agentleFS
fatih-developerfatih-developer/fth-skills/skills/brand-name-lab/SKILL.md

brand-name-lab

Skill7 starsChanged 43 days agoMITView on GitHub

Develop, compare, refine, or audit strategic names for companies, products, services, applications, platforms, features, and rebrands. Use when a user asks for brand or company name ideas, wants names from particular languages or concepts, rejects earlier suggestions, needs a shortlist or final choice, wants a naming method, or asks to check pronunciation, memorability, meaning, brand architecture, domain, social-handle, company-name, or trademark risk.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this unified operational flow for end-to-end naming tasks (Develop mode).

    line 25
  2. Distinctive:

    Before generating names, lock in the alignment.

    line 28
  3. Distinctive:

    Ask for any existing preferred or rejected names.

    line 31
  4. Distinctive:

    Use mind maps, synonyms, metaphors (animals, vehicles, mythology).

    line 49
  5. Distinctive:

    Do not stop at the first 10 obvious ideas.

    line 51
  6. Very specific:

    If exact .com is unavailable/expensive, use strategic workarounds:

    line 84
  7. Very specific:

    Add a prefix/suffix (get, try, use) or category descriptor (...crm.com, ...fund.com).

    line 85
  8. Very specific:

    Use alternative TLDs accepted in the industry (e.g., .io, .co, .ai for SaaS).

    line 86
  9. Very specific:

    Avoid "Hot Garbage": Do not stack workarounds (e.g., getxxxcrm.io).

    line 87

≈ “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

Brand Name Lab

Create names from brand strategy rather than from random attractive words. Separate ideation from validation, produce breadth internally, and show only candidates that survive the requested level of screening. A name is the most enduring asset of a brand; approach it as a strategic and verifiable product, not a 20-minute creative exercise.

CRITICAL LANGUAGE RULE: The instructions in this skill are written in English, but you MUST respond in the language of the user's request. All outputs, explanations, candidates, categories, and findings must be delivered in the user's language unless otherwise specified.

Select the working mode

Choose the lightest mode that satisfies the request:

  1. Explore — Generate fresh directions or a varied candidate list.
  2. Develop — Build a reasoned shortlist and compare candidates using the full process.
  3. Audit — Evaluate one or more existing names.
  4. Validate — Research finalists for linguistic, digital, corporate, and trademark risk.

Infer the mode from the request. When the user asks for the best name, a final choice, availability, or a decision, use Develop and follow the 10-step playbook.

The 10-Step Naming Playbook

Use this unified operational flow for end-to-end naming tasks (Develop mode).

1. Naming Brief

Before generating names, lock in the alignment.

  • Determine if naming a parent company, product, or feature taxonomy.
  • Identify the core ideas, tone/personality, target audience, and language/geography constraints.
  • Ask for any existing preferred or rejected names.

2. Type & "Big Idea" Selection

Select the appropriate name types and the emotional promise (the "Big Idea"). 7 Name Types:

  • Eponymous: Named after a person (e.g., Disney).
  • Descriptive: Says what it does (e.g., The Home Depot). Hard to protect.
  • Acronym: (e.g., KFC, GE).
  • Real Words: Dictionary words carrying attribute/benefit (e.g., Uber, Slack). Note: pure real words are largely unavailable globally.
  • Composite: Two words combined (e.g., Facebook, Ray-Ban). Highly memorable.
  • Invented: Added/removed/changed letters (e.g., Kleenex). Distinctive but can sound generic.
  • Associative: Reflects imagery and meaning (e.g., Amazon, Sirius).
  • (Additional layers) Non-English (e.g., Lego, Hulu) and Abstract (pure phonetic power, e.g., Kodak).

For parent companies, prefer carrying a "Big Idea" (e.g., Nike = winning, GoPro = heroism) rather than being purely descriptive.

3. Generate (Volume is Key)

Generate a massive internal list (100+ candidates).

  • Use mind maps, synonyms, metaphors (animals, vehicles, mythology).
  • Explore etymology, word parts, foreign languages, and composites.
  • Do not stop at the first 10 obvious ideas.

4. Sound & Memory Filter (Phonological Loop)

Evaluate candidates for 3-second working memory stickiness.

  • Alliteration: Repeating sounds (e.g., Coca-Cola, PayPal).
  • Rhyme: Rhyming syllables. Does the name bounce in the phonological loop? If yes, it has a massive marketing advantage.

5. Shortlist & Practical Tests

Narrow down to a solid shortlist (20-100 internally, 5-10 to present) using these critical tests:

  • Crowded Bar Test: Can it be heard, understood, and remembered in a noisy bar?
  • Spell / Autocorrect Test: Will Google ask "Did you mean..."? Is it hard to spell after hearing it once? (Avoid clever misspelling traps).
  • Pronounceability Test: Will 5-10 people read it the same way?
  • Own the Search: Is it unique enough that you will own the day-one SERP?

6. Screening (Linguistic & Cultural)

  • Language Fail: Does it mean something embarrassing or offensive in target languages?
  • Cultural: Does it risk cultural appropriation or misalignment?
  • Restrictive: Does it lock the company into a narrow product line, killing future pivots?

7. Presenting

Present the finalists strategically.

  • Group by semantic territory or name type.
  • Provide pronunciation, meaning/origin, and a one-line strategic rationale for each.
  • Include Brand Architecture tests (e.g., <Product> by <Company>, <Company> <Module>).

8. Full Legal (Advisory)

  • Conduct a preliminary trademark search in relevant classes and territories.
  • Disclaimer: Always state that this is a preliminary screening and recommend qualified trademark counsel for final clearance.

9. Domain Strategy

  • Check domain availability.
  • Rule: Brand name comes first, domain second.
  • If exact .com is unavailable/expensive, use strategic workarounds:
    • Add a prefix/suffix (get, try, use) or category descriptor (...crm.com, ...fund.com).
    • Use alternative TLDs accepted in the industry (e.g., .io, .co, .ai for SaaS).
  • Avoid "Hot Garbage": Do not stack workarounds (e.g., getxxxcrm.io). Keep it clean.

10. Select & Lock

  • Recommend the final choice based on strategic fit, sound memory, and availability.
  • Visual identity (logo) should only be designed after the name is locked.

Score and compare

For detailed comparative evaluation of finalists, read references/naming-scorecard.md and apply its weighted scorecard.

Common Pitfalls to Avoid (Master List)

  1. Skipping the strategic brief.
  2. Settling for the first 10 ideas.
  3. Choosing a name meaningful to the founder but empty to the customer.
  4. Using overly clever puns or misspellings (e.g., Flickr, Lyft) that require constant explanation.
  5. Choosing generic names too close to competitors (Pizza by Alfredo vs Alfredo's Pizza).
  6. Selecting long, tongue-twister names.
  7. Ignoring linguistic and cultural checks.
  8. Locking the domain before the name, leading to compromised brand names.
  9. Designing the logo before finalizing the name.
  10. Analysis paralysis (failing to make a choice).

🔗 Next Steps & Handoffs

<!-- BEGIN GENERATED: handoffs (generated from the ecosystem workflow map by build_ecosystems.py — do not edit by hand) -->

Ecosystem: @ecosystem-product — Product & Growth.

Workflows:

  • Product Launch Flow (product-launch, step 3 of 5): next → @geo-auditor (optional), @ugc-crafter (optional) (can run in parallel).
  • Naming & Positioning Flow (product-naming, step 1 of 2): next → @multi-brain-debate (optional).

Handoff contract: pass results to the next skill through an inline Handoff block in your reply with the fields skill, workflow, created_at, inputs, summary, and next (the handoff contract of @ecosystem-product). If a next skill is not installed, continue with its step from the ecosystem map, or install it with npx skills add fatih-developer/fth-skills --skill <name> after the user agrees.

<!-- END GENERATED: handoffs -->

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.