consult-oracle

Name: consult-oracle
Author: tobihagemann

4installs29forks

How to install consult-oracle?

tobihagemann/turbo/consult-oracle

$npx -y skills add tobihagemann/turbo --skill consult-oracle

Installs into the current project.

Summary

Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches. Use when stuck on a very hard problem, when standard approaches have failed, when multiple debugging attempts haven't worked, or when the user says \"ask the oracle\", \"consult oracl

Files · 1

View on GitHub

SKILL.md

1	# Consult Oracle
2
3	Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches.
4
5	## Configuration
6
7	The oracle reads from `~/.turbo/config.json`:
8
9	```json
10	{
11	"oracle": {
12	"chatgptUrl": "https://chatgpt.com/",
13	"chromeProfile": "Default"
14	}
15	}
16	```
17
18	\| Key \| Purpose \| Default \|
19	\|---\|---\|---\|
20	\| `chatgptUrl` \| ChatGPT URL (e.g., a custom GPT project URL) \| `https://chatgpt.com/` \|
21	\| `chromeProfile` \| Chrome profile directory name \| `Default` \|
22
23	## Step 1: Identify Key Files
24
25	Find the 2-5 files most relevant to the problem.
26
27	## Step 2: Formulate the Question
28
29	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.
30
31	## Step 3: Run the Oracle
32
33	Run via the Bash tool (`timeout: 600000`, do not set `run_in_background`). 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:
34
35	```bash
36	ORACLE_TAG=$(head -c 4 /dev/urandom \| xxd -p) && mkdir -p .turbo/oracle
37	python3 scripts/run_oracle.py --prompt "<problem description>" --file <relevant files...> --write-output ".turbo/oracle/$ORACLE_TAG.txt"
38	```
39
40	If the run fails, retry the command once — same prompt, attachments, profile, and timeout — when the failure looks transient, such as a browser challenge or automation error while the signed-in session is otherwise healthy. Report an authentication, browser-challenge, or permission blocker only after the retry reproduces it, and cite the failing output. Do not broaden permissions when the current context already has the access the run needs.
41
42	## Step 4: Follow Up
43
44	Resume the same ChatGPT conversation with `--followup` and the session slug. The prior turn's attached files and context persist, so re-attaching the full diff each turn is unnecessary. Run via the Bash tool with the same settings as Step 3 (`timeout: 600000`, do not set `run_in_background`):
45
46	```bash
47	python3 scripts/run_oracle.py --followup "<session-slug>" --prompt "<follow-up>" --write-output ".turbo/oracle/$ORACLE_TAG.txt"
48	```
49
50	Find the slug with `python3 scripts/run_oracle.py status` (the Slug column; follow-ups nest under their parent session) or from the directory names under `~/.oracle/sessions/`.
51
52	Reuse the chat for a multi-turn review of the same code; start a fresh session (Step 3) for an unrelated question. Cap at 5 turns to prevent runaway conversations.
53
54	When the reviewed code changed since the prior turn, re-attach the changed files (`--file <paths>`) or a fresh diff, or state what changed. Otherwise the model reasons from the earlier attachments and flags already-fixed issues as live contradictions.
55
56	## Step 5: Synthesize
57
58	Read the response from `.turbo/oracle/$ORACLE_TAG.txt`. Summarize the key insights from the consultation. Cross-reference suggestions with official docs and peer open-source implementations before applying. Oracle suggestions are starting points, not guaranteed solutions.

People who liked this also viewed

6 picks

Type

consult-oracle

4installs29forks

View on GitHub

How to install consult-oracle?

tobihagemann/turbo/consult-oracle

$npx -y skills add tobihagemann/turbo --skill consult-oracle

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Consult Oracle
2
3	Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches.
4
5	## Configuration
6
7	The oracle reads from `~/.turbo/config.json`:
8
9	```json
10	{
11	"oracle": {
12	"chatgptUrl": "https://chatgpt.com/",
13	"chromeProfile": "Default"
14	}
15	}
16	```
17
18	\| Key \| Purpose \| Default \|
19	\|---\|---\|---\|
20	\| `chatgptUrl` \| ChatGPT URL (e.g., a custom GPT project URL) \| `https://chatgpt.com/` \|
21	\| `chromeProfile` \| Chrome profile directory name \| `Default` \|
22
23	## Step 1: Identify Key Files
24
25	Find the 2-5 files most relevant to the problem.
26
27	## Step 2: Formulate the Question
28
29	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.
30
31	## Step 3: Run the Oracle
32
33	Run via the Bash tool (`timeout: 600000`, do not set `run_in_background`). 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:
34
35	```bash
36	ORACLE_TAG=$(head -c 4 /dev/urandom \| xxd -p) && mkdir -p .turbo/oracle
37	python3 scripts/run_oracle.py --prompt "<problem description>" --file <relevant files...> --write-output ".turbo/oracle/$ORACLE_TAG.txt"
38	```
39
40	If the run fails, retry the command once — same prompt, attachments, profile, and timeout — when the failure looks transient, such as a browser challenge or automation error while the signed-in session is otherwise healthy. Report an authentication, browser-challenge, or permission blocker only after the retry reproduces it, and cite the failing output. Do not broaden permissions when the current context already has the access the run needs.
41
42	## Step 4: Follow Up
43
44	Resume the same ChatGPT conversation with `--followup` and the session slug. The prior turn's attached files and context persist, so re-attaching the full diff each turn is unnecessary. Run via the Bash tool with the same settings as Step 3 (`timeout: 600000`, do not set `run_in_background`):
45
46	```bash
47	python3 scripts/run_oracle.py --followup "<session-slug>" --prompt "<follow-up>" --write-output ".turbo/oracle/$ORACLE_TAG.txt"
48	```
49
50	Find the slug with `python3 scripts/run_oracle.py status` (the Slug column; follow-ups nest under their parent session) or from the directory names under `~/.oracle/sessions/`.
51
52	Reuse the chat for a multi-turn review of the same code; start a fresh session (Step 3) for an unrelated question. Cap at 5 turns to prevent runaway conversations.
53
54	When the reviewed code changed since the prior turn, re-attach the changed files (`--file <paths>`) or a fresh diff, or state what changed. Otherwise the model reasons from the earlier attachments and flags already-fixed issues as live contradictions.
55
56	## Step 5: Synthesize
57
58	Read the response from `.turbo/oracle/$ORACLE_TAG.txt`. Summarize the key insights from the consultation. Cross-reference suggestions with official docs and peer open-source implementations before applying. Oracle suggestions are starting points, not guaranteed solutions.

People who liked this also viewed

6 picks

Type