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.

Separating what was asked from what is meant v1.0.0

Use this resource to understand the real goal behind an instruction before acting

New

  • 558 downloads
  • 195 likes
  • 122 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install instruction-intent-reading

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

Before acting on an instruction, the agent uses context and prior turns to infer the real goal, sizes its answer to what is needed and asks a question when the aim stays unclear. It treats a correction as a balance to adjust rather than a permanent ban. You get an action aimed at what you actually want.

Mostly picked by

Updated November 2, 2026

Card for the “Separating what was asked from what is meant” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: intent-reading method and the said-versus-meant split
  • SKILL.md: rules for corrections and vague requests

Good fit for

  • You give an agent short or ambiguous instructions
  • You often correct an agent on tone or level of detail

Not for

    Tags

    • intent
    • instruction
    • dialogue
    • ambiguity
    • agents

    About

    You say

    “Less jargon everywhere, but keep the detail on the method.”

    Card for the “Separating what was asked from what is meant” skill

    Skill published by haowjy under the Apache-2.0 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 understand the real goal behind an instruction before acting
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md1 KB

    Origin and licence

    Listed unmodified

    Author
    haowjy
    Source
    github.com/haowjy/creative-writing-skills/tree/1cb520f9c61e79ce2b1c56dba18601b2d6873433/plugin/claude/skills/intent-modeling
    Licence
    Apache-2.0

    Notice

    « intent-modeling » (haowjy, Apache-2.0) 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.