brand-domain-research
Skill19 starsChanged 20 days agoMITView on GitHub
Brainstorm brand, product, or project names, suggest matching domain names, and check domain registration records. Trigger when the user asks for naming ideas, domain suggestions, a domain availability check, or a combination.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- performance-aware-codingSkill
- review-and-refineSkill
- untangle-codebaseSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill for naming and domain discovery.
- Distinctive: line 14
When checking availability, verify the shortlisted domains before presenting them as likely unregistered.
- Distinctive: line 15
Search exact candidate names on the web when the user asks to vet them or when an obvious existing-brand collision could mislead the …
- Very specific: line 21
When shell access and curl are available, make one request per shortlisted domain, following redirects and setting a short timeout:
≈ “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.
Files
Brand and domain research
Use this skill for naming and domain discovery. Reuse the product brief and preferences already in the conversation. Ask one concise question only when a missing constraint would materially change the candidates; otherwise state a reasonable assumption and proceed.
Naming and domain suggestions
- Generate a focused shortlist of names that fits the product, audience, tone, and market. Add a brief reason for each candidate.
- Suggest matching domains only when requested or when the user asks for names and available domains together. Respect their preferred TLDs; otherwise choose a small set of sensible options rather than listing many extensions.
- When checking availability, verify the shortlisted domains before presenting them as likely unregistered. If the user asked only to brainstorm, mark domain status as unchecked.
- Search exact candidate names on the web when the user asks to vet them or when an obvious existing-brand collision could mislead the shortlist. Report visible conflicts, but do not claim this is legal or trademark clearance.
RDAP lookup
Use RDAP for a read-only registration-record check. Normalize each candidate to a bare domain hostname: remove any scheme, path, query, or fragment, lowercase it, and convert internationalized names to their ASCII IDNA form for the request while preserving the user's spelling in the answer. Reject malformed hostnames. Never place unvalidated user text into shell syntax.
When shell access and curl are available, make one request per shortlisted domain, following redirects and setting a short timeout:
curl -sS -L --max-time 15 \
-w '\nHTTP %{http_code}\n' \
"https://rdap.org/domain/${domain}"Interpret the HTTP status together with the JSON body:
- HTTP 200 with
objectClassName: "domain"means RDAP returned a registration record. - HTTP 404 with a not-found/no-data response means no registration record was returned and the name is likely unregistered. It does not prove that a registrar will let the user register it or what it will cost; names can be reserved or premium-priced.
- Timeouts, rate limits, malformed responses, and other errors are inconclusive. Do not call those domains available.
If shell access is unavailable, use the public RDAP lookup URL in a browser when available. Check only the candidate shortlist; do not bulk-scan names. Include the lookup date and label results as RDAP checks, not guaranteed purchase availability. Recommend a registrar lookup before the user acts on a promising name.
Output
For a naming request, return a concise table with the candidate name, matching domain, RDAP status when checked, and a short rationale. Separate verified lookup results from unchecked ideas. Do not register, purchase, or submit a domain checkout.
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
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.

