names: `image_01.jpg`, `image_02.jpg`, etc.
© daymade · MIT · daymade/claude-code-skills