agentleFS
forsvn-labsforsvn-labs/meta-skills/skills/create-brand/SKILL.md

create-brand

Skill14 starsChanged 3 months agoMITView on GitHub

Create or refine a practical brand foundation. Use for brand strategy, point of view, voice, messaging architecture, naming direction, verbal identity, visual creative direction, founder-versus-company voice, or a compact brand system that operators and creators can apply consistently.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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
  1. Distinctive:

    Do not turn archetypes into costumes.

    line 28
  2. Distinctive:

    Keep identity direction implementable without prescribing arbitrary aesthetics.

    line 44
  3. Distinctive:

    Read the voice aloud. If it requires constant performance from the real operator, simplify it.

    line 50
  4. Distinctive:

    Remove unsupported superlatives, false urgency, and borrowed category slogans.

    line 51
  5. Distinctive:

    Check that strategy, copy, visual direction, and product behavior make the same promise.

    line 52
  6. Distinctive:

    Do not invent product claims, customer evidence, or endorsements.

    line 57

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Create a practical brand foundation

Build a distinctive, usable brand system from product truth. Do not apply FORSVN's house style to a customer brand.

Ground the brand

Infer existing decisions from the product, audience, shipped interface, customer language, and current materials. Separate what the product proves today from the aspiration it is growing toward.

Define:

  • audience and high-friction moment;
  • product mechanism and credible change;
  • main alternative and useful tension;
  • available proof;
  • operator or founder personality that can be sustained;
  • category conventions worth keeping or rejecting.

Do not turn archetypes into costumes. Build distinction from a defensible mechanism, tension, or point of view. Decide whether each statement belongs to the founder, company, or product.

Create the system

Produce:

  1. Brand idea — one durable organizing thought.
  2. Position and promise — specific audience, moment, mechanism, and credible outcome.
  3. Point of view — what the brand believes that changes how it acts.
  4. Message architecture — primary promise, supporting pillars, proof, objections, and boundaries.
  5. Voice — three to five behavioral traits, each with “do” and “avoid” examples.
  6. Verbal patterns — vocabulary to own, language to avoid, naming and CTA behavior.
  7. Creative direction — visual principles, hierarchy, imagery, motion, and evidence treatment.
  8. Applications — representative homepage hero, product description, and social introduction.

Keep identity direction implementable without prescribing arbitrary aesthetics. Preserve accessibility, legibility, localization, and the product's real maturity.

Quality gate

  • Replace the name with a competitor. If the system still fits, add product mechanism or evidence.
  • Read the voice aloud. If it requires constant performance from the real operator, simplify it.
  • Remove unsupported superlatives, false urgency, and borrowed category slogans.
  • Check that strategy, copy, visual direction, and product behavior make the same promise.

Deliver the compact foundation first. Label provisional decisions and name the evidence needed to make them durable.

Do not invent product claims, customer evidence, or endorsements. Keep publication and external writes behind explicit approval.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.