agentsclimarketplace

Brand naming

Skill SkillMedev/brand-visual-identity/skills/brand-naming

Six skills for building brands that look intentional from day one.

Install
npx -y skills add SkillMedev/brand-visual-identity --skill brand-naming

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Generates twenty-plus brand or product name candidates across five naming archetypes, scores them against weighted criteria without averaging, and runs linguistic and memorability safety checks. Use when someone asks "help me name my startup", "is this a good product name", "generate name ideas for this feature", or is auditing an existing name for distinctiveness, strategic fit, and risk. Not a substitute for professional trademark clearance. Do NOT use for crafting the positioning the name must express - use positioning-statement instead; for briefing the visual identity around a chosen name, use logo-brief-writer.

SKILL.md

6.8 KB, as published. Nobody here has run it

Brand Naming

Naming is a strategic decision with long-term consequences: a name shapes perception, affects trademark viability, influences SEO, and is one of the hardest things to change once established. The costly failure is falling in love with the first clever candidate, then discovering after the logo, domain, and launch that it is unavailable, unpronounceable in a key market, or means something unfortunate in Portuguese.

Operating procedure

The order is deliberate: criteria before generation prevents post-hoc rationalization, and volume before evaluation prevents premature convergence.

Step 1: Gather inputs

  • What is being named: company, product, or feature. The stakes and criteria weights differ.
  • Category and the competitors' names - distinctiveness is only measurable against the actual field.
  • Primary target language plus the top 3 secondary language markets.
  • Constraints: domain budget, must it work as a verb, must it fit an existing naming system.
  • Criteria weights (next step). Label any assumed weight as an assumption.

Step 2: Establish naming criteria first

Define the criteria every candidate will be scored against before generating a single name. Standard set: Distinctive (stands out in the category), Memorable (recalled after one exposure), Pronounceable (works in the primary language without coaching), Meaningful (suggests something relevant without over-explaining), Available (trademark and domain likely obtainable), Scalable (survives the company or product evolving). Weight by project priority - a startup weights availability highest; an established brand extension usually weights distinctiveness first.

Step 3: Generate across at least five archetypes

Explore at least five archetypes to avoid fixating on one direction: Descriptive (describes the function: Zoom, Slack), Invented (coined words with no prior meaning: Kodak, Xero), Evocative (suggests a feeling or idea: Amazon, Stripe), People names (founder or character: Dyson, Patagonia), Alphanumeric (letters and numbers: G2, M1). Generate at least 20 candidates before evaluating any - premature evaluation kills creative range.

Step 4: Score candidates, never average

Score each candidate 1-3 per criterion. Do not collapse into a single average - the breakdown matters: a 3/3/3/3/1/3 (low only on availability) is a completely different decision than a 2/2/2/2/3/2 (mediocre across the board). Surface the top 5 with score breakdowns and a one-line rationale per criterion.

Step 5: Run the linguistic and cultural safety check

For every serious candidate: unintended meanings in the top 3 secondary language markets; phonetic associations (what does it sound like?); visual ambiguity (how does it read in all-caps and all-lowercase?); and a basic web search for existing uses. This is a screen, not clearance - state plainly that trademark clearance by a legal professional is required before finalizing any name.

Step 6: Test memorability and pronunciation

Speak each candidate aloud three times. Use it in natural sentences: "Have you heard of [Name]?" and "I work at [Name]." Names that feel awkward in speech rarely recover. Then run the recall test: read the shortlist to someone, wait 10 minutes, and ask them to repeat the names they remember. The survivors are the ones worth investing in.

Step 7: Present finalists in context

Never present names as a bare list. Show each finalist in a sentence, as a URL, as a social handle, and in a simple logotype lockup even in a neutral typeface. Context reveals what a spreadsheet hides - a name that scores well can look odd as a URL or feel weak at display size.

Worked example

NAME SCORING - project management tool for construction crews
Weights: Available 3x (startup), Distinctive 2x, others 1x. Scale 1-3.

Candidate   Archetype    Dist Mem Pron Mean Avail Scale  Note
Crewline    Evocative     2    3   3    3    2     3    .com taken; .io open
Fathom      Evocative     3    3   3    2    1     3    crowded trademark class
Struktiv    Invented      3    2   2    2    3     3    spelling needs coaching
Sitewise    Descriptive   1    2   3    3    1     2    generic; existing uses
Beacon Ops  Descriptive   2    2   3    3    2     2    handle available

Reading: Fathom has the best raw profile but scores 1 on the highest-weighted
criterion - that is a walk-away, not a compromise. Shortlist to context
testing: Crewline, Struktiv. Struktiv's pronounceability risk goes to the
spoken-aloud and 10-minute recall tests before any further investment.

Deliverable

Produce a naming report containing: the weighted criteria, the full candidate list grouped by archetype (20 minimum), the scoring table for the top 5 with per-criterion rationale, linguistic and cultural safety findings, a shortlist of 2-3 finalists shown in context (sentence, URL, handle, lockup), and the explicit trademark-clearance next step.

Do NOT

  • Do not average scores into one number; the breakdown is the decision.
  • Do not evaluate before 20 candidates exist - early judging collapses the search into one archetype.
  • Do not present names in a bare list; a name is never encountered in isolation in the real world.
  • Do not treat a web search as trademark clearance; the search screens out obvious conflicts, nothing more.
  • Do not advance a name that dies in spoken sentences, however good it looks written.
  • Do not let the loudest stakeholder's favorite skip the scoring - every candidate goes through the same table.

Quality bar

  • Criteria and weights were fixed before generation, not fitted to a favorite afterward.
  • At least five archetypes are represented in the candidate list.
  • Every top-5 score has a stated rationale; no unexplained numbers.
  • Every finalist passed the spoken-aloud test and appears in context mockups.
  • The report states the trademark-clearance requirement explicitly.

Escalation

This process is not legal advice. Require professional trademark search and clearance before finalizing any name or spending on identity. For the strategy the name must express, use positioning-statement; for briefing the visual identity, use logo-brief-writer; for documenting the finished identity, use brand-guidelines.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.