<h1 align="center">
<a href="https://prompts.chat">
- Deep research queries requiring ChatGPT's reasoning
Loading actions...
<a href="https://prompts.chat">
TypeScript and ESLint rules that MUST be followed when creating, modifying, or reviewing any file under apps/frontend/, including .ts, .tsx, .js, and .jsx files. Also apply when discussing frontend linting, type safety, or ESLint configuration.
risks
tabs_context_mcptabs_context_mcp(createIfEmpty: true)
If no ChatGPT tab exists:
tabs_create_mcp()
Note the tabId.
navigate(url: "https://chatgpt.com", tabId: <tabId>)
Wait 3-5 seconds for full load.
read_page(tabId: <tabId>, filter: "interactive")
textbox element)form_input may work, but computer(type) is more reliablecomputer(action: "left_click", ref: <textbox_ref>, tabId: <tabId>)
computer(action: "type", text: "<research_query>", tabId: <tabId>)
Query Crafting Tips for Research:
computer(action: "key", text: "Return", tabId: <tabId>)
computer(action: "wait", duration: 20-30, tabId: <tabId>)
computer(action: "screenshot", tabId: <tabId>)
get_page_text(tabId: <tabId>)
Save extracted text to project files for use in content pipelines:
Write tool → save to research/ or docs/ directory
Same conversation persists — just type follow-up in the same input:
computer(action: "left_click", ref: <textbox_ref>, tabId: <tabId>)
computer(action: "type", text: "<follow_up_query>", tabId: <tabId>)
computer(action: "key", text: "Return", tabId: <tabId>)
| Issue | Solution |
|---|---|
| Page takes long to load | Wait 5s after navigate, then read_page |
| Response still generating | Screenshot to check, wait if animated dots visible |
| Refs become stale | Re-read page with read_page after any navigation |
| get_page_text returns too much | Filter the output — ChatGPT page includes sidebar text |
| Model selector defaults to "Auto" | Usually fine; if specific model needed, click model selector first |
| Rate limiting | ChatGPT may throttle — wait and retry |
| Login required | User must be pre-logged in; cannot enter credentials |
For maximum research speed, run ChatGPT and Gemini simultaneously:
get_page_textThis gives you two independent research perspectives to cross-reference.
If generating images through ChatGPT while another session uses Gemini, see skills/multi-session-coordination.md for browser lock coordination. Only one session touches the browser at a time.
If downloading any files (images, documents) from the browser: