Menu
Run a Google Search and capture the AI response/Overview.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | google-ai-search |
| description | Run a Google Search and capture the AI response/Overview. |
This skill allows running a Google search query and capturing the AI Overview (SGE) response. It connects to a running Chrome instance via Chrome DevTools Protocol (CDP) to leverage the user's active session and authentication.
You must have Chrome running with remote debugging enabled on port 51673 (or specify a custom port).
To launch Chrome with remote debugging on Mac:
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=51673
node agents/skills/google-ai-search/scripts/google-ai-search.ts [--port <port>] <query>
Example:
node agents/skills/google-ai-search/scripts/google-ai-search.ts "how to use webusb in chrome extension"
The script will attempt to capture the AI response (either from network traffic or SGE DOM container) and save it as an HTML file in your ~/Downloads directory (e.g., ~/Downloads/aimode_how-to-use-webusb-in-chrome-.html).
Extract distilled page content as Markdown using Chromium's on-device ML page content annotation.
Fetch a URL using Playwright and convert its content to Markdown.
Gerrit helpers for fetching unresolved comments and CL diffs.
Set up or debug npm Trusted Publishing (OIDC) from GitHub Actions. Handles permissions, metadata validation, and provenance.
Paul's modern stack conventions for new projects (pnpm, native node test, esbuild, buildless-types). Consult when starting a new project or repository.
How to effectively use QMD (Quick Markdown Search) to pull in extra relevant context, run multi-query searches, extract high-scoring chunk IDs, and fetch their contents. Use this skill when asked to search across a large markdown knowledge base, run QMD queries, or retrieve deep context using the qmd CLI.