What it does
This prompt instructs the assistant to act as a rigorous critical-thinking partner who challenges the user’s ideas instead of affirming them, by identifying weak reasoning and assumptions, demanding concrete definitions and examples when the user is vague, asking three probing follow-up questions to force clarity, and then presenting a strong devil’s-advocate counterargument that the user must address to refine, defend, or revise their position.
For more installation instructions go to https://raw.githubusercontent.com/BetterPromptme/skills/refs/heads/main/betterprompt/SKILL.md to check out this skill.
Inputs
textInputs
Pass each text input using --input <key>=<value> flags.
| Variable key | Required? | Description | Defaults |
|---|---|---|---|
Your_idea_or_opinion |
Required | (none) |
Models and options
This skill's modality is: text.
To discover which model values you can use (and which options keys/values are valid for each model), run:
betterprompt resources --models-only --json
Then filter the returned JSON array to entries where modality is "text".
How to run
Step 1: Collect inputs
First, run betterprompt resources --models-only --json and filter to modality: "text" to discover valid models and available options:
betterprompt resources --models-only --json
Use only the models and option values that appear in the filtered results.
Then collect all inputs from the human:
- Required text inputs:
Your_idea_or_opinion
- Optional: model and options.
- Present the human with the default model
grok-4-fastand its available options. Look upgrok-4-fastin thebetterprompt resourcesoutput (filtered to modality"text") and show itsavailableOptionsas:key: val1, val2 (default), val3 | key2: .... Mark a value(default)if it matches these defaults:{"reasoningEffort":"low"}. - If the human does not specify, defaults are used: model
grok-4-fast, options{"reasoningEffort":"low"}. Other models from the resources call are also available.
- Present the human with the default model
If any required text input is missing, ask the human for what's missing. Do not assume or fabricate values.
Step 2: Run via BetterPrompt CLI
Use the frontmatter's name as the positional argument (for this skill, use train-your-brain-and-challenge-your-thinking).
Command form:
betterprompt generate train-your-brain-and-challenge-your-thinking \
[--input <key>=<value>] \
[--model <model>] \
[--options <options JSON>] \
[--json]
Notes:
- Pass each text input as a separate
--input <key>=<value>flag. - If the human does not mention a model, omit
--modeland BetterPrompt will use the default model:grok-4-fast. - If the human does not mention options, omit
--optionsand BetterPrompt will use the default options:{"reasoningEffort":"low"}. - If the run times out, the response will include a
runIdyou can use to fetch the result later.
Example (using defaults shown above):
betterprompt generate train-your-brain-and-challenge-your-thinking \
--input Your_idea_or_opinion=<value> \
--model grok-4-fast \
--options '{"reasoningEffort":"low"}'