Skip to content
Back to skills

In Your Own Words

ASecurity

Paraphrase the problem you think the user is solving and the outcome they want, so any misunderstanding shows up before work begins. Use for "/in-your-own-words", "tell me what you think I want", or before starting on a long or messy request.

  • 1,531 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
ai-agentsgo

Security analysis

A100/100

Scanned November 7, 2026

npx -y skills add hashgraph-online/awesome-codex-plugins --skill in-your-own-words --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of In Your Own Words?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for In Your Own Words
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hashgraph-online-in-your-own-words/badge)](https://www.skillsdirectory.com/skills/hashgraph-online-in-your-own-words)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: in-your-own-words
description: Paraphrase the problem you think the user is solving and the outcome they want, so any misunderstanding shows up before work begins. Use for "/in-your-own-words", "tell me what you think I want", or before starting on a long or messy request.
---

# in-your-own-words

Before doing anything, tell the user what you think they want. Do not quote them back to themselves: a paraphrase forces you to commit to an interpretation, and a quote hides whether you have one.

1. State what you believe the user's goals are.
2. State the problem you believe they are trying to solve, which may differ from the task they described.
3. Name any point where you had to guess, so the user can correct it.

Then stop. Do not start the work until the user confirms or corrects your understanding. If they want the prompt itself improved instead, that is the [`sharpen` skill](../sharpen/SKILL.md).

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.