name: brand-name-checker
description: Check product and brand names for conflicts across trademarks, domains, social handles, and package registries. Returns a risk level and Proceed/Modify/Abandon recommendation. Skip for name brainstorming, logo design, or trademark filings.
license: MIT
effort: max
metadata:
    version: 1.4.0
    author: "Luong NGUYEN <luongnv89@gmail.com>"

Brand Name Checker

Check product and brand names for conflicts across trademarks, domains, social media, and package registries (npm, PyPI, Homebrew, apt).

When to Use

Use this skill before adopting a product or brand name. To stay within the agent's context budget, lean sections (templates, examples) live in references/*.md and per-source workers live in agents/*.md — only the orchestrator instructions are inlined here.

Subagent Architecture

This skill uses parallel subagents to handle 13+ sequential web fetches across independent sources. Pattern: B (Parallel Workers) + D (Research+Synthesis).

Agents

Parallelization Strategy

• Early-Exit Rule: If social-checker finds an exact handle taken on any of the 6 platforms, skip steps 2-4 (Registry, Domain, Trademark) and jump straight to the synthesizer with an "Abandon" verdict. This is referenced elsewhere in this file simply as the Early-Exit Rule.
• Independent Workers: Registry, domain, trademark checkers run in parallel without dependencies
• Sequential Flow: Social → (if clear) → Parallel {Registry, Domain, Trademark} → Synthesizer

Speedup: ~4x faster than sequential approach (13+ web fetches parallelized into 2-3 waves).

Environment Check

Before executing:

1. Verify WebSearch and WebFetch tools are available
2. Confirm internet connectivity for external service queries
3. Check rate limits on social platforms and registries

Repo Sync Before Edits (mandatory)

Before creating/updating/deleting files in an existing repository, sync the current branch with remote. See references/repo-sync.md for the exact git fetch / git pull --rebase commands and stash recovery flow.

Input

Name to analyze provided in $ARGUMENTS. If empty, ask user for the name.

Optionally check for prd.md in project to understand product context.

Analysis Protocol

Early-Exit Rule applies (see Subagent Architecture above): an exact social handle taken on any of the 6 platforms skips Steps 2-4 straight to Step 6 (Recommendation) with an "Abandon" verdict.

Step 1: Social Media Check (First Priority)

Use WebSearch to check handles on:

• X/Twitter: "@[NAME]" site:twitter.com OR site:x.com
• Instagram: "@[NAME]" site:instagram.com
• GitHub: "[NAME]" site:github.com/[NAME]
• LinkedIn: "[NAME]" site:linkedin.com/company
• TikTok: "@[NAME]" site:tiktok.com
• Discord: "[NAME]" site:discord.com

If exact handle taken (Early-Exit Rule): Return NEGATIVE: Exact social handle taken (@platform) and STOP. Suggest different name.

Step 2: Package Registry Check (if Step 1 clear)

Package registries are first-come-first-served namespaces. Unlike GitHub (which allows duplicate project names), registries enforce unique names — once someone claims "your-name" on PyPI or npm, you cannot publish under that name. This makes registry checks urgent: if the name is taken on a registry you plan to publish to, you either need a different name or a naming variant (e.g., prefix/suffix).

Use WebFetch to check these registries directly:

For each registry, report:

• Available: 404 / not found — safe to claim
• Taken: Package exists — note the owner, description, and last publish date (a recently claimed but empty package could indicate namespace squatting)
• Similar: No exact match but close variants exist (e.g., name-js, py-name) — worth noting

If the name is taken on a registry the user plans to publish to, flag it prominently and suggest variants (e.g., name-cli, name-py, name-lib, prefixed with org scope like @org/name for npm).

Step 3: Domain Check (if Step 1 clear)

Use WebSearch to check:

• .com (highest priority)
• .io, .app, .co
• Regional: .eu, .fr

Search: site:[NAME].com and "[NAME].com" domain availability

Status:

• Available: No active site
• Parked: Domain exists but for-sale/parking
• Active: In use (flag if same industry)

Step 4: Trademark Check (if Step 1 clear)

Use WebSearch for trademark databases:

Focus on Nice Classes 9, 35, 42 (software/technology). Note if marks are live or expired.

Step 5: Risk Assessment

Step 6: Recommendation

• Proceed: Low risk - name is viable
• Modify: Moderate risk - suggest 1-2 variants addressing conflicts
• Abandon: High risk - suggest completely different alternatives

Output Format

SOCIAL: Clear | NEGATIVE: [reason]
REGISTRY: npm (status) | PyPI (status) | Homebrew (status) | apt (status)
DOMAIN: .com (status) | .io (status) | .app (status)
TM: WIPO (status) | EUIPO (status) | INPI (status)
RISK: [Low/Moderate/High] - [reason]
RECOMMEND: [Proceed/Modify/Abandon] (+ variants if needed)

PRD Integration

If prd.md found, add:

Name Fit Assessment:

• Alignment with product vision
• Memorability, pronunciation, spelling
• Target audience fit

Alternative Suggestions:

Step Completion Reports

After each major step, emit a status report. The general template, plus per-step examples (Social, Registry, Domain, Trademark, Risk, Recommendation), live in references/step-reports.md. Adapt check names to what the step actually validates; use √ for pass, × for fail.

Acceptance Criteria

• Social media check completed across all 6 platforms with clear available/taken status
• Package registry status confirmed for npm, PyPI, Homebrew, and apt (unless the Early-Exit Rule fired)
• Domain availability checked for .com and at least two alternative TLDs (unless the Early-Exit Rule fired)
• Trademark search completed against WIPO, EUIPO, and INPI (unless the Early-Exit Rule fired)
• Risk level assigned (Low / Moderate / High) with supporting rationale
• Final recommendation delivered (Proceed / Modify / Abandon) with named alternatives if needed

Expected Output

SOCIAL: Clear (Twitter, Instagram, GitHub, LinkedIn, TikTok, Discord all available)
REGISTRY: npm (available) | PyPI (TAKEN — owner: example-org, last publish: 2022-03) | Homebrew (available) | apt (available)
DOMAIN: .com (active — unrelated industry) | .io (available) | .app (available)
TM: WIPO (clear) | EUIPO (clear) | INPI (similar mark in class 42 — "Acme Tools SAS", filed 2021)
RISK: Moderate — PyPI name taken on a target registry; .com parked; minor trademark similarity in France
RECOMMEND: Modify — use "acme-cli" (npm/PyPI clear, .com available, no TM conflicts)

Edge Cases

• Exact social handle taken on any of the 6 platforms: Early-Exit Rule (see Subagent Architecture) — skip all remaining checks and return an Abandon recommendation with alternative name suggestions.
• Rate-limited registry API: Retry once after 5 seconds; if still blocked, mark the registry as "unchecked" and note it in the report — do not skip silently.
• Trademark database unavailable: Note the outage per database; downgrade risk only if all three TM sources are inaccessible (warn user).
• Name contains special characters or spaces: Normalize to slug form (e.g., my tool → my-tool) before all checks; report both the original and normalized forms.
• Very short names (1–3 characters): Flag high trademark collision risk upfront; abbreviations are almost always claimed across social and TM databases.
• Name already in use by a well-known brand (typosquat risk): Escalate to High risk even if all technical checks pass.

Final Action

• Proceed: Confirm safe to use, suggest registration order:

1. Package registries first — claim names on npm/PyPI/Homebrew immediately, even with a placeholder package. These are first-come-first-served and the most vulnerable to namespace squatting.
2. Domain — register the primary domain.
3. Social handles — secure handles on key platforms.

• Modify: Recommend best variant with explanation
• Abandon: Recommend best alternative from suggestions