Content Style Guide logo

Content Style Guide

Organization
bitwarden
content-style-guide

Bitwarden's product content style guide for end-user-facing GUI copy — voice, tone, AP-style-with-exceptions grammar, sentence case in UI, and accessibility-first language at a U.S. 7th-grade reading level.

Overview

Publisherbitwarden
Repositoryai-plugins
Skill namecontent-style-guide
Stars
149
Forks
19
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Content Style Guide 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.
  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/bitwarden/ai-plugins.git /tmp/ai-plugins
mkdir -p .claude/skills
cp -r /tmp/ai-plugins/plugins/bitwarden-design-tools/skills/content-style-guide .claude/skills/content-style-guide
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Content Style Guide 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 Content Style Guide 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 Content Style Guide 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.

Product Content Style Guide

This skill grounds GUI copy decisions in Bitwarden's product content style guide. Apply it to end-user-facing strings only — button labels, error messages, toasts, modals, onboarding flows, empty states, form labels, helper text, link text, and similar. Do not apply to design tokens, code comments, internal/dev-facing strings, or marketing copy.

When in doubt about a specific case, ask before changing copy.

Voice and tone

Voice is constant. Tone flexes with context.

Product voice is approachable, encouraging, and transparent — consistent across platforms.

Tone conveys mood and depends on who you're talking to and what's happening. Security is serious stuff. Users aren't looking for humor or fluff — they want to know their information is safe. So Bitwarden's product tone is almost always serious and respectful.

Tone spectrums:

  • Casual ↔ formal
  • Enthusiastic ↔ matter-of-fact

Where common content types land on the tone map (axes: casual ↔ formal × matter-of-fact ↔ enthusiastic):

Content typeCasual / FormalMatter-of-fact / Enthusiastic
Success messagesCasualEnthusiastic
Onboarding copyCasualEnthusiastic
DialogsCasualMatter-of-fact
Empty statesCasualMatter-of-fact (slightly)
LabelsNeutralMatter-of-fact
CommunityFormalEnthusiastic
ConfirmationsFormalMatter-of-fact
Help articlesFormal (slightly)Neutral
WarningsFormalMatter-of-fact
Error statesFormalMatter-of-fact

Examples

Error message — formal, matter-of-fact:

  • Good: An error occurred. Please try again.
  • Avoid: Uh oh! We goofed. Go ahead and refresh!

Onboarding message — casual, enthusiastic:

  • Good: Hey there! 👋 Welcome to Bitwarden. We'll show you around!
  • Avoid: This is your vault. Get started now.

Applying this skill

During explicit copy critique ("review this copy", "is this error message ok"):

  1. Identify the content type (error, onboarding, button, etc.) and the expected tone using the tone map above.
  2. Check voice consistency (approachable, encouraging, transparent).
  3. Walk grammar and mechanics rules relevant to the snippet — see references/grammar-mechanics.md.
  4. Walk accessibility rules relevant to the snippet — see references/accessibility-rules.md.
  5. Return specific, actionable rewrites — not just "this is wrong."

Inside figma-to-angular runs (external skill in the clients repo, not bundled here):

When the Figma design includes copy strings, validate them against this guide before emitting them into the Angular template. If a string clearly violates a rule (e.g., title-case button, ampersand, "Click here" link), surface the issue and propose a compliant alternative — do not silently rewrite. Ask the user which to use.

Inside design-review critiques:

If the stage is 60% or 90%, include content observations alongside visual feedback (90% is the right stage for "nitty-gritty grammar, finalizing copy"). Skip content nitpicks at 30% — the copy will change. Frame content feedback the same way as visual feedback: tied to user/product goals, not personal taste.

Output format for copy critique

  1. Content type and expected tone — name what this string is and where it should land on the tone spectrum.
  2. What's working — what to keep.
  3. Issues — each tied to a specific rule from this guide (cite the section name, including the references file if the rule lives there).
  4. Proposed rewrite(s) — concrete alternatives the user can pick from.

Keep critique specific. "The button uses title case; sentence case per references/grammar-mechanics.md (Capitalization)" beats "the capitalization is off."

Additional resources

The detailed rules live in two references files. Load them when the critique needs them — most copy issues touch only one or two rules.

  • references/grammar-mechanics.md — Acronyms, ampersands, capitalization (sentence case, product names, features, lowercase objects), dates and months, days of the week, e.g. / i.e., ellipsis, file sizes and formats, money, numbers, Oxford comma, times and time zones, versus.
  • references/accessibility-rules.md — Reading level and directness, scannable layouts, non-English and ESL considerations, spelling out acronyms, avoiding "easy" and "simple" framings, text styling, spatial language, alt text, meaningful link text, gender-neutral pronouns.

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 Content Style Guide AI skill do?

Bitwarden's product content style guide for end-user-facing GUI copy — voice, tone, AP-style-with-exceptions grammar, sentence case in UI, and accessibility-first language at a U.S. 7th-grade reading level.

Why use Content Style Guide on TypingMind?

Because you install it once and use it with any model. Content Style Guide 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 Content Style Guide in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bitwarden/ai-plugins/tree/main/plugins/bitwarden-design-tools/skills/content-style-guide. 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 Content Style Guide?

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 Content Style Guide?

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

Is the Content Style Guide AI skill free?

It is published on GitHub by bitwarden. Check the repository for licensing terms. 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 👇