Visant Methodology logo

Visant Methodology

Community
pedrojaques99
visant-methodology

Visant's official brand-building methodology: 9 stages in 3 phases and the dependency cascade between them. Use to generate or audit a full branding, or to write the prompt for one stage. Use on "Visant methodology", "full branding", "audit branding", "metodologia Visant", "branding completo", "auditar branding".

Overview

Publisherpedrojaques99
Repositoryvisant-skills-public
Skill namevisant-methodology
Stars
81
Forks
1
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by pedrojaques99 on GitHub. Read the source before you install it.

Installation

Install the Visant Methodology AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/pedrojaques99/visant-skills-public/tree/main/visant-methodology
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/pedrojaques99/visant-skills-public.git /tmp/visant-skills-public
mkdir -p .claude/skills
cp -r /tmp/visant-skills-public/visant-methodology .claude/skills/visant-methodology
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Visant Methodology in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Visant Methodology on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Visant Methodology is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Visant Methodology

"Marca não se desenha no feeling. É consequência de um processo bem feito." (A brand is not designed on gut feeling. It is the consequence of a well-run process.)

Stage names are kept in Portuguese (with English in parentheses) because they are the official terms used in Visant's material and deliverables.

Structure: 3 phases, 9 stages (cascade)

Each stage feeds the next. Skipping stages weakens the brand.


PHASE 1: A ESTRATÉGIA (strategy, the brain)

Stage 01: Mensagem Central & Pilares (central message and pillars)

Mensagem Central = an INTERNAL technical sentence (not a slogan).

PRODUCT + DIFFERENTIATOR + EMOTIONAL LINK = Mensagem Central
  • Product: what is technically being sold.
  • Differentiator: what sets the offer apart from others in the same field.
  • Emotional link (Elo Emocional): the feeling that creates connection.

The 3 Pillars: core values. A good pillar: if violated, the brand stops being itself. A good pillar: the brand can DO it, not just say it.

Example (a racket-sports matchmaking app):

  • MC: "A matchmaking app for racket sports whose edge is the social side: it makes players feel part of a community."
  • Pillars: Belonging | Shared Progress | Ease

Stage 02: Pesquisa de Mercado & Persona (market research and persona)

Research ≠ inspiration. A moodboard is not a diagnosis.

3 layers to map:

  1. What competitors deliver well (do not compete there)
  2. What everyone delivers badly (opportunity)
  3. What nobody delivers (free territory)

The market's unresolved frustration is the gold.

Visant persona: focus on pains, longings and hidden needs, not demographics.

  • ~8 named pains/desires (Dor 01, Dor 02, Desejo 01...)
  • Name, age, real context
  • Questions: what do they want and cannot get? What do they try to solve alone and fail? What do they fear?

Stage 03: Arquétipos & Tom de Voz (archetypes and tone of voice)

A brand is a person. Mix of primary + secondary (only one = one-dimensional).

Key question: "If this brand were a person, how would it behave at a bar table with strangers?"

Visant's 12 archetypes:

  1. O Explorador / Explorer (curiosity, challenge)
  2. O Cara Comum / Everyman (belonging, authenticity)
  3. O Herói / Hero (overcoming, conquest)
  4. O Sábio / Sage (knowledge, clarity)
  5. O Cuidador / Caregiver (protection, safety)
  6. O Governante / Ruler (authority, control)
  7. O Mago / Magician (innovation, disruption)
  8. O Rebelde / Rebel (change, freedom)
  9. O Criador / Creator (originality, expression)
  10. O Prestativo / Helper (serving, making easy)
  11. O Amante / Lover (desire, sensoriality)
  12. O Bobo / Jester (humor, irreverence)

Tone of voice = 3 tone pillars, each with an example sentence.


Stage 04: Manifesto

Condenses the strategy into words that breathe. If the Mensagem Central faces inward, the Manifesto faces outward.

3 movements:

  1. Provocation: a question/image the reader recognizes ("yes, that's me")
  2. Tension: the problem that exists: frustration, lack, discomfort
  3. Promise: what the brand does, with whom, for what. A final impact sentence.

Slogan suggestion: the manifesto's final sentence becomes a slogan candidate.


PHASE 2: A IDENTIDADE VISUAL (visual identity, the face)

Stage 05: Logotipo & Geometria (logo and geometry)

3 steps: Concept → Sketch → Construction & Test

  • List what the symbol must communicate (from the Pillars and Archetype)
  • A logo built on a grid = professionalism and longevity
  • Apply it to layouts BEFORE refining (an isolated logo deceives)

Note: visual stage. AI generates conceptual guidelines, not the logo itself.


Stage 06: Cromatismo & Tipografia (color and typography)

Palette + typography = 80% of a brand's tone.

Palette: a named color is a color with purpose. Each color gets a name that says when to use it. Example: "Matchday Green" (#9BAE00), the game-day green, dense, mature.

Type pair (at least 2 families):

  • Headline: emphasis, large titles, visual accent.
  • Body (legibility): running text, neutral, clear at small sizes.

Stage 07: Sistema Gráfico & Layouts (graphic system and layouts)

A strong brand is recognized even without the logo showing.

4 components:

  1. Patterns: for backgrounds, fabrics, packaging.
  2. Graphic elements (grafismos): the brand's own shapes/illustrations.
  3. Image rules: how it photographs, crops, which filters it applies.
  4. Editorial grids: the grid that organizes posts, pages, presentations.

PHASE 3: O RITUAL (the ritual, delivery)

Stage 08: Apresentação (presentation, 40 slides)

The client needs to see the PROCESS before seeing the RESULT.

3 principles:

  1. Narrative before the result (suspense)
  2. One decision at a time
  3. Confidence and authority

Stage 09: Manual & Entrega (brand system)

3 layers: Understanding (manual) | Operation (files) | Preservation (usage rules)


The Visant Decalogue

  1. A brand is not designed on gut feeling. It is the consequence of a well-run process.
  2. With strategy and visual theme defined, aesthetics gain a unique personality.
  3. Discovering the audience's desires is what makes clients buy a brand.
  4. Market research is essential to find what nobody is doing.
  5. A strong brand is recognized even without the logo showing.
  6. A well-made presentation sells the process.
  7. The work only ends when the brand withstands time on its own.
  8. Processes free mental space for you to be creative.
  9. Good brand immersion is what most prevents change requests.
  10. The goal is to turn clients into fans before they know the product.

Applying it in an AI generator

Visant Labs' branding generator (the "branding machine", branding-generate in visant-mcp-connect) follows this cascade. When generating branding with any AI, follow it strictly:

StepVisant stageBrandingData fieldDepends on
1Mensagem Central & PilarescentralMessage, pillarsprompt
2Market researchmarketResearch (3 layers)step 1
3Personapersona (8 pains/desires)steps 1-2
4Archetypes & tone of voicearchetypes, toneOfVoicesteps 1-3
5Manifesto & sloganmanifesto, sloganSuggestionsteps 1-4
6SWOT analysisswotsteps 1-3
7Color palettecolorPalette (named colors)steps 1-5
8Type pairtypographysteps 1-5
9Graphic systemgraphicSystemsteps 5-8
10Logo conceptlogoConceptsteps 1-5, 7-8

Golden rule: every generation prompt MUST receive the outputs of the previous stages as context. The cascade is what makes the AI generate with coherence instead of genericness.


Glossary

TermDefinition
Brand SystemFull package of final deliverables
Cascata (cascade)Dependency logic: each stage feeds the next
Cromatismo DinâmicoValidating palettes by applying them to real layouts
Elo EmocionalThe feeling the brand conveys (3rd ingredient of the MC)
Identidade FlexívelA graphic system that holds up on any surface
ManifestoEmotional, public declaration of the brand's existence
Mensagem CentralInternal technical sentence: Product + Differentiator + Emotional link
Mix ArquetípicoCombination of primary and secondary archetype
Pilares3 values that, if violated, make the brand stop being itself
Sistema GráficoVisual elements that let the brand be recognized without the logo

Neighbors

  • [[visant-mcp-connect]]: the tools that run each stage
  • [[visant-brand-sync]]: reconcile a brand that already exists

Frequently asked questions

What does the Visant Methodology AI skill do?

Visant's official brand-building methodology: 9 stages in 3 phases and the dependency cascade between them. Use to generate or audit a full branding, or to write the prompt for one stage. Use on "Visant methodology", "full branding", "audit branding", "metodologia Visant", "branding completo", "auditar branding".

Why use Visant Methodology on TypingMind?

Because you install it once and use it with any model. Visant Methodology is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Visant Methodology in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pedrojaques99/visant-skills-public/tree/main/visant-methodology. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Visant Methodology?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Visant Methodology?

As many as you like. As long as a model supports skills, you can use Visant Methodology with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Visant Methodology AI skill free?

Yes. It is published on GitHub by pedrojaques99 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇