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.

Create a benchmarked, verified skill v1.0.0

Use this resource to create or improve a quality skill, benchmarked and verified by several agents

New

  • 529 downloads
  • 193 likes
  • 148 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install skill-factory-autoresearch

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 interviews you to set the purpose and gold standards, has sub-agents research the material, drafts the skill, then improves it through iterations scored by an LLM judge. A multi-agent check, with a devil's advocate, closes the process. You get a documented, evaluated skill.

Mostly picked by

Updated November 2, 2026

Card for the “Create a benchmarked, verified skill” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: five phases, from interview to verification
  • references/rubric-templates.md: evaluation rubric templates
  • references/consensus-protocol.md: consensus protocol between verifiers

Good fit for

  • You want to turn existing documentation into a usable skill
  • A skill gives uneven results and needs measuring

Not for

    Tags

    • skills
    • evaluation
    • benchmark
    • creation

    About

    You say

    “Create a contract-review skill from these three reference documents, then measure it.”

    Card for the “Create a benchmarked, verified skill” skill

    Skill published by a-tokyo 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 create or improve a quality skill, benchmarked and verified by several agents
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/benchmark-standard.md9.2 KB
    • references/consensus-protocol.md10.1 KB
    • references/pipeline-phases.md20.4 KB
    • references/publishing.md4.7 KB
    • references/rubric-templates.md7.8 KB
    • references/skill-authoring-best-practices.md8 KB
    • references/skill-craft-principles.md8 KB
    • SKILL.md26.3 KB

    Origin and licence

    Listed unmodified

    Author
    a-tokyo
    Source
    github.com/a-tokyo/agent-skills/tree/99652ee6a78759a5ef655388497a2b889ad6c602/skills/create-skill-autoresearch
    Licence
    MIT

    Notice

    « create-skill-autoresearch » (a-tokyo, 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.