Domain Name Brainstormer

# Create a "Domain Name Brainstormer" AI Skill

I want you to help me set up a reusable AI skill that I can use in future conversations. Read the complete skill definition below, then help me install it.

## Complete Skill Definition

# Domain Name Brainstormer

Generate and score candidate brand / domain names from seed words using common naming patterns. The script does not check live registration — it produces candidates fast so you can spend your time evaluating the best ones.

---

## Table of Contents

- [Keywords](#keywords)
- [Quick Start](#quick-start)
- [Core Workflows](#core-workflows)
- [Tools](#tools)
- [Reference Guides](#reference-guides)
- [Best Practices](#best-practices)

---

## Keywords

domain, domain name, naming, brand naming, product name, company name, .com, brainstorm, naming brainstorm, brand identity, naming strategy

---

## Quick Start

### Generate 200 Candidates in 30 Seconds

```bash
python scripts/name_generator.py "data,insight,signal" --count 200
```

Then:
1. Eliminate anything > 12 characters
2. Eliminate anything that's hard to spell after hearing it once
3. Eliminate anything that sounds like a competitor
4. Take the top 10-15 to a registrar (manually) to check availability across .com / .ai / .io / .co

---

## Core Workflows

### Workflow 1: Seed-Word Brainstorm

**Goal:** Convert a few keywords describing the product into 100+ ranked candidates.

**Steps:**
1. List 3-7 seed words that describe the product, value, or feeling
2. Run: `python scripts/name_generator.py "seed1,seed2,seed3" --count 200`
3. Sort the output by score (highest first)
4. Apply the elimination filter from `references/naming_framework.md`
5. Pick a shortlist of 10-15 to manually check for trademark and domain availability

**Expected Output:** Ranked list of candidates with scores, classified by pattern (vowel-drop, blend, prefix-suffix, TLD-as-suffix).

**Time Estimate:** 5-10 minutes.

### Workflow 2: Pattern-Specific Generation

**Goal:** Get more of one specific pattern (e.g., only blends, or only TLD-as-suffix names).

**Steps:**
1. Run with pattern filter: `python scripts/name_generator.py "fast,ship" --pattern blend --count 100`
2. Available patterns: `vowel_drop`, `prefix_suffix`, `blend`, `tld_suffix`, `repeat`, `all`
3. Iterate seeds until you have 20+ candidates worth taking to availability checks

**Expected Output:** Pattern-specific list.

**Time Estimate:** 5 minutes per pattern variation.

### Workflow 3: Trademark / Availability Pre-Check

**Goal:** Avoid wasting energy on names that are obviously taken.

**Steps:**
1. Take the shortlist from Workflow 1 or 2
2. **Manually** check each on:
   - A domain registrar (Namecheap, Cloudflare, Porkbun) for .com / .ai / .io / .co
   - The USPTO TESS database (or your jurisdiction's trademark office) for live trademarks in the relevant class
   - A regular Google search for existing usage
3. Drop anything with a live trademark in the same product class, an active product on a similar domain, or a trademarked .com that you do not own

> The script does **not** automate registrar lookups — those need real network calls and rate-limited APIs. Doing this step manually for a 10-name shortlist takes 10-15 minutes.

---

## Tools

### name_generator.py

Generates candidate names by applying naming patterns to seed words and scores each on length, pronounceability, and uniqueness.

```bash
# Default: 100 candidates, all patterns
python scripts/name_generator.py "data,signal,insight"

# More results
python scripts/name_generator.py "data,signal" --count 300

# One pattern only
python scripts/name_generator.py "data,signal" --pattern vowel_drop

# JSON for programmatic use
python scripts/name_generator.py "data,signal" --json
```

**Patterns implemented:**
- `vowel_drop` — Remove inner vowels: "data" → "dta", "insight" → "nsght"
- `prefix_suffix` — Add common naming prefixes/suffixes: "ly", "ify", "io", "lab", "labs", "hq", "co", "stack", "kit", "app"
- `blend` — Combine two seeds: "data" + "signal" → "dasignal", "datignal"
- `tld_suffix` — Treat TLD as part of the name: "send.fast" reads as "sendfast"
- `repeat` — Doubling pattern: "data" → "datadata"

**Score (0-100) factors:**
- Length 5-10 chars scores highest
- Pronounceability via consonant-vowel ratio
- Penalty for common-word collisions
- Penalty for hyphens or numbers (these dilute brand)

---

## Reference Guides

- **`references/naming_framework.md`** — Why names matter, the elimination filter, naming-pattern playbook, common pitfalls

---

## Best Practices

- **Don't pre-commit to .com.** A `.io` or `.ai` is fine for most B2B products in 2026; `.com` matters less than it did a decade ago.
- **Say it out loud.** If you can't tell someone the domain in a noisy bar and have them spell it correctly, drop it.
- **Avoid naming-collisions.** A "DataLoop" in your space and a "DataLoop" in adjacent SaaS will cause confusion forever.
- **Don't pick the first one.** Generate 200, filter to 30, shortlist 10, sit on the shortlist for 24 hours. The one that still feels right after sleeping is the one.
- **Trademark before launching.** A great name with a trademark conflict will cost you a rebrand later.

---

## Integration Points

- Pairs with `marketing/brand-strategist/` for brand-narrative work
- Pairs with `marketing/landing-page-generator/` for messaging once a name is chosen
- Used by `c-level-advisor/` workflows during company / product launches

---

## What I Need You to Do

First, detect which platform I'm using (Claude.ai, ChatGPT, etc.) and follow the matching instructions below.

### If I'm on Claude.ai:

Walk me through these exact steps:

1. **Create the Project:** Tell me to go to **claude.ai > Projects > Create project** and name it **"Domain Name Brainstormer"**

2. **Add Project Knowledge:** Give me the COMPLETE skill definition above as a single copyable text block inside a code fence. Tell me to click **"Add content" > "Add text content"** inside the project, then paste that entire block. Do NOT say "paste from above" -- give me the actual text to copy right there.

3. **Set Custom Instructions:** Tell me to open project settings and paste this exact instruction:
   "You are an expert Domain Name Brainstormer in the Personal Productivity domain. Use the project knowledge as your expertise. Follow the workflows, frameworks, and templates defined there. Always provide specific, actionable output."

4. **Test It:** Give me a specific sample prompt I can use inside the new project to verify it works. Pick a real task from the skill's workflows.

### If I'm on ChatGPT:

Walk me through these exact steps:

1. **Create a Custom GPT:** Tell me to go to **chatgpt.com > Explore GPTs > Create**
2. **Configure it:**
   - Name: **"Domain Name Brainstormer"**
   - Description: "Generate candidate brand and product names by combining seed words with prefixes, suffixes, vowel-drops, blends, and TLD variations, then score candidates for memorability, length, and pronounceability. Use when naming a new product, company, or feature, or when the user mentions domain names, brand naming, naming brainstorm, or finding an available .com."
   - Instructions: Give me the COMPLETE skill definition above as a single copyable text block inside a code fence to paste into the Instructions field. Do NOT say "paste from above."
3. **Test It:** Give me a sample prompt to verify it works.

### If I'm on another platform:
Ask which tool I'm using and adapt the instructions accordingly.

## Important
- Always provide the full skill text in a ready-to-copy code block -- never tell me to "scroll up" or "copy from above"
- Keep the setup steps simple and numbered
- After setup, test it with me using a real workflow from the skill

Source: https://github.com/borghei/Claude-Skills/tree/main/personal-productivity/domain-name-brainstormer/SKILL.md