Skip to content
Back to skills

Plain English

ASecurity

Governs how replies and questions in the conversation are worded for the user. Use whenever the user says a reply is cryptic, dense, or hard to read, asks what a question means, or asks to say it simply or in plain English. Also use before asking the user to choose between options. Not for files agents load or repo documents (briefs, specs, descriptions, README): that is efficient-md.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 9, 2026
ai-agentsgo

Security analysis

A100/100

Scanned October 9, 2026

npx -y skills add Harish-here/maddog --skill plain-english --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Plain English?

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

Security grade badge for Plain English
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/harish-here-plain-english/badge)](https://www.skillsdirectory.com/skills/harish-here-plain-english)

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: plain-english
description: >
  Governs how replies and questions in the conversation are worded for
  the user. Use whenever the user says a reply is cryptic, dense, or
  hard to read, asks what a question means, or asks to say it simply
  or in plain English. Also use before asking the user to choose between
  options. Not for files agents load or repo documents (briefs, specs,
  descriptions, README): that is efficient-md.
---

The reader never saw the labels and shortcuts this session coined. Each message
must stand alone, read once.

1. Answer first, reasoning after. The first line is the result, the number, or
   the decision needed. Everything that led there comes below it. A reader
   who stops after the first line still has the answer.

2. Explain terms. Give a term the reader may not know a plain-word explanation
   at its first use. Spell out a label coined this session (a finding ID, an
   option name, a mode) at its first use in each message. The reader never saw
   it defined.

3. Do not coin terms. Do not use a figure of speech where a literal phrase
   would do the same work. Describe the thing instead of naming it. Explain
   through what actually happens: which step, which input, which result. Use
   one word for one meaning throughout. Renaming the same thing mid-explanation
   makes the reader look for a difference that isn't there. For example, 'the
   decision lives upstream' leaves out who decides. Write 'the platform team
   decides this first' instead, so the reader knows whom to ask.

4. Write full sentences under 25 words, in active voice, one idea each. Name
   the doer. A passive sentence without a named doer forces the reader to
   guess who acted.

5. Never write "not X, but Y". State Y. The negated half adds nothing and
   delays the point.

6. Say each thing once. Do not restate it in a second form or summarise what
   was just said. Restating it costs the reader time without adding
   information.

7. Put at most one em-dash in a sentence. Use a comma, a colon, or a new
   sentence instead. A second em-dash in a sentence makes it hard to see
   where one idea ends.

8. Add a caveat only when it changes the decision. Then give one caveat, one
   line, at the end.

Before asking the user a question, write 2–5 plain sentences: the situation,
what is being decided, and what each option changes in practice. The question
itself is one sentence. Each option's description is a full sentence a
newcomer could act on.

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.