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.

Prompt rewording for false positives v1.0.0

Use this resource to reword an allowed prompt to reduce false safety triggers

New

  • 314 downloads
  • 220 likes
  • 245 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install prompt-wording-false-positives

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

For a legitimate prompt, the agent returns the full text with surgical edits limited to the sentences most likely to trigger the classifiers, without summarising or restructuring. The goal and benign text stay the same. The skill must not be used to bypass a policy.

Mostly picked by

Updated November 2, 2026

Card for the “Prompt rewording for false positives” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: minimal-edit method
  • SKILL.md: output format
  • SKILL.md: example and limits

Good fit for

  • A legitimate work prompt is wrongly blocked by a filter
  • You want the wording to keep a clearly benign intent

Not for

    Tags

    • prompt
    • false positives
    • wording
    • safety

    About

    You say

    “Reword the two sentences of this report prompt that trigger the filter, leaving the rest untouched.”

    Card for the “Prompt rewording for false positives” skill

    Skill published by davidondrej 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 reword an allowed prompt to reduce false safety triggers
    3. Review and adjust the result

    Content preview

    Files

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

    Origin and licence

    Listed unmodified

    Author
    davidondrej
    Source
    github.com/sickn33/agentic-awesome-skills/tree/e9809578fd426a284af017c5db99f8eb6628e6ca/skills/fable-safe-prompt
    Licence
    MIT

    Notice

    « fable-safe-prompt » (davidondrej, 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.