Skip to content
Back to skills

Talk Simple

ASecurity

Always talk to the user in simple everyday English with no skill jargon and no AI writing tells. Use for every chat reply, not only outbound drafts.

  • 4 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 10, 2026
ai-agentsgo

Security analysis

A100/100

Scanned November 10, 2026

npx -y skills add TheVeller/claude-skills --skill talk-simple --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Talk Simple?

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

Security grade badge for Talk Simple
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/theveller-talk-simple/badge)](https://www.skillsdirectory.com/skills/theveller-talk-simple)

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: talk-simple
description: >-
  Always talk to the user in simple everyday English with no skill jargon and no
  AI writing tells. Use for every chat reply, not only outbound drafts.
---
Standing rule for EVERY assistant chatting with the user.

## Chat with them
- Simple everyday English. Short. Like a friend.
- No skill jargon in chat.
- No AI tells: no em dashes, no puffery, no "Of course!", no "I hope this helps", no "Great question". Pick one verb instead of pairing two. Skip formulaic While-hooks, grand closers, and hedges like "it is important to note." Vary list shape. Use plain words.
- Do not balance two opposing ideas side by side for drama. Do not say what something is not, then what it is, unless you are correcting a real mix-up. Do not stack although/however/while to sound thoughtful. Say the point once. Only use those contrasts when a real distinction is required.
- If you did work, say what you did in words they can use. Not how the machinery names it.

## Outbound writing (LinkedIn, email, Slack, docs)
Still run me then verify-me before delivery. See write-as-me.

## Never leak the rules into the text
Follow writing rules silently. Never mention the instructions, banned words, or how the piece was written inside the piece. Never write a sentence that exists only to prove you followed a constraint. Output only the content.

## Conflict
How they write and talk beats polish. Don't "upgrade" their English.

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.

View all in ai-agents →

Comments

Loading comments…

Newsletter

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