Build Startup Brand logo

Build Startup Brand

Community
Kappaemme-git
build-startup-brand

Turn a startup idea, product, URL, pitch, or existing visual identity into a distinctive startup brand system and a polished standalone HTML report. Use when Codex needs to create or refine startup positioning, a salient brand idea, brand promise, tagline, messaging, voice, creative territories, logo or symbol directions, color palette, typography, visual language, brand applications, or compact brand guidelines. Also use for startup rebrands and brand audits that should end with an actionable, openable brand identity report.

Overview

PublisherKappaemme-git
Repositorybuild-startup-brand
Skill namebuild-startup-brand
Stars
24
Forks
1
Bundled files
9
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.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Kappaemme-git on GitHub. Read the source before you install it.

Installation

Install the Build Startup Brand 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/Kappaemme-git/build-startup-brand/tree/main
  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/Kappaemme-git/build-startup-brand.git \
  .claude/skills/build-startup-brand
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Build Startup Brand 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 Build Startup Brand 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 Build Startup Brand 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.

Build Startup Brand

Turn strategy into three differentiated creative territories, then develop the selected territory into a usable brand system. Deliver the work in conversation and in a standalone HTML report the user can open in Codex.

Language

  • Always conduct the conversation, discovery questions, analysis, recommendations, creative territories, brand copy, and final report in English.
  • Use English even when the user writes in another language or supplies non-English material.
  • Translate relevant input into English before developing the brand. Preserve proper nouns, registered product names, URLs, and source quotations when accuracy requires it.
  • Set meta.language to en in every report JSON.

Read the right references

Choose the mode

  • new-brand — Build a brand for a new startup. Use by default.
  • rebrand — Preserve valuable recognition while solving specific brand problems.
  • strategy-only — Stop after positioning, salient idea, promise, and messaging.
  • territories — Deliver and score three creative territories, then stop for selection.
  • full — Run discovery, territories, selection, complete system, and report.
  • one-shot — When the user cannot review intermediate work, recommend one provisional route and complete it while marking assumptions clearly.

Use full unless the request implies another mode.

Run the workflow

1. Inspect before asking

  • Inspect any supplied URL, repository, pitch, screenshots, notes, or existing identity.
  • Extract the product, stage, audience, job or pain, category, alternatives, promise, proof, personality, constraints, and existing brand equity.
  • If current competitors, visual conventions, domains, or market claims matter, research current primary sources. Cite material facts in the report.
  • Ask only for information that is missing and would change the direction. Prefer one compact batch of no more than five questions.
  • Never ask the user to repeat information already available in the supplied material.

2. Establish the strategic core

  • Define one primary audience and one buying or adoption trigger.
  • State the category or competitive frame, current alternative, distinctive value, credible proof, and desired perception.
  • Write one positioning statement, one salient brand idea, and one brand promise.
  • Separate fact, user-provided claim, inference, and creative recommendation.
  • Stop and expose the weakness when the startup lacks a specific audience, meaningful difference, or credible promise. Do not hide a positioning problem behind visual polish.

3. Build three territories

  • Create exactly three strategically valid and visibly different creative territories.
  • Give each territory a name, thesis, metaphor, tagline direction, voice, symbol direction, palette, typography direction, application example, and principal risk.
  • Make each territory traceable to the same strategic core while expressing a different personality or mechanism.
  • Score all territories with the weighted framework in references/creative-territories.md.
  • Recommend the strongest territory and explain the trade-off, not merely the total score.
  • Create the first HTML report containing the strategic core, three territories, scores, recommendation, assumptions, and open questions.

4. Pause for selection

  • Ask the user to select a territory or request a hybrid.
  • Do not silently combine routes. A hybrid must name exactly which elements come from which territory and why they remain coherent.
  • Skip the pause only in one-shot mode; label the selected route provisional.

5. Develop the selected system

  • Produce the messaging hierarchy, tagline, voice traits, vocabulary, color roles, typography roles, symbol logic, image direction, layout principles, and usage rules.
  • Show at least four applications relevant to the startup, such as landing-page hero, product UI, social post, pitch cover, sales deck, packaging, or favicon.
  • Use image generation for moodboards, art direction, or concept exploration when it materially improves the result.
  • Do not present generated raster lettering as a production-ready logo. Rebuild approved simple marks as clean SVG when feasible, or label them as concept art requiring vector refinement.
  • Check legibility, color contrast, monochrome behavior, small-size behavior, category confusion, and obvious similarity to named competitors.

6. Deliver the final report

  • Store structured source data as outputs/<startup-slug>-brand-identity.json.
  • Generate outputs/<startup-slug>-brand-identity.html with:
bash
node scripts/generate_report.mjs <input.json> <output.html>
  • Open or inspect the generated report and verify its layout, content, scores, palette, and applications.
  • Return a clickable absolute link to the HTML report.
  • Keep the JSON beside the report so future iterations can update the identity without starting over.

Enforce the quality bar

  • Build for a startup, not for the founder's personal brand.
  • Produce every user-facing deliverable in English.
  • Prefer one ownable idea over a collection of generic values.
  • Treat the current workaround and doing nothing as competitors.
  • Never invent customer evidence, traction, market facts, testimonials, or legal clearance.
  • Avoid unsupported superlatives and default startup language such as “innovative,” “disruptive,” “game-changing,” and “next-generation.”
  • Make distinctiveness strategic, verbal, and visual; unusual colors alone do not create a brand.
  • Keep taglines short, specific, comprehensible without a pitch, and connected to the promise.
  • Use accessible body-text color combinations. Flag decorative combinations that fail normal-text contrast.
  • Treat competitor screening as preliminary and trademark availability as unverified unless a qualified search proves otherwise.
  • End with concrete next tests: five-second recognition, audience comprehension, monochrome, favicon, landing-page message, and competitor-confusion checks.

Default deliverable

Deliver:

  1. Strategic core
  2. Three creative territories
  3. Weighted scorecard and recommendation
  4. Selected brand system
  5. Verbal identity
  6. Visual identity
  7. Application examples
  8. Do and don't rules
  9. Risks, assumptions, and validation plan
  10. Standalone HTML report plus editable JSON source

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Build Startup Brand AI skill do?

Turn a startup idea, product, URL, pitch, or existing visual identity into a distinctive startup brand system and a polished standalone HTML report. Use when Codex needs to create or refine startup positioning, a salient brand idea, brand promise, tagline, messaging, voice, creative territories, logo or symbol directions, color palette, typography, visual language, brand applications, or compact brand guidelines. Also use for startup rebrands and brand audits that should end with an actionable, openable brand identity report.

Why use Build Startup Brand on TypingMind?

Because you install it once and use it with any model. Build Startup Brand 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 Build Startup Brand in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Kappaemme-git/build-startup-brand/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Build Startup Brand?

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 Build Startup Brand?

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

Is the Build Startup Brand AI skill free?

Yes. It is published on GitHub by Kappaemme-git 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 👇