chatgpt
Skill0 starsChanged 9 months agoMITView on GitHub
ChatGPT browser automation - ask questions, select models, multi-turn conversations
4 other projects use a version of this.
Adopted by
Most recently taken up by
- zqcccc/chrome-agent-bridgetheir own version, first seen Oct 28, 2026
- P-Essonam/clicsdevtheir own version, first seen Sep 3, 2026
- lifeshoftcode/codex-chatgpt-skill-recipetheir own version, first seen Jun 21, 2026
- mediause/agent-skillstheir own version, first seen May 11, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- mediause/agent-skills★ 9same name
- lifeshoftcode/codex-chatgpt-skill-recipe★ 2same name
- P-Essonam/clicsdev★ 1same name
- zqcccc/chrome-agent-bridge★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository33 other files it gives its agents.
- 13fSkill
- info-lake-healthSkill
- calendarSkill
- chatgpt-organizerSkill
- exploreSkill
- flashbackSkill
- GANSkill
- kbSkill
- learnSkill
- linkSkill
- meeting-backtestSkill
- meeting-transcriptSkill
- mocSkill
- notebooklmSkill
- organizer-transcriptSkill
- planSkill
- podcastSkill
- podwise-downloaderSkill
- portfolioSkill
- prompt-optimizerSkill
- researchSkill
- reviewSkill
- socratic-writerSkill
- substackSkill
- supply-chainSkill
- telegramSkill
- thesisSkill
- tradeSkill
- vault-healthSkill
- wechat-haoSkill
- x-bookmarksSkill
- xueqiuSkill
- youtube-downloaderSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 133
If standard models timeout, check that the stop button selector still works
- Very specific: line 134
Run debug_selectors.py to verify STOP_BUTTON_SELECTORS
- Very specific: line 172
Browser mode: Always visible (headless=False) — ChatGPT actively blocks headless
- Very specific: line 177
Config centralization: All selectors in config.py — single file to update on UI changes
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ℹ️ 备用工具 — 日常多AI协同请用
/write --team(socratic-writer)。本工具仅在需要特定 GPT 模型(如 o3)或上传文件到 ChatGPT 网页版时使用。
ChatGPT Browser Automation Skill
Reusable ChatGPT automation via Patchright (Playwright fork). Opens a visible Chrome browser, types questions, detects responses using dual stop-button + text-stability polling, and persists Q&A to JSON + Obsidian.
When to Use
- Other skills need ChatGPT as a reasoning backend (e.g.,
socratic-writer) - You need to query ChatGPT with model selection (o3, gpt-4o, etc.)
- You want Q&A history searchable in Obsidian
When NOT to Use
- Claude can answer the question directly — no need for ChatGPT
- The task requires the ChatGPT API (use the OpenAI SDK instead)
- Headless automation — ChatGPT blocks headless browsers
Quick Start
# First time: setup venv + install deps
python scripts/run.py setup_environment
# Authenticate (opens browser for manual login)
python scripts/run.py auth_manager setup
# Ask a question
python scripts/run.py ask_question --question "What is 2+2?"
# Ask with model selection
python scripts/run.py ask_question --question "Explain quantum entanglement" --model o3
# Multi-turn interactive session
python scripts/run.py conversation interactive --model gpt-4oCore Workflow
One-Shot Q&A (ask_question.py)
The primary entry point. Each call opens a fresh browser session:
- Auth check → launch persistent Chrome context (visible)
- Navigate to chatgpt.com → wait for page load
- Dismiss popups → select model (if specified)
- Click-focus input →
page.keyboard.type()(ProseMirror compatible) - Click send button (or fallback Enter)
- Dual response detection:
- Layer 1: Stop button visible → still generating (progress every 15s)
- Layer 2: Text stability — 3 identical reads at 1.5s intervals
- Save cookies → persist to history → return text
# Programmatic usage from other skills
from ask_question import ask_chatgpt
answer = ask_chatgpt("What is 2+2?", model="o3")Multi-Turn Conversation (conversation.py)
Keeps browser open across questions:
# Interactive REPL
python scripts/run.py conversation interactive --model o3
# Type questions, get answers, empty line to endScript Reference
| Script | Purpose | CLI |
ask_question.py | One-shot Q&A | --question "..." [--model o3] [--no-history] |
conversation.py | Multi-turn sessions | interactive [--model o3] |
auth_manager.py | Login management | setup|status|validate|clear|reauth |
history_manager.py | Q&A history | search --query "..."|list|stats |
debug_selectors.py | Selector diagnostics | (no args — opens browser, reports) |
config.py | All selectors + config | (imported, not run directly) |
browser_utils.py | BrowserFactory + stealth | (imported, not run directly) |
run.py | Venv wrapper | <script_name> [args] |
setup_environment.py | First-time setup | [--check] |
Model Selection
Available models (update MODEL_MAPPINGS in config.py when ChatGPT changes):
| Name | Key | Timeout |
| o3 | o3 | 300s (thinking) |
| GPT-4o | gpt-4o | 120s |
| GPT-4 | gpt-4 | 120s |
| GPT-4.5 | gpt-4.5 | 120s |
| o4-mini | o4-mini | 120s |
| o4-mini-high | o4-mini-high | 300s (thinking) |
| Deep Research | deep-research | 300s (thinking) |
Data & Persistence
| Data | Location |
| Browser state | data/browser_state/state.json |
| Chrome profile | data/browser_state/browser_profile/ |
| Auth metadata | data/auth_info.json |
| Q&A history | data/history.json |
| Obsidian logs | ~/Documents/Obsidian Vault/ChatGPT/ChatGPT_YYYY-MM-DD.md |
Troubleshooting
"Not authenticated"
python scripts/run.py auth_manager setupSelectors broken (UI changed)
python scripts/run.py debug_selectorsThis shows which selectors match and which are broken. Update config.py accordingly.
Model not found in menu
The model picker UI changes frequently. Run debug_selectors.py to see current button labels, then update MODEL_MAPPINGS in config.py.
Response timeout
- Thinking models (o3, deep-research) have 300s timeout — this is normal
- If standard models timeout, check that the stop button selector still works
- Run
debug_selectors.pyto verifySTOP_BUTTON_SELECTORS
ProseMirror typing issues
The skill uses page.keyboard.type() instead of element.fill() because ChatGPT's contenteditable div (ProseMirror) only processes real keyboard events. If typing fails, the input selector may have changed — check INPUT_SELECTORS in config.
Integration with Other Skills
Other skills can import ask_chatgpt directly:
import sys
sys.path.insert(0, str(Path.home() / ".claude/skills/chatgpt/scripts"))
from ask_question import ask_chatgpt
# Simple query
answer = ask_chatgpt("Analyze this argument: ...")
# With model selection
answer = ask_chatgpt("Deep analysis needed", model="o3")
# Skip history (for internal queries)
answer = ask_chatgpt("Quick check", no_history=True)For multi-turn from code:
from conversation import ChatGPTSession
session = ChatGPTSession()
session.start(model="gpt-4o")
answer1 = session.ask("First question")
answer2 = session.ask("Follow-up based on your answer")
session.end() # Saves all Q&A to historyArchitecture Notes
- Browser mode: Always visible (
headless=False) — ChatGPT actively blocks headless - Browser pattern:
launch_persistent_context— better fingerprint persistence thannew_context - Input method:
page.keyboard.type()— ProseMirror rejectsfill()on contenteditable - Response detection: Dual algorithm (stop-button + text stability polling)
- Auth expiry: 3 days (ChatGPT sessions expire faster than Google)
- Config centralization: All selectors in
config.py— single file to update on UI changes
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

