agentleFS
jhonatan-oliveiradevjhonatan-oliveiradev/agent-skills/skills/naming-brands-and-products/SKILL.md

naming-brands-and-products

Skill1 starsChanged 3 months agoMITView on GitHub

Use when a brand, product, service, feature, or program needs a name that must fit strategic positioning, language constraints, category context, and preliminary availability checks.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write a naming brief from the brand strategy: audience, offer, desired associations, personality, category frame, languages/markets, naming …

    line 12
  2. Distinctive:

    Run a linguistic screen. Read candidates aloud, test likely pronunciations and misspellings, inspect meanings and unintended associations …

    line 16
  3. Distinctive:

    Test names in realistic context: spoken introduction, URL/search result, product UI, endorsement line, sub-brand extension, and support …

    line 17
  4. Distinctive:

    Run preliminary availability checks for obvious conflicts.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Naming Brands and Products

Core principle

Naming is strategic selection under constraints, not a contest for the cleverest word. Generate broadly, evaluate consistently, and separate creative preference from linguistic, operational, and legal risk.

Naming workflow

  1. Write a naming brief from the brand strategy: audience, offer, desired associations, personality, category frame, languages/markets, naming architecture, and hard constraints.
  2. Define evaluation criteria before generating candidates. Typical criteria include strategic fit, distinctiveness, memorability, pronunciation, spelling, extension potential, and avoidable negative associations.
  3. Build several naming territories instead of one word list. Territories may use descriptive, suggestive, metaphorical, invented, founder/place, compound, or other structures when they fit the brief.
  4. Generate breadth inside each territory. Do not evaluate every idea while generating; premature filtering collapses diversity.
  5. Run a linguistic screen. Read candidates aloud, test likely pronunciations and misspellings, inspect meanings and unintended associations in relevant languages, and flag confusing similarity to category terms or competitors.
  6. Test names in realistic context: spoken introduction, URL/search result, product UI, endorsement line, sub-brand extension, and support conversation.
  7. Run preliminary availability checks for obvious conflicts. Search target markets and relevant goods/services using authoritative trademark databases where available. Treat domains and social handles as operational signals, not proof of trademark availability.
  8. Score the shortlist against the criteria and document trade-offs. Prefer a small set of candidates with clear rationale over dozens of unranked options.
  9. Escalate legal clearance when the name will carry material commercial value. A naming exercise or database search is not legal advice and cannot guarantee registrability or freedom to use.

Red flags

Reject or downgrade a candidate when it:

  • needs a long explanation before it makes sense;
  • is only distinctive through unusual spelling that harms recall or pronunciation;
  • creates a misleading category or product promise;
  • has obvious conflicts in a target market;
  • works only in a design mockup but fails when spoken or typed;
  • blocks likely future extensions without a strategic reason.

Verification

For each finalist, record the territory, strategic rationale, pronunciation, likely spelling errors, linguistic concerns, preliminary trademark-search notes, digital-operational notes, and unresolved risks. The shortlist should make the remaining decision explicit rather than hide uncertainty.

References

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.