brand-context
Skill0 starsChanged 34 days agoMITView on GitHub
Load the project's brand memory (brand/BRAND.md) before any graphic or visual work, and define its format. Use when asked to design, make, edit, or judge a logo, poster, social post, banner, slide, packaging, UI, colors, fonts, theme, or any brand, CI, or identity question; or when another graphic skill needs the brand.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- vercel/evetheir own version, first seen Nov 15, 2026
- vercel-labs/marketing-team-eve-templatetheir own version, first seen Nov 12, 2026
- cofoundy/brand-skillstheir own version, first seen Oct 13, 2026
- egdev6/discord-project-managertheir own version, first seen Oct 13, 2026
- akachandan1/proofstacktheir own version, first seen Oct 11, 2026
- skyf0xx/gambittheir own version, first seen Sep 30, 2026
Used with
Projects with it also use brand-story and brand-voice.
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.
akachandan1Skillbrand-story
Receipts-based marketing storytelling engine for LinkedIn and X personal-brand, founder, and brand accounts. Use when the user wants to plan social content, write a LinkedIn post or X thread, research what's being said on social platforms before writing, react to a trend, or build a content calendar. Triggers: "brand story", "plan my content", "write a post", "LinkedIn post", "X thread", "tweet", "content calendar", "what should I post", "social listening", "research this topic", "react to this", "post about", "founder content".
Also in 3 projects that use this
Dokkabei97Skillbrand-voice
Defines and enforces brand voice guidelines for startups. Creates tone, style, messaging frameworks and provides consistency checks across all content. Ensures every piece of communication sounds like it comes from the same brand.
Also in 3 projects that use this
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- vercel/eve★ 5.9ksame name
- vercel-labs/marketing-team-eve-template★ 456same name
- hyperfx-ai/marketing-skills★ 112same name
- cofoundy/brand-skills★ 79same name
- skyf0xx/gambit★ 29same name
- egdev6/discord-project-manager★ 4same name
- productionx-in/Core-Skills★ 1same name
- akachandan1/proofstack★ 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-imageSkill
- brand-intakeSkill
- brand-systemSkill
- 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
5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read BRAND.md in full, then tokens.json and theme.css when present.
- Very specific: line 13
Read the Status table. decided binds the work.
- Very specific: line 22
Create the file by copying BRAND-TEMPLATE.md into brand/BRAND.md and filling the title.
- Very specific: line 24
When the human confirms a pillar, set its Status row to decided, or to deferred (reason) with an Open questions row.
- Distinctive: line 25
Keep the file short enough to read in one pass.
“Common” is measured: kept by at least 6 in 10 of the 8 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 context
The brand memory is brand/BRAND.md in the working directory, beside tokens.json and theme.css once they exist. A project with several brands keeps one folder each at brands/<slug>/; ask which one when the request doesn't say. A graphic made without the brand memory is generic by construction, so every graphic decision starts here.
Load
- Read
BRAND.mdin full, thentokens.jsonandtheme.csswhen present. - Read the Status table.
decidedbinds the work.observedis the default, and you flag every departure from it.openor missing means ask the one question that unblocks, or make a provisional choice and log it. - Take every color, font, and space value from the tokens. A value the tokens lack is a new token, added there first (see TOKENS.md).
When the brand memory is missing
/brand-intake and /grill-brand create it; they skip this section. For any other command or request, tell the human in one line: "No brand memory yet. Type /brand-intake if you have existing logo, fonts, or colors, or /grill-brand to shape one from scratch." You cannot fire those yourself, since only the human can. If they want to proceed anyway, label the output an unbranded sketch and keep it plain.
Writing to the brand memory
- Create the file by copying BRAND-TEMPLATE.md into
brand/BRAND.mdand filling the title. Section headings stay in English because other skills look them up; the content is in the user's language. - Edit in place, one fact in one place. Every change to a pillar adds a Decision log row: date, decision, why, alternatives rejected.
- When the human confirms a pillar, set its Status row to
decided, or todeferred (reason)with an Open questions row. Later commands gate ondecided, so a pillar left atopenafter a confirmed decision blocks them. - Keep the file short enough to read in one pass. Detail that outgrows it moves to a sibling file the section points at.
- Status vocabulary:
open(nobody decided),observed(found in existing assets, not yet confirmed),decided(the human confirmed),deferred(parked, with a reason). - Values for colors, fonts, and spacing live in the tokens, with the reasons in
BRAND.md. - Offer once to add a one-line pointer to the project's
AGENTS.mdorCLAUDE.md: "Brand memory lives inbrand/BRAND.md; read it before any graphic work."
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.