Product Naming

Research, evaluate, and validate product/startup/app names with domain, social media, and trademark checks.

Workflow

detect entry --> research --> present --> validate* --> report

Two phases with implicit transition: the agent presents research results and the user decides whether to proceed to validation.

Context Loading Strategy

Load references based on the detected entry point:

• User needs suggestions: load research.md first, then validation.md after user approval

• User has candidates for quality review: load research.md only (scoring section)

• User wants availability checks: load validation.md only

The tld-guide.md is always loaded as part of the validation phase.

Triggers

Trigger Pattern Entry Point References

Suggest names, find a name, name ideas, what should I call Phase 1 (research + generation) --> Phase 2 (validation) research.md + validation.md

Evaluate these names (quality focus) Phase 1 only (scoring, no generation) research.md

Check availability, domain available, check this name Phase 2 only (domains, socials, trademark) validation.md

Notes:

• "Evaluate" is flexible -- it can enter Phase 1 or Phase 2 depending on context. Quality evaluation enters Phase 1; availability check enters Phase 2.

• tld-guide.md is not a direct trigger. It is loaded by validation.md during domain checks.

Cross-References

brainstorming --> product-naming (direction feeds name generation context) product-naming --> docs-writer (validated name feeds into PRD/Brief) product-naming --> design-builder (chosen name informs brand/logo direction)

Guidelines

DO:

• Check domain availability for every name candidate

• Check .com and .com.br for every name (universal requirement); add .io and .app for tech/mobile products

• Add extra TLDs based on product type (see tld-guide.md)

• Bias invented names toward PT+EN bilingual phonetics

• Flag the strongest option as TOP PICK when one clearly stands out

• Present eliminated names with clear reasons

• Run competitor analysis before generating names

• Suggest name variations for top candidates

DON'T:

• Skip domain checks -- availability is critical for final decisions

• Eliminate names solely on domain unavailability (note as caveat instead)

• Use emojis outside of status indicators (availability uses traffic light emojis only)

• Generate more than 20 candidates (keep focused)

Output

Reports are saved as .md files in .artifacts/docs/ (create the directory if needed):

• Research flow: .artifacts/docs/{product}-research.md -- uses templates/research-report.md

• Validation flow: .artifacts/docs/{product}-validation.md -- uses templates/validation-report.md

Status indicators: 🟢 disponivel 🔴 indisponivel 🟡 incerto

Error Handling

• No product context provided: ask what the product does and who it's for

• Too many candidates (10+): batch availability checks for efficiency

• Domain check uncertain: mark as 🟡 and note it

• Rate-limiting: add delays between requests

• No tools available: mark all availability as 🟡 Uncertain

• All candidates eliminated: suggest the user adjust constraints or generate a new batch

• Trademark search returns no results: mark as 🟡 and recommend manual verification