Product naming
Skill sebastian-software/skills.sebastian-software.com/skills/product-naming
Research, generate, screen, and shortlist names for products, software, services, companies, features, and internal initiatives. Use for naming or renaming work, multilingual name checks, spoken-name and spelling tests, domain and search-conflict research, preliminary trademark screening, naming scorecards, candidate shortlists, or a documented naming decision. Especially useful when a name must work across German and English or several European languages without sounding like a generic technology brand.From its SKILL.md
npx -y skills add sebastian-software/skills.sebastian-software.com --skill product-namingAssembled 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.
SKILL.md
5.1 KB, 917 tokens by cl100k_base, as published. Nobody here has run it
Product Naming
Create names from a clear product strategy, then test them as real identifiers. Keep creative generation separate from evidence-backed screening so attractive ideas do not receive invented domain, linguistic, or legal certainty.
Workflow
- Build the naming brief before generating candidates:
- product, audience, problem, promise, category, and alternatives
- desired character and associations
- geographic and language scope
- spoken, written, search, domain, and app-store contexts
- legal entity, product, or feature name
- hard constraints, exclusions, and decision owner
- If the product thesis or target user is unresolved, route that decision to
product-management; naming cannot repair unclear positioning. - Choose two to four relevant name territories. Load Name generation for territories, sound, form, and anti-patterns.
- Generate a deliberately broad longlist without making availability claims. Include different structures and explain the intended association in one sentence each.
- Apply the fast filter: relevance, distinctiveness, pronunciation, spelling, memorability, unwanted meaning, category confusion, and team constraints.
- Research only the surviving candidates. Load Screening and verification for current domain, search, language, trademark, and handle checks.
- Score evidence transparently and retain three to six finalists. State unknowns and required professional clearance.
- Test finalists with representative speakers in realistic situations: hearing the name once, spelling it, recalling it later, searching for it, and using it in a sentence.
- Recommend a top choice plus a credible fallback after the spoken-name test.
- Record the decision, rejected alternatives, verification date, reservation
actions, and conditions that would reopen the choice with
decision-recordswhen the repository uses ADRs or another durable decision convention.
Operating Rules
- Prefer a distinctive, human-feeling name over a generic stack of category terms, technology abbreviations, or fashionable suffixes.
- Treat pronunciation and spelling after hearing the name as hard product requirements when word of mouth, sales calls, podcasts, or international use matter.
- Check the actual language set. Do not claim “works globally” from English-only intuition or an AI-generated translation.
- Keep cultural origin and intended meaning honest. Do not fabricate etymology for an invented word.
- Separate registrability, availability, and desirability. A free domain does not make a name safe or strategically strong; a parked domain does not prove the corresponding trademark is unavailable.
- Never report domain, handle, company, product, or trademark status without a current check and dated source. Search-result snippets alone are insufficient.
- Describe trademark research as preliminary screening, not legal clearance. Recommend qualified counsel before commercial commitment when the stakes warrant it.
- Do not purchase domains, reserve handles, file marks, or contact owners unless the user explicitly authorizes that external action.
Default Deliverable
For a full naming assignment, return:
- Naming brief and unresolved questions
- Name territories and rationale
- Shortlist table with pronunciation, meaning, fit, risks, and evidence status
- Current domain, usage, language, and preliminary trademark findings
- Ranked recommendation with tradeoffs, not a winner by score alone
- Spoken-name test and representative-user validation plan
- Legal, registration, and reservation next steps
Routing Boundaries
- Use
product-managementto resolve audience, product thesis, differentiation, or portfolio architecture before naming. - Use
consultant-profilewhen naming is part of an individual consultant's positioning rather than a product or business identity. - Hand post-selection messaging and launch work to a product marketing specialist; use a brand specialist only when one is available.
- Use
web-legal-compliancefor website disclosures and jurisdiction-specific launch requirements; it does not replace trademark counsel. - Use
originality-reviewwhen a produced identity or campaign must be compared with supplied visual and verbal references. Keep trademark similarity and clearance with this skill's preliminary screening and qualified counsel. - Use
decision-recordsto preserve a durable naming choice, the rejected alternatives, and conditions that would reopen it.
What ships with it: 5 files
14.6 KB alongside SKILL.md
agents/
- openai.yaml210 B
evals/
- evals.json3.2 KB
references/
- name-generation.md3.1 KB
- screening-and-verification.md4.4 KB
- README.md3.7 KB
Gives 0 of the 12 instructions most product growth skills give in 917 tokens
Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-07
- Read product marketing context before asking questionsin 24 of 728, across 18 files
- Define the ideal customer profilein 21 of 728, across 3 files
- Document a rollback plan before deploymentin 21 of 728, across 12 files
- Analyze the codebase to understand the productin 19 of 728, across 1 file
- Ask clarifying questions about the value propositionin 19 of 728, across 1 file
- Search for companies matching the criteriain 19 of 728, across 1 file
- Look for signals of immediate needin 19 of 728, across 1 file
- Assign a fit score from one to tenin 19 of 728, across 1 file
- Identify the target decision-maker rolein 19 of 728, across 1 file
- Suggest a personalized contact strategyin 19 of 728, across 1 file
- Provide conversation starters for outreachin 19 of 728, across 1 file
- Format results in a scannable markdown templatein 19 of 728, across 1 file
Said here and by no other author read
- build the naming brief before generating candidates
- choose two to four relevant name territories
- generate a broad longlist without availability claims
- apply the fast filter to longlist candidates
- research only the surviving candidates
- score evidence and retain three to six finalists
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.