platform-chat

Collect and normalize AI platform responses from ChatGPT, DeepSeek, Gemini, and Qwen into JSON.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/opensourceways/geo-workflow --skill platform-chat
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: platform-chat
Source: https://github.com/opensourceways/geo-workflow/tree/main/.claude/skills/platform-chat
Command: npx skills add https://github.com/opensourceways/geo-workflow --skill platform-chat

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Collecting and standardizing AI platform responses from multiple web UIs (ChatGPT, DeepSeek, Gemini, and Qwen) for evaluation is tedious and error-prone. This Skill automates browser-based sampling and extraction, producing a consistent data format to support benchmarking and improvement work.

Core Features & Use Cases

  • Cross-platform web UI sampling: interacts with ChatGPT, DeepSeek, Gemini, and Qwen to gather responses and citations.
  • Automated data output: writes results to a unified responses.json compatible with the scoring engine.
  • Use Case: run periodic checks on a set of questions to monitor platform behavior and citation quality.

Quick Start

Run the skill to sample AI platform responses across ChatGPT, DeepSeek, Gemini, and Qwen and write the results to a centralized responses.json for evaluation.

Frequently Asked Questions about platform-chat

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser-based AI response collection from ChatGPT, DeepSeek, Gemini, and Qwen?

To automate browser-based AI response collection, use this skill to sequentially sample ChatGPT, DeepSeek, Gemini, and Qwen web UIs, extracting responses and citations into a unified JSON format for evaluation.

What is the best way to standardize AI platform responses for benchmarking?

The best way to standardize AI platform responses for benchmarking is to automate web UI sampling, normalize extracted text and citations, and write the results to a consistent JSON output compatible with scoring engines.

Does the browser automation skill require session tokens for web UI authentication?

Yes, the browser automation skill handles authentication via session tokens or environment credentials to access ChatGPT, DeepSeek, Gemini, and Qwen platforms for automated sequential sampling.

How does the skill handle AI platform responses with insufficient citations?

When AI platform responses lack sufficient citations, the skill enforces a minimum citation count by triggering automated follow-up queries through platform-specific scripts to gather the required data.

Can I use Playwright to extract citations from multiple AI platforms?

Yes, you can use Playwright with this skill to execute platform-specific scripts that query questions, extract responses and citations, and store results in a consistent JSON format suitable for evaluation.

What limitations exist when automating web UI sampling across different AI platforms?

Limitations of automating web UI sampling include platform-specific script requirements for ChatGPT, DeepSeek, Gemini, and Qwen, and the need to handle authentication via session tokens or environment credentials for successful extraction.