Skip to content
Agentmart
Submit a tool

counterintuition-probe

Challenge the most obvious explanation or preferred move by probing for counterintuitive alternatives that may better explain the situation.

Skill by Alubiama

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/alubiama-counterintuition-probe

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Challenge the most obvious explanation or preferred move by probing for counterintuitive alternatives that may better explain the situation. Use when the first answer feels too natural, when the team may be trapped by common sense, or when a surprising alternative deserves stress testing.

Use cases: testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/counterintuition-probe

What's inside

Skill name
counterintuition-probe
Description
Challenge the most obvious explanation or preferred move by probing for counterintuitive alternatives that may better explain the situation. Use when the first answer feels too natural, when the team may be trapped by common sense, or when a surprising alternative deserves stress testing.
License
MIT
Instructions
71 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Counterintuition Probe

## Goal

Attack the obvious answer and see whether a less intuitive explanation or move is stronger.

This skill does not oppose ideas for sport. It probes whether "what everyone assumes" is actually the best reading of the situation.

## When To Use

- the leading answer feels too obvious
- common sense is dominating the room
- the same explanation keeps winning without hard pressure
- a surprising alternative might explain more

## Scope Boundaries

In scope:

- identify the dominant assumption
- generate 1-3 serious counterintuitive alternatives
- compare them against the obvious answer
- recommend whether the obvious answer survives

Out of scope by default:

- contrarianism for its own sake
- endless philosophical debate
- random weird alternatives

## Workflow

1. State the obvious answer.
2. Name why it feels compelling.
3. Run a short guided reflection:
   - what would make the obvious answer fail
   - what assumption is carrying it most
4. Generate 1-3 counterintuitive alternatives.
5. Test which explains more with fewer assumptions.
6. Use `consider-the-opposite` explicitly against the preferred view.
7. Name what would falsify each view.
8. Recommend whether to keep, weaken, or replace the obvious answer.

## Output Contract

Always return:

1. `obvious_answer`
2. `why_it_feels_right`
3. `reflection_breakpoints`
4. `counterintuitive_alternatives`
5. `comparative_strength`
6. `falsifiers`
7. `recommended_position`
8. `recommended_followup`
9. `next_step`

## Guardrails

- Do not reward novelty alone.
- Do not keep weak alternatives alive just because they are surprising.
- Prefer falsifiable alternatives over clever rhetoric.
- Use counterintuition to improve judgment, not to create performative disagreement.

## Anti-Patterns

- contrarian theater
- shallow devil's advocacy
- weirdness without explanatory gain

From Alubiama/awesome-cognitive-skills, MIT.

More from Alubiama/awesome-cognitive-skills

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Mar 15, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Alubiama

Cite this page

counterintuition-probe skill. Agent Mart. https://agentmart.dev/skills/alubiama-counterintuition-probe (last updated 2026-10-24)