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 review by independent AI reviewers v1.0.0

Use this resource to get several independent reviews before approving a delivery

New

  • 363 downloads
  • 202 likes
  • 164 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install adversarial-code-review-court

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 convenes reviewers from different vendors, each with its own probe set, then makes any approving verdict pass deeper reviews. The result is a signed court record with three possible verdicts, and a human makes the final call.

Mostly picked by

Updated November 2, 2026

Card for the “Adversarial review by independent AI reviewers” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: court roster, protocol and anti-collusion rules
  • config.json: model routing configuration, and schemas/output.json: court record format

Good fit for

  • A release must be approved before it ships
  • A passing verdict seems too easy to obtain

Not for

    Tags

    • code review
    • reviewers
    • verdict
    • security

    About

    You say

    “Convene the review court on this PR before we go to production.”

    Card for the “Adversarial review by independent AI reviewers” skill

    Skill published by proffesor-for-testing 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 get several independent reviews before approving a delivery
    3. Review and adjust the result

    Content preview

    Files

    • config-schema.json1.3 KB
    • config.json1.8 KB
    • evals/fixtures/seeded-mutant-delivery/budget-tests.ts.fixture0.8 KB
    • evals/fixtures/seeded-mutant-delivery/budget.ts.fixture1 KB
    • evals/fixtures/seeded-mutant-delivery/README.md2 KB
    • evals/qe-court.yaml2.6 KB
    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • schemas/output.json3.8 KB
    • scripts/validate-config.json0.5 KB
    • SKILL.md12.7 KB

    Origin and licence

    Listed unmodified

    Author
    proffesor-for-testing
    Source
    github.com/proffesor-for-testing/agentic-qe/tree/b177b2315521376b83f2eed40e4994fd7581d067/assets/skills/qe-court
    Licence
    MIT

    Notice

    « qe-court » (proffesor-for-testing, 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.