Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Controlled thought experiment on a scenario v1.0.0

Use this resource to anticipate how a system behaves in a scenario you cannot test for real

New

  • 372 downloads
  • 146 likes
  • 104 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install controlled-counterfactual-analysis

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent changes a single variable in a scenario with fixed conditions, walks through the mechanical chain step by step, then limits its conclusions to what the reasoning supports. It helps spot breaking points before you commit.

Mostly picked by

Updated November 2, 2026

Card for the “Controlled thought experiment on a scenario” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: counterfactual method and fixed-condition rules
  • SKILL.md: mechanism chain and bounds on conclusions

Good fit for

  • You want to know how the system reacts to a regional outage
  • An irreversible architecture needs review before the choice

Not for

    Tags

    • scenario
    • counterfactual
    • risk

    About

    You say

    “What if the main database went down during the campaign: walk the chain and tell me the breaking points.”

    Card for the “Controlled thought experiment on a scenario” skill

    Skill published by tjboudreaux under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to anticipate how a system behaves in a scenario you cannot test for real
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md3.7 KB

    Origin and licence

    Listed unmodified

    Author
    tjboudreaux
    Source
    github.com/tjboudreaux/cc-thinking-skills/tree/7b8fece345dfaa11773be7152ccd194589cb5437/skills/thinking-thought-experiment
    Licence
    MIT

    Notice

    « thinking-thought-experiment » (tjboudreaux, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.