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.

Adversarial AI council for high-stakes decisions v1.0.0

Use this resource to stress-test an irreversible decision with adversarial AI advisors

New

  • 450 downloads
  • 131 likes
  • 167 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install adversarial-ai-decision-council

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 first checks that the subject warrants a council, frames the question, gathers advisors with distinct dimensions, runs a peer review round, then writes a synthesis. You see where the advisors agree, where they clash and the blind spots they caught.

Mostly picked by

Updated November 2, 2026

Card for the “Adversarial AI council for high-stakes decisions” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: council gate, advisor dimensions and rounds
  • SKILL.md: final synthesis, agreements, clashes and blind spots

Good fit for

  • You are weighing a sale of the business or a strategic supplier change
  • A costly decision that is hard to reverse needs challenge

Not for

    Tags

    • decision
    • council
    • strategy
    • irreversible
    • challenge

    About

    You say

    “Put the decision to close the Lyon workshop to the council.”

    Card for the “Adversarial AI council for high-stakes decisions” skill

    Skill published by duc01226 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 stress-test an irreversible decision with adversarial AI advisors
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md14.9 KB

    Origin and licence

    Listed unmodified

    Author
    duc01226
    Source
    github.com/duc01226/easyplatform/tree/1b6bdf10470d5b99baf8a6802f674c12c17461e9/.agents/skills/llm-council
    Licence
    MIT

    Notice

    « llm-council » (duc01226, 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.