Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →tobihagemann/consult-oracle
Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches.
Passed 11 of 18 test cases with the skill, and 5 of 18 without it.
and 10 more in the full report
10 fixed4 passed either way6 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
The browser consultation script finished generating recommendations for an algorithmic bottleneck in `lib/math.py` and saved the response log. What step must be performed before executing the suggested code changes?
| Checked | Without skill | With skill |
|---|---|---|
| Cross-references generated recommendations with official documentation. | Missed | Passed |
The instructions your model reads when the skill loads.
Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches.
The oracle reads from ~/.turbo/config.json:
{
"oracle": {
"chatgptUrl": "https://chatgpt.com/",
"chromeProfile": "Default"
}
}
| Key | Purpose | Default |
|---|---|---|
chatgptUrl | ChatGPT URL (e.g., a custom GPT project URL) | https://chatgpt.com/ |
chromeProfile | Chrome profile directory name | Default |
Find the 2-5 files most relevant to the problem.
Write a clear, specific problem description. Include what has already been tried and why it failed. Open with a short project briefing (stack, services, build steps). The more context, the better the response.
Use a generous timeout (60 minutes / 3600000ms). The script loads chatgptUrl and chromeProfile from ~/.turbo/config.json automatically and reuses the signed-in ChatGPT session from that Chrome profile. Generate a random tag and persist the response:
ORACLE_TAG=$(head -c 4 /dev/urandom | xxd -p) && mkdir -p "$PWD/.turbo/oracle" && echo "$PWD/.turbo/oracle/$ORACLE_TAG.txt"
Substitute the printed value for <printed-path> in the command below and on every follow-up turn. Shell variables do not survive between shell calls, and an earlier cd in a compound command leaves the session in a different directory, so a relative path resolves against that directory instead.
test cases passed, vs 5 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.