taste-brand
Skill4 starsChanged 16 days agoMITView on GitHub
Defines positioning, personality, voice, tone, messaging and visual identity direction, then freezes them into brand-guidelines.md for every other Tastemaker skill. Use for "brand", "voice and tone", "messaging", "tagline", "brand guidelines", "copy feels generic", or as a 10-line Light pass before landing pages, banners and decks. Bans hype copy and imitation of real brands.
In this repository12 other files it gives its agents.
- dist/AGENTS.mdAGENTS.md
- dist/copilot-instructions.mdCopilot instructions
- taste-auditSkill
- taste-bannersSkill
- taste-briefSkill
- taste-componentsSkill
- taste-directionSkill
- taste-guardSkill
- taste-identitySkill
- tastemakerSkill
- taste-slidesSkill
- taste-tokensSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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 10
Originality is mandatory: never imitate a real brand's name, slogan, mark or distinctive visual signature.
- Distinctive: line 44
No hype words (C01), no invented proof (C03), no "Welcome to" (C05).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Taste Brand: specific beats clever
Freeze who the product is, how it sounds and how it looks into brand-guidelines.md. Downstream skills read it and never re-invent it.
Originality is mandatory: never imitate a real brand's name, slogan, mark or distinctive visual signature. From a reference, extract abstract principles only ("geometric, calm, single accent").
Modes
- Light (default for UI, banners, slides): fill the 10-line essentials below and write them to
brand-guidelines.md. - Full (explicit brand request): run all steps; produce the full guidelines from
references/guidelines-template.md.
Full procedure
- Discovery (infer; ask max 3 questions): one-liner, audiences, category and alternative types, promise, proof points, tone constraints, locales, existing assets, no-go list. Output a 15-line Brand Brief.
- Positioning: "For
<audience>who<need>,<Brand>is the<category>that<benefit>, unlike<alternative type>, because<reason to believe>." Plus purpose, vision, mission, 3-5 values each with a behaviour example, max 3 differentiators each with evidence. - Personality and voice: sliders and principles in
references/voice-and-messaging.md. - Messaging: tagline, value proposition, pitch, pillars, boilerplate, per-audience messages.
- Visual direction: color, type, imagery, iconography, radius/elevation, motion, data-viz palette, each with one line of rationale tied to the sliders. Hand concrete values to taste-tokens.
- Consistency audit on any deliverable (table in references); output fails with exact fixes, then apply them.
Light essentials (10 lines)
Name / one-liner:
Audience:
Voice: <3 adjectives> | never: <3 banned traits>
Primary / accent / neutral + one verified contrast pair:
Heading / body font:
Radius + elevation language:
Icon style:
Imagery rule:
Tagline (original, passes competitor test):
Button verb pattern:Copy laws (apply everywhere)
- Competitor test: if a competitor could use the line unchanged, rewrite with specifics (audience, number, mechanism).
- No hype words (C01), no invented proof (C03), no "Welcome to" (C05).
- Buttons: verb + object. Errors: what, why, fix, no blame. Sentence case. No emoji. Numerals with units and locale formats.
- Inclusive, plain language; no idioms that do not translate.
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.

