business-naming
Generate, refine, compare and, when needed, screen distinctive names for startups, products, apps, developer tools, open-source projects, product families…
Skill by Tam Nguyen
Chalk Labs
Need help deploying business-naming?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/amahony-business-naming
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, legal
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/business-naming
What's inside
- Skill name
business-naming- Description
- Generate, refine, compare and, when needed, screen distinctive names for startups, products, apps, developer tools, open-source projects, product families, local businesses, services, companies and nonprofits. Use when asked to name or rename a business, brand, product, shop, studio or organization; derive a name from an existing project; build a company and product naming system; compare candidates; or check for conflicting companies, domains, packages, marketplaces or trademarks. Defaults to a fast creative pass; screens only a shortlist, and only on request or for a final choice. Never claims legal clearance or presents unverified availability as fact.
- License
- MIT
- Compatibility
- The creative modes need no tools. Validation needs web search; domain availability is confirmed by the user in their registrar.
- Metadata
- author: Tam Nguyen · source: https://github.com/tamdogood/builder-essential-skills/tree/main/skills/name-your-business · version: 1.0.0 · category: Writing
- Instructions
- 104 lines in SKILL.md · view on GitHub
Files (4)
- LICENSE
- SKILL.md
- clearance.md · references/
- naming-strategy.md · references/
SKILL.md (first lines)
# Business naming Get the person to useful names quickly, then deepen the work only when the decision warrants it. Be imaginative in generation, severe in selection, and plain about evidence and trade-offs. ## Operating rules - Choose the least expensive mode that satisfies the request. - Diagnose the audience, position, category and growth horizon before generating. Adapt the method to the business: a neighbourhood clinic, a developer tool, a nonprofit and a holding company should not sound as though one generator named them. - Give a clear top choice at the confidence the mode supports. In creative-only work, call it the **creative favourite**; reserve a final recommendation for validated work. - Keep creativity and validation apart. Do not let an open domain rescue a weak name, or let registry searches narrow the ideas before good candidates exist. - Never invent a story for a name after the fact. Meanings, roots, puns and links to a source name must be defensible; label interpretation as interpretation. - Never say a name is legally cleared or a trademark is available. Report preliminary findings and recommend trademark counsel before significant investment. - For open-source or source-inspired names, keep code-licence permission separate from trademark and naming permission. Never imply an official relationship without evidence. - Do not buy a domain, file a trademark, reserve a handle, contact anyone or announce a name without explicit permission. - Show a curated shortlist, not pages of discarded names. ## Choose the mode **Fast naming (default).** For brainstorming, exploration, refinement or comparison when nobody asked about availability. Work from the description and the chat; do not search unless a referenced source must be understood. Generate at least 15 varied candidates privately, filter hard, and present about five. Say once that the shortlist is creative-only and unverified, and offer to screen the person's favourite three. **Source-inspired naming.** When the person supplies an existing name, product, project or brand as inspiration. Look at only as much of the source as you need. Identify its mechanism (meaning, sound, pun, acronym, metaphor, spelling, behaviour, origin story or domain relationship) and carry the mechanism or spirit forward instead of adding a fashionable suffix. Distinguish an authorized extension of the source brand from an independent successor. Add validation when conflicts, availability or a final choice come up. **Validation.** When the person asks to search, verify, check availability, investigate conflicts or choose a final name. A final choice needs validation even if they only say "pick the winner". Screen only three to five names, check only the surfaces that matter for this business, and treat every result as preliminary screening. If web search is not available this turn, return a provisional creative shortlist, mark every current-status claim **not verified**, and give no final recommendation. ## Workflow ### 1. Frame the naming problem Capture or reasonably infer: what the business does in one sentence; who buys, uses or refers it; the differentiator and the response it should get; brand posture (technical, premium, playful, trustworthy, warm, restrained and so on); category and likely expansion over three to five years; what is being named (company, master brand, product, service, location, protocol, package, product family or parent brand); launch markets, languages, pronunciation constraints, required or forbidden words, domain preferences and budget; and whether a source name is a parent, an inspiration or only a comparison. Ask at most one short question when the answer would change the candidates substantially. Otherwise state an assumption and proceed. Read `references/naming-strategy.md` with skill_read, and follow its guidance for the business type and name architecture. ### 2. Set the strategy Work out privately: the **position** (what the business should be known for); the **naming job** (orient, differentiate, signal, aid recall or stretch); the **audience response**; **brand character** as three traits and three anti-traits; the **stretch** the name may need later; the **architecture** of company, products, services and sub-brands; at least four distinct **creative territories**; and, in validation mode only, the **validation policy**: jurisdictions, relevant namespaces, exact-match domains, acceptable alternatives and budget. When validation is requested without a domain policy, default to the exact-name `.com` for a general commercial business. Use `.org` for a nonprofit or a country-code domain for a local market when it genuinely fits. Never quietly fall back to a modifier or novelty domain. ### 3. Understand a supplied source Only in source-inspired mode. Record the source name's likely mechanism and why it works, what the source owns legally or strategically, what is worth carrying forward, and what the new independent name must leave behind. ### 4. Generate broadly and filter hard Generate across several lenses rather than repeating one root: what the product does or changes for the customer; metaphor from a credible world; literal clarity; real words, compounds or compressed phrases; defensible coined forms; founder, place, provenance or material when authentic; technical wordplay for technical products; and a system that can cover the company, products and modules. Fast mode needs at least 15 candidates. Go to 40–60 only for a high-stakes engagement, when validation eliminates the first pool, or when the first territories are weak. If the person supplied candidates only for comparison, add new ones only when they bring a missing direction. Test promising names in natural phrases: "I use ___", "Welcome to ___", "___ helps us ___". For technical names, also test lowercase commands, package names, repository names and spoken handoffs. Reject candidates that are generic, imitative, trend-bound or close to a known player; hard to hear, say, spell, type or remember for the audience; dependent on a forced explanation; misleading, tied to a temporary feature or too narrow for the stretch; culturally careless, unintentionally comic or negative in a launch language; likely to imply an unauthorized relationship with another brand; or built by appending `AI`, `Labs`, `Cloud`, `Tech`, `ly` or another fashionable fragment to a generic word. Score survivors with the rubric and stress tests in the strategy reference. Domain and namespace availability are gates in validation mode, never points for strategic quality. ### 5. Validate only the serious shortlist Skip in fast mode. Read `references/clearance.md` before making any availability or conflict claim. For each of three to five candidates: 1. Search the exact name, close spellings and sound-alikes with the category, country and product nouns. 2. Check the surfaces that matter: active companies and products, live sites, GitHub, npm, PyPI, crates.io, app stores, marketplaces, social handles or industry directories. 3. Check proposed domains as the clearance reference describes. You cannot confirm that a domain can be registered; list the exact domains for the person to check in their registrar, and record their results when they share them. 4. Search official trademark databases when the person asks for trademark screening or is making a final decision, covering the relevant jurisdictions, goods or services, spellings and sound-alikes, without drawing a legal conclusion. 5. Check launch languages for slang, pronunciation and transliteration. Recommend a native-speaker review for a high-stakes international launch. 6. When the legal company name matters, check the relevant company register. Keep company, brand, trademark, package, handle and domain status separate. Put evidence beside each claim: exact strings, links, precise status language and the check time with timezone. When a generated name fails, refill from the strongest territory. When a name the person supplied fails, report the conflict plainly before offering replacements. Ask before relaxing a domain preference, adding a modifier, accepting a premium domain or changing another constraint. ### 6. Deliver the response for the mode **Fast or source-inspired:** 1. Lead with the **creative favourite** and one sentence on why it wins. 2. A table of about five leaders: `Name | Why it fits | Main weakness | Possible tagline`. 3. Five to eight runners-up only when they add genuinely different directions, grouped by style. 4. The best choice for each relevant strategy, such as clearest, most distinctive, closest to the source or strongest company brand. 5. State: **Creative shortlist only: current domains, trademarks, companies and namespaces were not checked.** Offer to screen the person's favourite three. Include no domain claims, no long method recap and no description of research that was not done. A tagline is a usage test, not an excuse for a name that cannot stand alone. **Validated recommendation:** 1. **Verdict:** recommended name, pronunciation, one-sentence rationale and why it beats the field. 2. **Strategic story:** territory, defensible meaning, emotional signal and room to grow. 3. **In use:** three natural spoken, written or technical examples. 4. **Domain evidence:** exact domain and its status; registrar, price and check time when the person confirmed it, otherwise **not verified**. 5. **Preliminary screening:** relevant company, product, package, marketplace, trademark, language and affiliation findings, with limitations. 6. **Finalist scorecard:** the winner plus two to four ranked alternatives with scores, exact domains and trade-offs. 7. **What lost:** important rejected routes and why. 8. **Next actions:** register promptly, keep the evidence, commission legal clearance, check languages where needed, then build the verbal and visual identity. Use "verified available at check time" only for a domain that passed the registrar gate. End with the warning that availability changes and a domain is not secured until registration completes. Save a naming report only when the person asks for a file. ## Failure handling - Fast mode needs no research. Never describe its lack of research as a tool failure; keep its claims creative-only. - If a referenced source cannot be opened, use the description given, say what context is missing, and ask for it only if the naming mechanism cannot be understood otherwise. - If a package, marketplace or handle lookup is unavailable, mark only that surface **not verified**. - If a domain is premium, reserved, brokered or ambiguously priced, say so and exclude it unless it fits the budget and the person accepts the trade-off. - If the trademark jurisdiction is unknown, state the limited scope and ask before calling the shortlist launch-ready. - If every strong candidate fails validation, keep the strategy and run a new round. Never rescue weak names because their domains are open.
From amahony/agent-templates, MIT.
More from amahony/agent-templates
- 0.570score
paper-opportunity-radar
Tam Nguyen
Run a cumulative daily or one-off sweep of research papers on a chosen topic, audit their claims, methods, integrity signals and independent support, then…
SkillAFreshness: AClaude Code +9 - 0.570score
blog-post-writing
Tam Nguyen
Write a blog post that reads like a person wrote it and earns search traffic.
SkillAFreshness: AClaude Code +9 - 0.570score
design-system-planning
Jeremy Kaye
Set a product's visual design language and screen contracts after the product plan and before phase planning.
SkillAFreshness: AClaude Code +9 - 0.570score
mastery-plan
Tam Nguyen
Build an evidence-based path toward exceptional capability in a field or skill, and coach the learner along it.
SkillAFreshness: AClaude Code +9 - 0.570score
phase-planning
Jeremy Kaye
Create and maintain phase files, the plans that break work into phases, sprints and tasks with a status for every task.
SkillAFreshness: AClaude Code +9 - 0.565score
onboarding-guide
Omni
Walk a new team member through how the team works, one step at a time, using the onboarding checklist in this skill.
SkillAFreshness: AClaude Code +9 - 0.565score
decision-record
Omni
Write a decision record capturing context, options considered, and the chosen option.
SkillAFreshness: AClaude Code +9 - 0.565score
deep-explanation
Tam Nguyen
Explain any topic from first principles as a layered, causal explanation that fully answers the question.
SkillAFreshness: AClaude Code +9 - 0.565score
orwell-writing
Tam Nguyen
Use when an agent is asked to draft, rewrite, edit, review, polish, copyedit, simplify, humanize, or create written prose, including creative writing, essays…
SkillAFreshness: AClaude Code +9 - 0.565score
document-review
Omni
Review a draft document for clarity, structure, tone, and errors, and return prioritised feedback.
SkillAFreshness: AClaude Code +9 - 0.565score
job-description
Omni
Write a job description in house format from a hiring manager's notes.
SkillAFreshness: AClaude Code +9 - 0.565score
linkedin-post-writing
Omni
Write, improve or audit a LinkedIn post, or draft hook options, with a reader-first method built to grow followers.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 19, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0.0
- License
- MIT
- Repository
- github.com/amahony/agent-templates
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Tam Nguyen
- 0.570score
paper-opportunity-radar
Tam Nguyen
Run a cumulative daily or one-off sweep of research papers on a chosen topic, audit their claims, methods, integrity signals and independent support, then…
SkillAFreshness: AClaude Code +9 - 0.570score
blog-post-writing
Tam Nguyen
Write a blog post that reads like a person wrote it and earns search traffic.
SkillAFreshness: AClaude Code +9 - 0.570score
mastery-plan
Tam Nguyen
Build an evidence-based path toward exceptional capability in a field or skill, and coach the learner along it.
SkillAFreshness: AClaude Code +9 - 0.565score
deep-explanation
Tam Nguyen
Explain any topic from first principles as a layered, causal explanation that fully answers the question.
SkillAFreshness: AClaude Code +9 - 0.565score
market-validation
Tam Nguyen
Run an honest market-fit and viability audit of a project or idea and produce a decision document.
SkillAFreshness: AClaude Code +9 - 0.565score
orwell-writing
Tam Nguyen
Use when an agent is asked to draft, rewrite, edit, review, polish, copyedit, simplify, humanize, or create written prose, including creative writing, essays…
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get business-naming running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
business-naming skill. Agent Mart. https://agentmart.dev/skills/amahony-business-naming (last updated 2026-10-24)