brand-guidelines

An agent skill by anthropics, from anthropics/skills. Tags: anthropic, design, documents, visual-art.

What it does

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add anthropics/skills --skill brand-guidelines

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/anthropics/skills
cp -r skills/skills/brand-guidelines ~/.claude/skills/brand-guidelines

Safety box score

Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is documentation-only: it defines Anthropic brand colors, typography, and styling preferences, with no executable code, downloads, or file mutation commands. The main thing you grant by using it is visual reformatting of artifacts, not access to machine, accounts, or data.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	`SKILL.md` contains only branding guidance and no scripts, shell commands, or code evaluation.
Network access	0 (none)	There are no URLs to fetch or data to send; the only external reference is the Apache license text in `LICENSE.txt`.
Filesystem reach	0 (none)	The files describe styling rules but do not read, write, or delete any paths on disk.
Secrets & credentials	0 (none)	Nothing in the skill asks for tokens, keys, passwords, `.env` files, or other credentials.
Privilege & persistence	0 (none)	No sudo, installs, services, shell profile edits, or other privilege-changing actions appear in the files.
Instruction hijack surface	0 (none)	The content does not instruct the agent to ignore rules, hide actions, or follow fetched instructions.
Irreversible actions	0 (none)	It only applies styling guidance; it does not send messages, publish, deploy, pay, or delete anything.
Transparency	0 (none)	All shipped files are plain-text markdown/license files; there are no binaries, installers, or decoded-at-runtime blobs.

Before installing

Confirm you want Anthropic-style branding applied to the artifacts this skill touches.
If your environment relies on custom fonts, check that Poppins and Lora are available or that the fallback fonts are acceptable.

Rated 2026-10-16 by an automated review of 2 files from the skill's repository.

Source

Repository: anthropics/skills (all skills from this repository)
Path: skills/brand-guidelines/SKILL.md
Branch: main
Updated: 2026-09-19

canvas-design — Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art.
theme-factory — Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc.
algorithmic-art — Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code.
frontend-design — Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one.
pptx — Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks.
slack-gif-creator — Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts.