Brand Naming logo

Brand Naming

Community
fcoury
brand-naming

Brand, company, product, feature, app, startup, and project naming workflow for generating, filtering, testing, and evaluating distinctive names. Use when the user asks to name something, rename an existing brand, brainstorm name candidates, evaluate a shortlist, avoid generic/descriptive names, check whether a name has enough energy, or design a naming exercise for a team.

Overview

Publisherfcoury
Repositorybrand-naming-codex-skill
Skill namebrand-naming
Stars
3
Forks
0
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Brand Naming 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/fcoury/brand-naming-codex-skill/tree/main/skills/brand-naming
  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/fcoury/brand-naming-codex-skill.git /tmp/brand-naming-codex-skill
mkdir -p .claude/skills
cp -r /tmp/brand-naming-codex-skill/skills/brand-naming .claude/skills/brand-naming
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Brand Naming 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 Brand Naming 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 Brand Naming 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.

Brand Naming

Use this skill to help the user create or evaluate names that are memorable, emotionally resonant, easy to process, and distinctive in their category.

The core stance: a name is not the brand, but it is the handle everything else gets poured into. Optimize for compounding advantage, not consensus comfort.

Operating Principles

  • Treat "safe" descriptive names as risky by default. They often land in the invisible zone: acceptable, professional, and forgettable.
  • Prefer names that are surprisingly familiar: easy to say and spell, but with a twist that creates a small reaction.
  • Use the tension zone. A name that some people love and some people question often has more energy than a name everyone accepts.
  • Name for what the product means, not merely what it does.
  • Generate far more raw material than feels reasonable. Quantity creates the conditions for quality.
  • Use AI for breadth, not final judgment. Human reactions, sound, context, and gut-level energy decide the shortlist.

Workflow

Run the naming process in five phases. If the user only wants one part, apply the relevant phase without forcing the whole workshop.

1. Map The Landscape

Before generating names, define the competitive territory and what to avoid.

Ask for or infer:

  • The thing being named and its category.
  • The target audience and buying context.
  • 10-20 competitors or alternatives.
  • Existing names the user admires or dislikes.
  • Constraints: tone, language, geography, legal sensitivity, domain needs, pronunciation requirements, taboo words, and must-use concepts.

Analyze competitor names for patterns:

  • Descriptive: says exactly what the company does.
  • Compound: combines category words or benefits.
  • Invented: coined but pronounceable.
  • Metaphorical: points to an adjacent idea or symbol.
  • Acronym or initialism.
  • Founder or place name.
  • Category cliche: common suffixes, prefixes, or formulas.

Then state clear boundaries:

  • "Do not use this pattern because competitors overuse it."
  • "Do not describe the category literally."
  • "Do not overfit the current feature set if the company may expand."

2. Find The Ultimate Benefit

Build a benefit ladder so names come from meaning, not feature description.

Use this ladder:

  1. Feature: what the product or service actually does.
  2. Functional benefit: what problem that solves.
  3. Emotional benefit: how the user feels after the problem is solved.
  4. Ultimate benefit: the larger aspiration, identity, or state created.

Example:

text
Feature: task tracking and team collaboration
Functional: projects get done on time
Emotional: less chaos, more control
Ultimate: clarity

Reduce the ultimate benefit to one or two words. Use those words as the creative springboard.

When possible, ask customer-facing questions:

  • "How do people feel after using this?"
  • "What changes in their day?"
  • "What identity do they get to step into?"
  • "What would they miss if it disappeared?"

3. Run The Treasure Hunt

Generate a large, messy candidate pool before judging. For serious naming work, target at least 300 candidates. For a lighter session, still aim for 60-100.

Explore from the ultimate benefit through multiple routes:

  • Synonyms and near-synonyms.
  • Etymology, Greek and Latin roots, old words, and word fragments.
  • Adjacent fields, such as optics, weather, navigation, music, architecture, biology, mythology, craft, tools, rituals, games, or geography.
  • Metaphors, objects, places, motions, textures, and moments that embody the benefit.
  • Invented words that feel pronounceable in the target language.
  • Portmanteaus and fragment combinations.
  • Sound-first candidates based on desired energy.

Use approximate thinking:

  • Keep half-formed, strange, funny, or rough ideas in the pool.
  • Do not reject too early because an idea is not polished.
  • Let weak candidates point toward stronger neighboring candidates.

Pay attention to sound symbolism:

  • Hard consonants like K, T, and P can feel precise, strong, or technical.
  • Softer sounds like L, M, and S can feel smooth, warm, or gentle.
  • V can add confidence, speed, and daring.
  • Open vowels can feel expansive; clipped syllables can feel sharp.

Say candidates out loud. Names must work in speech, not just on a page.

4. Filter Without Killing Energy

First remove obvious failures:

  • Hard to say, spell, hear, or remember.
  • Too close to a competitor.
  • Literally descriptive of the category.
  • Too narrow for the likely future of the company.
  • Unpleasant or unintended meanings in relevant languages or cultures.
  • Awkward when used in common sentences.

Useful sentence tests:

text
I work at <name>.
We use <name> for our team.
Can you send me the <name> link?
<name> raised a Series A.
<name> is replacing our old workflow.

Check basic availability when the shortlist is manageable:

  • Domains, including exact .com, credible alternates, and modifier domains such as get<name>.com, <name>hq.com, or use<name>.com.
  • Social handles if relevant.
  • Trademark conflicts. Tell the user to involve qualified counsel for legal clearance; do not present a casual search as legal advice.

Preserve polarizing names for the tension test. Do not let consensus optimize the list into blandness.

5. Tension Test And Score

Test with individual reactions, not consensus focus groups.

Ask 5-15 people, including potential customers when possible:

  • "What does this name make you feel?"
  • "What kind of company or product do you imagine?"
  • "How would you spell it after hearing it?"
  • "What does it remind you of?"

Avoid asking "Do you like it?" That question rewards personal taste and consensus. Track emotional reactions and recall.

Score finalists 1-10:

  • Distinctiveness: does it stand out from competitors?
  • Processing fluency: is it easy to say, hear, spell, and remember?
  • Emotional resonance: does it connect to the ultimate benefit?
  • Energy: does it create a reaction or tension?
  • Longevity: will it still fit in ten years?
  • Availability: are domains, handles, and trademark paths plausible?

Do not simply pick the highest average. A name with 9-10 scores in distinctiveness and energy may beat a balanced name that is merely fine.

Deliverables

Match the output to the user's request. Useful formats include:

  • Naming brief: audience, category, competitors, boundaries, benefit ladder, target feelings, and constraints.
  • Candidate batches grouped by naming territory.
  • Shortlist with rationale and risks.
  • Scorecard table for finalists.
  • Rename recommendation with story: where the brand was, where it is going, and why the new name helps.
  • Weekend workshop plan with timed phases.

When presenting names, include enough rationale to help judgment:

text
Name - type - what it evokes - why it fits - watchouts

Quality Bar

Push beyond the first pass. First-pass names are often generic, especially when AI-generated. If candidates feel like category wallpaper, go back to the benefit ladder or adjacent fields.

Reject or challenge names that:

  • End in overused category suffixes or formulas.
  • Merely combine obvious product nouns.
  • Require a paragraph of explanation before they work.
  • Sound professional but create no emotional reaction.
  • Depend on a narrow feature that may stop mattering.
  • Are clever in writing but awkward in speech.

Favor names that:

  • Are one to three syllables, ideally two.
  • Sound natural in conversation.
  • Feel like they could be real words, even when invented.
  • Create a small "wait, what?" without becoming confusing.
  • Point to the ultimate benefit through metaphor, sound, or implication.
  • Can grow with the company.

Rename Guidance

When evaluating whether to rename, look for friction:

  • People cannot spell or pronounce the current name.
  • The team constantly explains what it means.
  • It describes what the product used to do, not what it has become.
  • The domain or search situation creates repeated pain.
  • Customers confuse it with a competitor.
  • The founders cringe when saying it out loud.

For young companies, treat lost name equity as a smaller risk than years of daily friction. For established household names, require a higher bar and more careful migration planning.

When recommending a rename, include a transition story:

text
We started as <old frame>. We are becoming <new ambition>.
The new name captures <ultimate benefit> and gives us room to grow.

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 Brand Naming AI skill do?

Brand, company, product, feature, app, startup, and project naming workflow for generating, filtering, testing, and evaluating distinctive names. Use when the user asks to name something, rename an existing brand, brainstorm name candidates, evaluate a shortlist, avoid generic/descriptive names, check whether a name has enough energy, or design a naming exercise for a team.

Why use Brand Naming on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/fcoury/brand-naming-codex-skill/tree/main/skills/brand-naming. 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 Brand Naming?

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 Brand Naming?

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

Is the Brand Naming AI skill free?

Yes. It is published on GitHub by fcoury 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 👇