brand-system
Skill0 starsChanged 34 days agoMITView on GitHub
Compile the decided logo, type, and color into design tokens, a CSS theme, a brand board, and written guidelines.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- shaharsha/claude-skillstheir own version, first seen Oct 24, 2026
- timscheuerai/gtm-architecture-templatetheir own version, first seen Sep 14, 2026
- aamirqutub/claude-skillstheir own version, first seen Aug 9, 2026
- appautomaton/presentationtheir own version, first seen Jul 8, 2026
- firefly-events/plugin-hivetheir own version, first seen May 18, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- appautomaton/presentation★ 57same name
- shaharsha/claude-skills★ 6same name
- timscheuerai/gtm-architecture-template★ 2same name
- firefly-events/plugin-hive★ 1same name
- aamirqutub/claude-skills★ 0same name
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 repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ask-designerSkill
- brand-contextSkill
- brand-imageSkill
- brand-intakeSkill
- color-systemSkill
- design-briefSkill
- design-craftSkill
- design-critiqueSkill
- design-grillingSkill
- design-routesSkill
- grill-brandSkill
- logo-labSkill
- make-graphicSkill
- type-systemSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
Look at the board rendered at 390 px and 1280 px, and take a screenshot when a browser tool exists.
“Common” is measured: kept by at least 6 in 10 of the 5 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
Brand system
Guidelines are what let a brand survive other people's hands: the NASA Graphics Standards Manual is the famous case, one binder that told everyone how typography, color, stationery, signage, and vehicles carried the identity (Danne & Blackburn, 1975; reissued by Standards Manual). This skill compiles what the human decided into the same kind of artifact: tokens a machine reads, a theme a page loads, a board a person looks at, and rules everyone follows.
Load the brand-context and design-craft skills (the Skill tool, or read their SKILL.md). Reply in the user's language.
1. Check the pillars
Read the Status table. Logo, Typography, and Color must be decided. For any that is not, name it and tell the human which command to run (/logo-lab, /type-system, /color-system), then stop. Graphic language, Layout, and Voice may be filled in here, with the human's confirmation.
2. Write the tokens
Complete brand/tokens.json. When it already exists (/type-system and /color-system create it), merge in what is missing and keep what the human decided; otherwise create it from templates/tokens.template.json, replacing every value including $description. The group names are in TOKENS.md in brand-context. The file is DTCG-style ($value, $type, aliases like {color.brand.700}), with hex strings for color. Groups: color, font, size, leading, space, radius, shadow, an optional dark group of overrides, fontImport (the Google Fonts URL), and the contrast pairs under $extensions["graphic-skills"].pairs.
Then run both checks from the project root, with <design-craft> and <brand-system> standing for those skills' folders, and fix the tokens until each exits 0:
node <design-craft>/scripts/contrast.mjs --tokens brand/tokens.json
node <brand-system>/scripts/build-theme.mjs brand/tokens.json brand/theme.csstheme.css is generated; edit the tokens, never the CSS.
3. Build the brand board
Create brand/brand-board.html from templates/brand-board.html: one page that links theme.css and shows the idea, the logo kit with clear space, the palette with roles and contrast ratios, the type specimens, the graphic-language motifs, the layout rules, voice samples, and do and don't. The template is a worked example; replace all of its content. Search the finished file for the sample content listed in the template's header comment (the sample brand names, the sample person and route names, the sample hex values, the sample fonts); none may remain.
Look at the board rendered at 390 px and 1280 px, and take a screenshot when a browser tool exists.
4. Write the guidelines
Complete the brand memory so a stranger could use the brand correctly:
- Logo: clear space, minimum sizes, misuse (from
/logo-lab). - Color: roles, proportions, the contrast table (from the script).
- Typography: roles, scale, per-script line heights.
- Graphic language: three motifs at most, each as a rule (see
graphic-language.md), plus the Image recipe when an image generator is in use (seeimage-prompts.md). - Layout: grid, margins, the spacing scale, and the composition rule for each top channel from Strategy.
- Voice: tone, register, words used and avoided.
- Accessibility floor and Guardrails.
Offer to add the pointer line to AGENTS.md or CLAUDE.md (see brand-context).
5. Done
The skill is done when both scripts exit 0 with every declared pair passing, the board was seen rendered with no sample content left, every Status row reads decided or deferred with a reason (set each completed pillar to decided as the human confirms it), and the human confirmed the guidelines. Tell them the next commands: /design-brief, then /make-graphic.
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.

