Chatgpt Search
Search ChatGPT and extract structured response data via Chrome remote debugging
What You Can Do
You can automate ChatGPT searches by attaching Claude to a running Chrome instance, submitting queries, and extracting the full response payload including streamed messages, UI hydration data, and network API calls. This enables you to integrate ChatGPT results directly into your workflows, analyze response structure, or build data pipelines that depend on ChatGPT's output without using the official API.
Features
attaches to Chrome port 9222 to control browser automation
waits for complete ChatGPT message streaming and extracts full text output
retrieves the underlying JSON data structure that powers ChatGPT's UI rendering
captures all HTTP calls made during the query for analysis and integration
extracts structured data from product recommendations and search cards
maintains stable browser sessions across multiple searches with automatic Chrome launch
returns all data in a single formatted object for easy downstream processing
Example Output
Query: "Best practices for Node.js error handling"
Output structure:
{
"messages": [
{
"role": "user",
"content": "Best practices for Node.js error handling"
},
{
"role": "assistant",
"content": "Here are key error handling patterns..."
}
],
"productCards": [
{
"title": "Error Handling Guide",
"url": "https://nodejs.org/en/docs/guides/error-handling/"
}
],
"hydrationJson": { /* full UI state JSON */ },
"apiCalls": [
{
"method": "POST",
"url": "https://api.openai.com/v1/chat/completions",
"status": 200
}
]
}
What's Included
- SKILL.md instruction file with Chrome remote debugging setup:
- Chrome launch script with automatic profile cloning:
- Network logging and session management workflow:
- Browser automation commands (new_session, enable_network_log, new_tab):
- Response parsing templates for messages, hydration JSON, and API calls:
Who It's For
- Backend engineers building ChatGPT integration pipelines
- Data scientists automating research and insight extraction from ChatGPT
- DevOps engineers automating browser-based workflows
- Security researchers analyzing ChatGPT API behavior and response structure
- Business analysts collecting competitive intelligence or market research at scale
Best For
- Automated ChatGPT query execution without API rate limits
- Extracting and analyzing ChatGPT's underlying response structure and hydration data
- Building headless workflows that depend on ChatGPT search results
- Network-level monitoring of ChatGPT API calls for debugging or compliance
- Scraping product recommendations and structured data from ChatGPT responses
You might also like
When a user uploads a file to Claude, you can intelligently detect its type and read it using the appropriate method. Instead of blindly running cat on binary files or loading massive CSVs into context, this skill routes each file type to the right tool, reading only what's needed to answer the user's question. You'll extract text from PDFs, parse structured data from CSVs and JSON, process images, and decompress archives—all without wasting context or producing garbage output.
by seifbenayed
You can formally verify mathematical proofs by translating theorems into Lean 4 code, leveraging Mathlib's extensive library of formalized mathematics. The skill guides you through researching existing lemmas, designing proof strategies, testing approaches, implementing formal proofs, and verifying correctness—turning informal mathematical claims into machine-checked theorems without requiring deep Lean syntax expertise.
by parcadei
You can read PDFs directly from disk, extract text and embedded content, identify document structure (text-based vs. scanned), list images and attachments, and choose the right extraction strategy based on document type. This skill helps you understand what's in a PDF before processing it, diagnose extraction issues, and pull specific content like tables, forms, and embedded files.
by seifbenayed
You can perform end-to-end PDF operations including extracting text and metadata from documents, merging multiple PDFs into a single file, splitting PDFs by page ranges, filling fillable forms programmatically, and adding text overlays to non-fillable PDFs. This skill handles both simple read operations and complex document workflows, making it essential for document processing, form automation, and PDF batch operations.
by seifbenayed
You can systematically verify licensing compliance across music compositions, calculate accurate mechanical royalties against current statutory rates, and generate audit-ready documentation that satisfies internal controls and external audit demands. This skill consolidates manual spreadsheet workflows into a structured, repeatable process with built-in error detection and cross-referencing against NMPA rates, licensing agreements, and regulatory requirements.
by seifbenayed
You can design complete REST API specifications from requirements, translating them into resource-oriented endpoint architectures that follow industry best practices. Claude generates OpenAPI 3.0 schemas with validated request/response definitions, ensures correct HTTP method semantics and status code usage, and produces Swagger documentation ready for Swagger UI, ReDoc, or Postman integration. Catch design anti-patterns and naming inconsistencies before implementation.
You can systematically identify all licensing requirements for a musical work across multiple territories, coordinate approvals from rights holders and collection societies, and generate legally compliant clearance letters and license terms. This skill maps composition rights (mechanical, performance, synchronization) and sound recording rights (master use, digital performance) while accounting for territory-specific regulations like EU directives, UK post-Brexit rules, and jurisdiction-specific collection society requirements.
by seifbenayed
Query your local Screenpipe instance to retrieve screen recordings, audio transcriptions, UI element accessibility trees, keyboard/mouse input logs, and productivity analytics. You can search by keywords, filter by content type (audio, OCR, accessibility, input), set time ranges, and extract structured data about your applications, meetings, and work sessions without sending data to external servers.
by az9713