Update to Argovance Skill OS

{
  "description": "Create, evaluate, shortlist, research, or repair distinctive names for companies, brands, products, services, apps, software, features, projects, collections, characters, channels, communities, events, places, domains, or internal initiatives. Use when the user needs a strong name, rejects generic or AI-sounding suggestions, keeps receiving repetitive semantic variations, wants different naming directions, or needs candidates checked for meaning, pronunciation, cultural issues, current usage, domains, handles, search competition, or preliminary trademark risk.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 309
    },
    {
      "relative_path": "references/anti-generic-filter.md",
      "size_in_bytes": 2102
    },
    {
      "relative_path": "references/creation-methods.md",
      "size_in_bytes": 2846
    },
    {
      "relative_path": "references/evaluation-framework.md",
      "size_in_bytes": 2034
    },
    {
      "relative_path": "references/screening-protocol.md",
      "size_in_bytes": 2156
    }
  ],
  "name": "create-distinctive-names",
  "skill_md_contents": "---\nname: create-distinctive-names\ndescription: Create, evaluate, shortlist, research, or repair distinctive names for companies, brands, products, services, apps, software, features, projects, collections, characters, channels, communities, events, places, domains, or internal initiatives. Use when the user needs a strong name, rejects generic or AI-sounding suggestions, keeps receiving repetitive semantic variations, wants different naming directions, or needs candidates checked for meaning, pronunciation, cultural issues, current usage, domains, handles, search competition, or preliminary trademark risk.\n---\n\n# Distinctive Name Creator\n\nDevelop a name with its own identity rather than a polished synonym of the obvious category metaphor. Treat naming as a process of strategic definition, linguistic creation, elimination, and current-world screening.\n\n## Diagnose the naming problem\n\nEstablish:\n\n- what is being named and what it must enable;\n- audience, markets, languages, jurisdiction, and expected lifespan;\n- category, positioning, personality, price or status signal, and desired emotional residue;\n- parent brand, portfolio, naming architecture, and required descriptors;\n- practical constraints: length, spelling, pronunciation, domain, handles, app stores, packaging, voice use, or code identifiers;\n- names already tried, liked, rejected, or unavailable and the exact reason for each;\n- prohibited words, themes, sounds, suffixes, metaphors, associations, and competitors;\n- whether the name should be descriptive, suggestive, associative, arbitrary, coined, personal, geographic, historical, or another type.\n\nExtract a rejection ledger from the conversation and supplied materials. A rejected direction remains excluded unless the user explicitly reopens it.\n\n## Build a naming brief\n\nConvert the diagnosis into:\n\n- one-sentence naming objective;\n- three to six personality tensions, such as precise but not clinical;\n- mandatory qualities;\n- forbidden qualities;\n- semantic territories to explore;\n- saturated territories to avoid;\n- linguistic and practical constraints;\n- evaluation criteria and decision owner.\n\nDo not generate names until the brief explains why previous results felt generic.\n\n## Break semantic lock-in\n\nRead [creation-methods.md](references/creation-methods.md). Explore genuinely independent construction methods, not only synonyms within one metaphor.\n\nFor each round:\n\n1. Select at least four structurally different methods appropriate to the brief.\n2. Produce a broad private candidate pool.\n3. Remove obvious, weak, derivative, hard-to-use, or prohibited candidates before presenting anything.\n4. Apply the direction-distance test from [anti-generic-filter.md](references/anti-generic-filter.md).\n5. Present a small, high-quality set grouped by construction logic, not a dump of minor variations.\n\nIf one direction fails, do not offer its synonym family as a “new direction.” Move to a different source domain, word formation, cultural register, sound system, or naming type.\n\n## Avoid fake originality\n\n- Do not manufacture novelty by attaching fashionable fragments or replacing random vowels.\n- Do not use a classical-language root merely because it sounds premium.\n- Do not assume short, abstract, misspelled, or hard-to-pronounce means ownable.\n- Do not force the product function into the name.\n- Do not copy the phonetic skeleton, suffix, rhythm, or semantic promise of category leaders.\n- Do not recommend a candidate solely because a domain variant appears obtainable.\n- Do not retrofit an invented etymology. Mark coined meanings as brand-created associations.\n\n## Evaluate before recommending\n\nRead [evaluation-framework.md](references/evaluation-framework.md). Evaluate surviving candidates on strategic fit, distinctiveness, memorability, sound, spelling, pronunciation, meaning, stretch, category distance, cross-language risk, usability, and evidence-based availability.\n\nTest names in context:\n\n- spoken introduction and phone spelling;\n- web header, product sentence, and call to action;\n- portfolio extensions or edition names;\n- neutral sentence without explanatory mythology;\n- likely mishearings, misspellings, abbreviations, nicknames, and hostile readings.\n\nA name must work before its origin story is explained.\n\n## Research availability responsibly\n\nWhen availability, uniqueness, domains, handles, companies, products, search competition, app stores, or trademarks matter, browse current sources and record the date. Follow [screening-protocol.md](references/screening-protocol.md).\n\nSeparate:\n\n- exact confirmed conflict;\n- close relevant conflict;\n- unrelated use;\n- search or registry not checked;\n- apparently available at the moment checked;\n- requires professional legal clearance.\n\nNever state “available,” “safe,” “protectable,” or “trademark-free” from a general web search. Domain and social availability are volatile. A preliminary screen is not legal clearance.\n\nResearch a short list, not every raw idea, unless the user specifically requests exhaustive screening.\n\n## Iterate intelligently\n\nWhen the user rejects results:\n\n1. Ask or infer what property failed: sound, familiarity, meaning, status, category resemblance, artificiality, cultural tone, or availability.\n2. Update the rejection ledger and naming brief.\n3. Identify the generator's repeated mechanism.\n4. Exclude that mechanism in the next round.\n5. Change at least two creation dimensions before producing new candidates.\n\nDo not defend a rejected name or recycle it with a suffix.\n\n## Deliver\n\nLead with the strongest recommendation only when one clearly wins. Otherwise present a decision-ready shortlist containing:\n\n- name and pronunciation;\n- construction and honest meaning;\n- why it fits this specific brief;\n- what makes it non-generic;\n- strengths, weaknesses, and likely misreadings;\n- example use in context;\n- preliminary screening status with date and sources;\n- next validation step.\n\nAlso provide the updated rejection ledger and directions deliberately not pursued. Use `$build-brand-universe` when the name must be developed inside a broader positioning and identity system. Use `$control-deep-research` for extensive multi-jurisdiction screening.\n\nThis skill owns creation and screening of company, brand, product, service, project and other identity names. Route navigation labels, buttons, errors, settings, status text, microcopy and consistency of terminology inside an interface to `$review-interface-language-and-naming`; do not turn a UI-label review into a new brand-naming exercise.\n"
}