agentleFS
leekleek/agent-skills/skills/brand-guidelines/SKILL.md

brand-guidelines

Skill5 starsChanged 6 days agoMITView on GitHub

Write or review user-facing copy against this repo's own brand guide (voices, where each applies, spelling, word choices) and a shared set of craft rules. Use when writing UI text, error messages, empty states, onboarding, emails, or marketing copy, or when the user states a copy preference to record as a brand rule.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use academy-guide, skill-share and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    academy-guide

    Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

    Also in 9 projects that use this

  • ArogyaReddySkill

    skill-share

    A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.

    Also in 25 projects that use this

  • ArogyaReddySkill

    raffle-winner-picker

    Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.

    Also in 26 projects that use this

  • zephyrwang6Skill

    deepl

    Übersetzt Texte, Dokumente und XLIFF-Dateien via DeepL API. Verwende für Übersetzungen mit /deepl translate, /deepl file oder /deepl xliff.

    Also in 4 projects that use this

  • zephyrwang6Skill

    imagemagick-conversion

    Convert and manipulate images with ImageMagick. Covers format conversion, resizing, batch processing, quality adjustment, and image transformations. Use when user mentions image conversion, resizing images, ImageMagick, magick command, batch image processing, or thumbnail generation.

    Also in 4 projects that use this

  • +3 more from zephyrwang6
  • +4 more from ArogyaReddy

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 180 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .agents/brand-guidelines.md before you write or review copy.

    line 18
  2. Distinctive:

    If the file does not exist, this repo has not set the skill up.

    line 20
  3. Distinctive:

    Use the product's existing words: Search the existing copy and translation files for the name the product already gives the thing, and use …

    line 30
  4. Distinctive:

    When the user states a copy preference, corrects a string's tone, or bans a word:

    line 39
  5. Very specific:

    Look in .agents/brand-guidelines.md for a rule that already covers it, and sharpen that rule rather than adding a near-duplicate.

    line 41

“Common” is measured: kept by at least 6 in 10 of the 180 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Brand Guidelines

Two layers of rules decide what good copy is:

  • The brand guide holds this repo's own decisions: its voices, the surfaces each voice applies to, spelling, casing, punctuation, word choices, and product terms. It lives in the target repo at .agents/brand-guidelines.md, and the user owns it.
  • The craft rules below hold for any product.

Where the two disagree, the brand guide wins. A blog post goes to the blog-writing skill, which has its own style guide.

Load the brand guide

Read .agents/brand-guidelines.md before you write or review copy. A section the guide leaves out means only the craft rules apply there.

If the file does not exist, this repo has not set the skill up. Ask the user before any other work (a structured question (harness-tools), otherwise in chat):

  • Set it up now (recommended): bootstrap the guide per BRAND-GUIDE-FORMAT.md, then continue the task.
  • Skip this time: continue with the craft rules alone, and say in your reply that the repo has no brand guide yet.

Done when you can name the default voice in one line, or the user chose to skip.

Write

  1. Name the surface (button, form label, error, empty state, confirmation, tooltip, 404, email, marketing page) and take the voice the guide assigns to it. A surface the guide does not list gets the default voice.
  2. Use the product's existing words. Search the existing copy and translation files for the name the product already gives the thing, and use that name. The guide's product terms win over what the code calls it.
  3. Write the copy to every craft rule and every brand-guide rule that covers the surface.

Review

Check each string in the page, path, or diff against both layers. Report one line per finding: <file:line or screen> · "<current>" → "<rewrite>" · <rule>. A string that meets the rules stays silent. Done when every user-facing string in scope was checked, including the ones the default view hides: errors, empty states, confirmations, tooltips.

Record a rule

When the user states a copy preference, corrects a string's tone, or bans a word:

  1. Look in .agents/brand-guidelines.md for a rule that already covers it, and sharpen that rule rather than adding a near-duplicate.
  2. Otherwise add it under the section it fits, in the shape that section uses in BRAND-GUIDE-FORMAT.md. A preference that would hold for any product still goes in this repo's guide: the craft rules change only in this skill's own repo.
  3. Show the user the added or changed text in your reply.

Craft rules

Plain by default

Copy with no voice assigned is plain: it uses the fewest words that carry the meaning, tells the user what to do, uses the active voice, and names the specific thing.

BeforeAfter
"Click here to save your changes""Save"
"You can filter results by date""Filter by date"
"Your changes will be saved""Save your changes"
"Some errors found""3 errors found"
"In order to continue""To continue"
"This might delete your data" (when it will)"This deletes your data"
"Item has been successfully deleted""Deleted"
"Supercharge your workflow" (in the product UI)"Speed up your workflow"

Personality is earned

A voice with personality goes only on the surfaces the brand guide assigns it to, where the user has a moment to spare: an empty state, a 404, onboarding. These surfaces stay plain whatever the guide assigns: error messages, destructive confirmations, billing and payment, settings, and reference documentation. There the user is frustrated, focused, or deciding whether to trust you.

  • A joke aims at the situation, never at the user.
  • The copy still says what happened and what to do with the joke removed.

Buttons

A button is an action verb plus its object when the object is not obvious: "Create project", where "Create" alone leaves the user guessing. Two or three words at most, no closing punctuation.

Error messages

Say what happened, why when that helps, and what to do next: "Could not save changes. Check your connection and try again." in place of "Error: Save failed." Name the field or value that is wrong; "Invalid input" names nothing.

Empty states

Say what will appear here, and give the one action that fills it: "No projects yet. Create your first project to start tracking orders."

Confirmation dialogs

The title names the action. The body states the consequence when the action destroys something. The buttons repeat the action ("Delete project", "Keep project"), so each one reads correctly alone.

Tooltips and help text

At most two sentences. Say why the control matters, since the label already says what it is. Link to the docs for anything longer.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.