skills.rest
kzarzycki
kzarzyckiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

chatgpt-deep-research

Execute ChatGPT Deep Research tasks and extract cited Markdown reports.

Updated Feb 19, 2026
Search Tags:#markdown#research#web automation#chatgpt#deep research#cited sources#report extraction
One-click install
npx skills add https://github.com/kzarzycki/agent-skills --skill chatgpt-deep-research-kzarzycki
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: chatgpt-deep-research
Source: https://github.com/kzarzycki/agent-skills/tree/main/research/skills/chatgpt-deep-research
Command: npx skills add https://github.com/kzarzycki/agent-skills --skill chatgpt-deep-research-kzarzycki

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

ChatGPT Deep Research knowledge gathering can be hard to operate consistently from a command-based workflow, especially when you need reliable submission, plan handling, and report extraction.

Core Features & Use Cases

  • Automated Deep Research submission: Navigates to ChatGPT Deep Research, inputs your research prompt, and triggers the research run using a Playwright-driven backend.
  • Plan and completion coordination: Waits for the plan to appear, handles auto-start behavior, monitors progress/completion signals, and times out safely when completion does not arrive.
  • Report extraction to Markdown: Extracts the finished Deep Research report from the nested sandboxed iframe and converts it to clean Markdown you can reuse.

Quick Start

Ask your agent to run the skill for the prompt file and return the resulting Deep Research report as a Markdown file.

Frequently Asked Questions about chatgpt-deep-research

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

FAQPage Schema
How do I automate ChatGPT Deep Research to extract a cited Markdown report?▼

To automate ChatGPT Deep Research extraction, this Skill delegates your prompt to chatgpt.com via a playwright-cli backend, monitoring completion signals to output a structured Markdown report with cited sources.

What is the best way to run multi-step investigative tasks like market analysis from an automated workflow?▼

For multi-step investigative tasks like market analysis, delegated execution of ChatGPT Deep Research automates prompt submission, handles plan coordination, and extracts source-backed reporting directly into your workflows.

Does web automation for ChatGPT Deep Research require a specific browser backend?▼

Web automation for ChatGPT Deep Research requires a playwright-cli backend to drive chatgpt.com, navigate nested sandboxed iframes, and detect platform DOM status signals for safe completion timeouts.

How do I handle completion detection and timeouts when extracting a Deep Research report?▼

To handle completion detection and timeouts when extracting a Deep Research report, the Skill monitors platform DOM progress signals, waits for the plan to appear, and times out safely if completion does not arrive.

Can I convert a finished Deep Research report to clean Markdown for reuse?▼

You can convert a finished Deep Research report to clean Markdown by extracting the content directly from the nested sandboxed iframe, making it immediately reusable for source-backed reporting.

Why does my Deep Research report extraction fail when waiting for completion in an automated workflow?▼

Deep Research report extraction may fail or time out if the platform DOM status signals do not indicate completion, or if the nested iframe extractor encounters issues during the plan and completion coordination phase.

Related Skills

Explore More Education & Research Skills→
paialexpaialex
1

playwright

Automate browser tasks from the terminal using Playwright CLI.

Community
Intermediate
Blake-JohnBlake-John

pymupdf

Convert PDF documents into Markdown, JSON, and text for LLM workflows.

Community
Intermediate
yigitkonuryigitkonur
11

run-agent-browser

Drives browser automation via agent-browser CLI for navigation, DOM interaction, sessions, tabs, screenshots, and data extraction.

Community
Intermediate
langchain-ailangchain-ai
27.5k

web-research

Orchestrate multi-source web research with parallel subagents and cited reports.

Official
Advanced