agentleFS
micoozmicooz/skills/skills/product-naming/SKILL.md

product-naming

Skill12 starsChanged 7 months agoMITView on GitHub

Product naming and domain research workflow for proposing creative English/Chinese product names, explaining naming metaphors, and checking matching domain availability and price signals. Use when the user asks to name or rename a product/project/company/tool and wants domain checks such as .com, .design, .art, registration status, premium/price caveats, or a concise shortlist rather than broad brainstorming.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. yunshu0909/yunshu_skillshub★ 760same name
    2. grahac/claude_skills★ 2same name
    3. shreyas-makes/agent-skills★ 2same name
    4. julianosirtori/skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

Show its rules and text

We split this skill into the rules it gives an agent

19 rules. About 0 are common, 14 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈14

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the closest product docs, package metadata, landing copy, README, or user-provided description.

    line 11
  2. Distinctive:

    If local docs are placeholder text, say so and infer only from real code/package surfaces.

    line 12
  3. Distinctive:

    Prefer single-word names or single-word-feeling coined names when the user asks for names that do not feel like combinations.

    line 16
  4. Distinctive:

    Use direct category words only when they remain brandable.

    line 17
  5. Distinctive:

    Keep each lane small: real words, metaphor words, coined words, and native-language names.

    line 18
  6. Distinctive:

    Check domains before final ranking.

    line 25
  7. Very specific:

    Read references/domain-query.md when domain availability or pricing is requested.

    line 26
  8. Very specific:

    Check the exact word across the requested TLDs, usually .com, .design, and .art.

    line 27
  9. Very specific:

    Treat RDAP 404/not-found as "likely available", and a domain object as registered.

    line 28
  10. Distinctive:

    If a domain query fails because of sandbox networking, request the needed network approval instead of guessing.

    line 29
  11. Distinctive:

    Keep price claims honest.

    line 31
  12. Very specific:

    Use Tencent Cloud CheckDomain only when valid credentials/signing are available or the user provides a working query path.

    line 32
  13. Distinctive:

    If Tencent Cloud cannot be called, label public registrar pricing as a non-premium reference, include the source/date, and do not present …

    line 33
  14. Distinctive:

    Put the best candidates first, not every generated name.

    line 37
  15. Distinctive:

    Use a compact table for the shortlist:

    line 44
  16. Distinctive:

    Do not invent availability, registrars, registration dates, or prices.

    line 58
  17. Distinctive:

    Do not equate RDAP availability with final checkout availability.

    line 59
  18. Very specific:

    Do not bury unavailable .com results.

    line 60
  19. Distinctive:

    Do not do trademark clearance unless the user asks.

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Product Naming

Workflow

  1. Ground the product in one sentence before naming.
    • Read the closest product docs, package metadata, landing copy, README, or user-provided description.
    • If local docs are placeholder text, say so and infer only from real code/package surfaces.
    • Capture the product's core action, audience, and strongest metaphor.
  2. Generate names in focused lanes.
    • Prefer single-word names or single-word-feeling coined names when the user asks for names that do not feel like combinations.
    • Use direct category words only when they remain brandable. Avoid overusing obvious category words unless the user explicitly wants them.
    • Keep each lane small: real words, metaphor words, coined words, and native-language names. Do not spray dozens of weak variants before checking availability.
  3. Explain the naming logic.
    • For each serious candidate, give the Chinese name direction and the implied product story.
    • Favor names whose metaphor can stretch with the product beyond the current feature set.
    • Reject candidates that are hard to pronounce, too generic to defend, misleading for the product, or mainly clever because of spelling.
  4. Check domains before final ranking.
    • Read references/domain-query.md when domain availability or pricing is requested.
    • Check the exact word across the requested TLDs, usually .com, .design, and .art.
    • Treat RDAP 404/not-found as "likely available", and a domain object as registered.
    • If a domain query fails because of sandbox networking, request the needed network approval instead of guessing.
  5. Keep price claims honest.
    • Use Tencent Cloud CheckDomain only when valid credentials/signing are available or the user provides a working query path. Its Price, RealPrice, Premium, and renewal fields are the precise source for Tencent Cloud purchase decisions.
    • If Tencent Cloud cannot be called, label public registrar pricing as a non-premium reference, include the source/date, and do not present it as the exact checkout price.
    • Mention that premium names can be much more expensive than TLD baseline pricing.
  6. Report a ranked shortlist.
    • Put the best candidates first, not every generated name.
    • Include: English name, Chinese direction, rationale, .com/.design/.art status, and price caveat.
    • Separate "recommended" from "also viable" when many domains are unavailable.
    • End with a practical recommendation such as "best if you accept .design" or "needs another coined-name pass if .com is mandatory."

Output Shape

Use a compact table for the shortlist:

Name中文方向Why it fitsDomains
Candidate中文方向Short metaphor tied to the product's core action.candidate.com registered; candidate.design likely available; candidate.art likely available

Then add a short note for pricing:

  • Exact Tencent Cloud price: only if CheckDomain returned Price/RealPrice.
  • Reference registrar price: only if copied from a public pricing page, with source and caveat.
  • Unknown: if no reliable pricing source was queried.

Guardrails

  • Do not invent availability, registrars, registration dates, or prices.
  • Do not equate RDAP availability with final checkout availability; call it "likely available" unless a registrar purchase API confirms it.
  • Do not bury unavailable .com results. If .com is taken, say so plainly.
  • Do not do trademark clearance unless the user asks; if the name will be used commercially, recommend a trademark search as separate legal diligence.

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.