brand-guidelines
Skill1 starsChanged 18 days agoMITView on GitHub
Applies Anthropic's brand colors and typography to code artifacts in this repo — HTML dashboards, generated pages, docs. Use when styling anything that should carry the ClaudeOS/Anthropic look. Adapts the chat-oriented brand skill to a codebase where colors come from Stylix base16 tokens, never hardcoded hex.
190 other projects use a version of this.
Adopted by
Most recently taken up by
- AtilaMedeiros/skillstheir own version, first seen Nov 16, 2026
- Badhon-00/MDCPtheir own version, first seen Nov 16, 2026
- darren469/Claude-Skillstheir own version, first seen Nov 16, 2026
- Ivan-propio/claude-skillstheir own version, first seen Nov 16, 2026
- david33137/claude-skillstheir own version, first seen Nov 16, 2026
- leek/agent-skillstheir own version, first seen Nov 16, 2026
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.
AnthropicSkillacademy-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 11 projects that use this
ArogyaReddySkillskill-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 28 projects that use this
ArogyaReddySkillraffle-winner-picker
Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.
Also in 28 projects that use this
zephyrwang6Skilldeepl
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
zephyrwang6Skillimagemagick-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
Patrick-Git-CreatorSkillartifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Also in 46 projects that use this
- +2 more from zephyrwang6
- +4 more from ArogyaReddy
Other versions190 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 190
- anthropics/skills★ 195ksame name
- ComposioHQ/awesome-claude-skills★ 75ksame name
- ComposioHQ/awesome-codex-skills★ 17ksame name
- composio-community/awesome-codex-skills★ 16ksame name
- composio-community/open-claude-cowork★ 4.3ksame name
- ComposioHQ/open-claude-cowork★ 4.3ksame name
- Mayandev/notion-avatar★ 3.2ksame name
- Prat011/awesome-llm-skills★ 1.7ksame name
- ChenglinPoly/infiAgent★ 1.2ksame name
- polyuiislab/infiAgent★ 1.2ksame name
180 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- add-moduleSkill
- deploySkill
- qml-dial-inSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 178 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Decided: the claude.ai tokens win: Do not "correct" the palette toward the deck hexes.
- Very specific: line 46
base0Cis a vivid blue, not the deck's muted one: Use it for small marks (thin bars, dots, strokes) where saturation reads as precision. - Distinctive: line 51
Do not cycle. Pick the accent that means something.
- Distinctive: line 96
Not in the upstream skill.
“Common” is measured: kept by at least 6 in 10 of the 178 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.
Files
Anthropic Brand Styling — in code
Adapted from the chat brand-guidelines skill, which targets slide decks via
python-pptx and hands out raw hex. Neither assumption holds here. In this
repo colors arrive as base16 tokens from Stylix, and artifacts are HTML.
The one rule that overrides the upstream skill
CLAUDE.md: "Always use Stylix/base16 palette references — never hardcode hex color values."
The brand hexes below are the reference the palette was derived from, not
values to paste. Emit var(--base0D), not #d97757. Source of truth at
runtime is ~/.config/stylix/palette.json; at Nix eval time it is
config.lib.stylix.colors.withHashtag.
Color — and which brand source wins
There are two Anthropic color sources, and they disagree. The upstream skill
carries the deck palette. This system's scheme (modules/desktop/theme.nix)
was extracted from live claude.ai CSS tokens — a more specific, product-
accurate source.
Decided: the claude.ai tokens win. Do not "correct" the palette toward the deck hexes. They describe the same identity at lower resolution.
| Brand role | Deck hex | Token | This system | Note |
| Light (text on dark) | #faf9f5 | base05 | #faf9f5 | exact match |
| Orange (primary accent) | #d97757 | base0D | #d97757 | exact match — --accent-brand |
| Dark (background) | #141413 | base00 | #1f1e1d | --bg-200 wins |
| Green (tertiary) | #788c5d | base0B | #8a9a6b | olive; base0B wins |
| Blue (secondary) | #6a9bcc | base0C | #2c84db | --accent-secondary-100 wins |
| Mid Gray | #b0aea5 | base04 / base03 | #c2c0b6 / #9c9a92 | brackets it |
| Light Gray (subtle bg) | #e8e6dc | — | — | no equivalent in a dark scheme |
Consequences you must respect:
- Orange is the primary accent, and it is exact. Spend it sparingly — one accent per view. It is the single strongest brand signal available.
base0Cis a vivid blue, not the deck's muted one. Use it for small marks (thin bars, dots, strokes) where saturation reads as precision. Never as a large fill — it goes loud next to the warm neutrals.- There is no Light Gray. Subtle backgrounds come from
base01/base02. - Accent cycling (orange → blue → green) is an upstream slide-deck behavior. Do not cycle. Pick the accent that means something; gray the rest.
Typography
| Role | Face | Stack |
| Headings / display | Poppins | "Poppins", "Inter", system-ui, sans-serif |
| Body prose | Lora | "Lora", Georgia, serif |
| Numerals, axes, UI chrome | Inter | "Inter", system-ui, sans-serif |
Lora is the system serif. lib/theme.nix → fonts.serif points Stylix at
it, so documents and prose contexts carry the brand face desktop-wide.
Poppins is installed but is not a UI font. It lives in lib/theme.nix →
brand.display, pulled into fonts.packages by modules/desktop/fonts.nix.
It is a geometric display face: right for a headline, poor at 11px. Pointing
fonts.sansSerif at it would restyle GNOME Shell, titlebars, and notifications
in a face never drawn for that job. Inter keeps the UI. Name Poppins only in an
artifact's own CSS, for headings.
Two hard constraints:
- Never fetch a webfont. Generated pages open as
file://and are specified self-contained. A Google Fonts@importfails silently and you get Arial. Because the faces are in fontconfig, naming them in CSS is enough. - Verify before relying on a face:
fc-list | grep -i poppins. If it comes back empty the system hasn't been rebuilt since the font was added.
Where this collides with dataviz — and who wins
Load both skills for a chart. Where they disagree, dataviz wins on marks and
figures; brand wins on prose.
- Serif body text is brand. But
datavizforbids a serif on the hero figure ("reads as off-brand decoration"). So: Lora for prose, Inter for the big number, axis ticks, and any tabular column. - Text never wears the data color. Brand orange on a temperature line is
correct; brand orange on the label next to it is not. Labels take
base05/base04/base03. tabular-numsonly in columns — never on a large standalone number.- Status colors (
base08warn,base0Bok) are reserved for state. They are not "accent 3," regardless of what the upstream accent-cycling section says.
Motion
Not in the upstream skill; the house style for generated pages:
- Entrance: a short staggered rise (
opacity+translateY), ~70ms apart. - Hover: a 2px lift plus a soft shadow. Never a color flip.
- Always guard with
@media (prefers-reduced-motion: reduce)— animation and transition off, and anystroke-dashoffsetdraw-on resolved to its final state, not left mid-draw.
Checklist
- No
#rrggbbanywhere in the artifact's source. (rgb(0 0 0 / .5)for a shadow is fine — that's an alpha, not a brand color.) :roottokens injected from Stylix, not typed by hand.- Poppins for headings, Lora for prose, Inter for numbers.
- Exactly one accent carries meaning; everything else is neutral.
prefers-reduced-motionhonored.- Open the file and look at it before calling it done.
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
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.

