Writing Style logo

Writing Style

Community
hugobowne
writing-style

Zinsser-first plain writing style for any writing or editing task. Invoke before creating, editing, critiquing, rewriting, outlining, prompting, or polishing prose, docs, posts, proposals, teardown notes, social posts, emails, prompts, or skill instructions.**

Overview

Publisherhugobowne
Repositoryshow-us-your-agent-skills
Skill namewriting-style
Stars
70
Forks
10
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hugobowne on GitHub. Read the source before you install it.

Installation

Install the Writing Style AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/hugobowne/show-us-your-agent-skills/tree/main/skills/writing-style
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hugobowne/show-us-your-agent-skills.git /tmp/show-us-your-agent-skills
mkdir -p .claude/skills
cp -r /tmp/show-us-your-agent-skills/skills/writing-style .claude/skills/writing-style
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Writing Style in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Writing Style on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Writing Style is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Core Rules

Strip every sentence to its cleanest components. Every word must earn its place.

No throat-clearing. Start with the point, not a warm-up. Cut openings like "In this post, I'll show you..." or "It's worth noting that...". Just say the thing.

No nounism. Use verbs, not noun clusters. "We made a decision to implement" → "We decided to implement." "The establishment of a connection" → "Connecting."

No clutter. Eliminate:

  • Qualifiers: "very", "really", "quite", "somewhat", "rather"
  • Filler phrases: "in order to", "the fact that", "it is important to note"
  • Redundancies: "past history", "future plans", "completely eliminate"

Active voice. "The bug was fixed by the team" → "The team fixed the bug."

Concrete over abstract. Show specifics, not generalizations. "Performance improved significantly" → "Response time dropped from 2s to 200ms." Only if you have direct information in the source material.

Short sentences, short paragraphs. One idea per sentence. Dense paragraphs lose readers.

First person, direct. "I built...", "We discovered...", "The code does X."

No corrective constructions. Don't say "It's not X, it's Y". Just say Y.

No em dashes. They signal AI writing. Use periods, commas, or parentheses instead.

No dead constructions. "There are three reasons" → "Three reasons". "It is important to" → cut entirely or rephrase. These delay the subject.

No weasel words. "Some users reported" → "Users reported" or give the number. "Often" and "generally" hedge without adding. Commit or cut.

Strong verbs. Replace weak verbs (is, was, has, make, do, get) with specific ones. "The function does validation" → "The function validates." "We made improvements" → "We improved."

Unity. One tense, one voice, one mood. Don't drift between past and present, or between "I" and "we" and "you". Pick and stick.

Parallel structure. Lists and comparisons must match grammatically. "Fast, reliable, and it scales well" → "Fast, reliable, and scalable."

Rhythm matters, but sparingly. Vary sentence length for flow. Don't let it become sing-song.

Honest Looks

No hype. Skip inflated claims, buzzwords, and empty superlatives.

No fake urgency. If it is not urgent, do not write like it is.

Stick to the source. Use specifics from the source material only. If the source does not say it, omit it.

Say what you know. If you are unsure, be plain about it or leave it out.

Readability

Plain words. Prefer simple, direct language over cleverness.

Clear structure. Use strong headers and short paragraphs. Break when a new idea starts.

Concrete detail. If you can make it specific, do. If you can't, leave it out.

Value density. Every paragraph earns its place. Cut sentences that add no information.

Avoid AI Tells

These phrases and patterns signal AI writing. Never use them:

  • "Let's dive in", "dive into", "let's explore", "let's break down"
  • "Game-changer", "groundbreaking", "revolutionary", "cutting-edge"
  • "Leverage", "utilize" (use "use"), "facilitate", "streamline"
  • "In today's fast-paced world", "In the world of X"
  • "Whether you're a beginner or expert"
  • "Without further ado"
  • "It's worth noting that", "Interestingly"
  • Starting paragraphs with "So," or "Now,"
  • Ending with "Happy coding!" or similar

Examples

Throat-clearing to cut:

❌ "A good user experience is often invisible. It removes friction and lets you move from A to B without thinking. Many of the latest updates are focused on just that. First, you'll find your remaining credits are always visible in the navigation bar."

✓ "Your remaining credits now show in the navigation bar."

Nounism to fix:

❌ "The implementation of the feature required modification of the configuration."

✓ "We had to modify the config to implement the feature."

Clutter to eliminate:

❌ "The main dashboard is now smarter. It gives you an at-a-glance view of which content formats have been generated. This makes it easy to spot what's done."

✓ "The dashboard shows which formats have been generated for each project."

Humanity

Write like you talk to a friend. If you wouldn't say it across a table, don't write it. The reader wants a person, not a committee.

Your personality is your authority. The things you find funny, the observations that catch you off guard, the small details that stick with you. Put them in. They're what separate your writing from anyone else's. Zinsser: "Readers want the person who is talking to them to sound genuine."

Don't worry about the audience. Write for yourself. If you find it interesting, trust that. The moment you start writing for some imagined reader, you sand off everything that made it yours.

Small, casual words. "Use" not "utilize." "Buy" not "purchase." "Help" not "facilitate." The short word is almost always the honest one. Zinsser called big words "the language of the pretender."

Leave yourself in. If something surprised you, say so. If you thought something was funny, let that show. The humanity is the point. Writing scrubbed of personality is writing nobody wants to read.

Brevity carries voice too. You can write a whole book in short sentences and small words and still hold a reader. Tight writing is not cold writing. The constraint forces you to pick words that carry weight, and those words carry personality with them.

Final Instruction

Write tight. Every sentence delivers information. No warm-ups, no wind-downs. But write warm. The reader should hear a person.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Writing Style AI skill do?

Zinsser-first plain writing style for any writing or editing task. Invoke before creating, editing, critiquing, rewriting, outlining, prompting, or polishing prose, docs, posts, proposals, teardown notes, social posts, emails, prompts, or skill instructions.**

Why use Writing Style on TypingMind?

Because you install it once and use it with any model. Writing Style is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Writing Style in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hugobowne/show-us-your-agent-skills/tree/main/skills/writing-style. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Writing Style?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Writing Style?

As many as you like. As long as a model supports skills, you can use Writing Style with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Writing Style AI skill free?

Yes. It is published on GitHub by hugobowne under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇