business-naming
Skill1 starsChanged 9 months agoMITView on GitHub
Generate and evaluate names for companies, products, brands, and features using a structured three-phase process (Identify, Invent, Implement) based on David Placek's Lexicon Branding methodology. Use when a user asks to name a company, name a product, brainstorm brand names, evaluate a shortlist of names, rename something, build a creative brief for naming, or find a name for a startup, app, or service. Accepts a description of the business, product, or brand to be named.
In this repository8 other files it gives its agents.
- domain-name-generatorSkill
- java-code-reviewSkill
- learning-guide-creatorSkill
- openapi-reviewSkill
- saas-landing-themeSkill
- software-requirementsSkill
- stock-screenerSkill
- tariff-guideSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 14 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
If the user provides minimal context, ask targeted questions to fill gaps.
- Distinctive: line 46
Read references/diamond-exercise.md before this phase.
- Distinctive: line 72
Create a "metaphorical window" -- a short phrase that opens creative possibilities without locking in narrow objectives.
- Distinctive: line 91
Use the Diamond as the naming brief, not a generic mission statement.
- Distinctive: line 97
Read references/sound-symbolism.md and references/forced-synchronicity.md before this phase.
- Distinctive: line 117
Use as a lens for filtering, not a rigid rule.
- Distinctive: line 138
Use these as seeds so names don't sound like the category.
- Distinctive: line 156
Remove anything that sounds like the category.
- Distinctive: line 193
If the user is testing names with others, advise:
- Distinctive: line 195
Ask: "What does this name make you imagine about the product?" This tests predisposition to consider, not subjective preference.
- Distinctive: line 197
Do not ask "Do you like it?" -- this produces unreliable data.
- Distinctive: line 262
When evaluating existing names, apply the same framework: Does it connect to behavior?
- Distinctive: line 264
Treat polarization as signal, not noise.
- Distinctive: line 269
When uncertain about the business, market, or user intent, ask rather than assume.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Business Naming
Generate and evaluate names using a structured three-phase process: Identify (set the framework), Invent (generate and filter), Implement (test and select). Aim for names that are distinctive, grounded in behavior and experience, and that start a story.
Input Handling
Determine what the user needs and gather context accordingly:
- New name -- User describes a business, product, or brand that needs a name. Run all three phases.
- Shortlist evaluation -- User provides candidate names to evaluate. Skip to Phase 3 (Implement), but run a quick Phase 1 (Identify) to establish the framework for evaluation.
- Brief creation -- User wants a creative brief for naming. Run Phase 1 (Identify) and deliver the brief as the output.
- Rename -- Existing name needs replacing. Run all three phases, adding the current name and its problems to the landscape analysis.
If the user provides minimal context, ask targeted questions to fill gaps. At minimum you need: what is being named, who it serves, and what makes it different.
Naming Process
Execute these phases in order.
Phase 1: Identify -- Set the Framework
Focus on behavior and experience, not mission statements.
Read references/diamond-exercise.md before this phase.
1a. Analyze Behavior
Establish three perspectives:
- Current behavior -- How does the company/product behave today? How do users interact with it? What is the experience?
- Desired behavior -- How should it behave? What experience should users have?
- Market response -- How does the market currently perceive the category? What language and expectations exist?
1b. Map the Landscape
Study the competitive naming landscape:
- List competitor names and the language patterns they use (e.g., real estate: Home, Find, Key, Nest, Roof, Door).
- Identify the cliches and overused words in the category.
- Define what the name must not sound like. A name that blends in with competitors is "a form of suicide."
1c. Creative Framework
Create a "metaphorical window" -- a short phrase that opens creative possibilities without locking in narrow objectives.
Format: [Core feeling] + [Action/arrival] + [Defining moment]
Example: "Clarity + arrival + the moment you know" (for a real estate site).
1d. Diamond Exercise
For startups or when context is limited, define what the name must achieve using the Diamond:
| Corner | Question |
| Win | What does winning look like for the company? |
| What you have to win | Current assets and strengths |
| What you need to win | Gaps and resources needed |
| What you have to say | The one thing the market must hear |
Use the Diamond as the naming brief, not a generic mission statement.
Phase 2: Invent -- Generate and Filter
Volume first, then filter ruthlessly.
Read references/sound-symbolism.md and references/forced-synchronicity.md before this phase.
2a. Sound Symbolism
Select target letter/sound associations that match the desired behavior:
| Letter/Sound | Association | Use when you want... |
| V | Alive, vibrant | Energy, movement, life |
| B | Reliable, solid | Trust, dependability |
| Z, S | Signal, sharp | Clarity, precision, cutting through noise |
| K, hard C | Crisp, strong | Authority, impact |
| L | Smooth, light | Elegance, ease |
| R | Action, force | Power, motion |
| M, N | Warm, grounded | Comfort, familiarity |
| T | Precise, tight | Efficiency, sharpness |
| P | Punchy, ready | Energy, pop |
Use as a lens for filtering, not a rigid rule.
2b. Three-Brief Strategy
Generate names from three different angles to escape category thinking:
- Brief A (Real) -- The actual brief from Phase 1. Generate names that directly address the behavior, framework, and Diamond.
- Brief B (Competitor) -- Imagine you are naming for a major competitor. What names would you generate for them? This produces names the category expects but may surface strong options.
- Brief C (Unrelated) -- Imagine you are naming something completely unrelated (a bicycle, a restaurant, a sailing company). This breaks category cliches and produces the freshest candidates.
2c. Forced Synchronicity
Mine 2-3 domains unrelated to the category for unexpected metaphors:
- Browse their language, visuals, and naming patterns.
- Note words, phrases, or metaphors that map onto the brand's behavior.
- Use these as seeds so names don't sound like the category.
Example: For a trades automation tool, borrow from music (cadence, tempo), sailing (bearing, trim), and sports (relay, baton).
2d. Generate at Volume
Produce a large number of candidates (aim for breadth, not perfection):
- Mix real words, metaphors, compounds, coined words, and borrowed terms.
- Vary length (1-3 syllables preferred for recall).
- Include unexpected directions from Brief C and forced synchronicity.
2e. Filter
Apply these filters in order:
- Distinctiveness -- Does it stand apart from the competitive landscape? Remove anything that sounds like the category.
- Story potential -- Does it invite a line of explanation? "We're called X because..." should feel natural and interesting.
- Sound check -- Does the sound match the desired behavior? (Use the sound symbolism lens.)
- Practical screens -- Is it pronounceable? Spellable? Free of negative associations in key markets? Short enough?
Note: Legal and trademark screening is for the user to do later. Flag obvious conflicts but do not eliminate names solely on trademark speculation.
Phase 3: Implement -- Test and Select
Get the name into context; test what it makes people imagine.
3a. Present with Context
For each recommended name, provide:
- The name
- Why it works -- How it connects to the behavior and framework from Phase 1
- Sound/metaphor -- What sonic and metaphorical qualities it carries
- In context -- A sample tagline, headline, or usage ("Welcome to X", "Built on X", "X: [tagline]") so the user can feel the "lift"
3b. Structure the Shortlist
Organize names into tiers:
- Top recommendations (5-10) -- Strongest candidates with full rationale
- Strong alternatives (5-10) -- Good options worth considering
- Honorable mentions -- Names with potential that didn't make the cut, with brief notes on why
3c. Evaluation Guidance
If the user is testing names with others, advise:
- Ask: "What does this name make you imagine about the product?" This tests predisposition to consider, not subjective preference.
- Do not ask "Do you like it?" -- this produces unreliable data.
- Embrace polarization -- Mixed love/hate reactions are a strength. "No power in comfort." A name that everyone "kind of likes" is probably weak. A name that some love and some question has signal.
Output Format
Structure the naming deliverable as follows:
Brief
Summarize the framework from Phase 1: behavior (current, desired, market), landscape to avoid, creative framework, and Diamond (if applicable). This grounds the name recommendations.
Sound Direction
State the target sound associations and forced synchronicity sources used.
Shortlist
Present names in a table:
| Name | Why it works | Sound / metaphor |
| Name | Connection to behavior and framework | Sound associations and source metaphor |
Organize into Top recommendations and Strong alternatives.
For each top recommendation, include a sample usage line showing the name in context (tagline, headline, or sentence).
Principles Applied
Briefly confirm which naming principles drove the selections:
- Distinctive > comfortable
- Behavior and experience over abstract values
- Name starts the story
- Sound symbolism alignment
Next Steps
Recommend concrete next steps:
- Prototype -- Where to show the name (mock ad, app icon, business card, etc.)
- Research -- The right question to ask ("What does this name make you imagine about the product?")
- Legal/trademark -- Screen the shortlist
- Polarization -- How to interpret mixed reactions
Guidelines
- Ground every name in the behavior and experience established in Phase 1. Names should connect to how people act and feel, not abstract corporate values.
- Prioritize distinctiveness. If a name could belong to any competitor in the category, it is too generic. Challenge yourself to escape category language.
- Show your work. Walk the user through the framework, landscape, and creative decisions so they understand why each name was recommended.
- Generate with volume. Do not stop at 5 obvious names. Explore unexpected directions through forced synchronicity and the three-brief strategy.
- Present names in context. A name on its own is abstract; a name in a tagline, headline, or mock usage comes alive.
- When evaluating existing names, apply the same framework: Does it connect to behavior? Is it distinctive? Does it start a story?
- Treat polarization as signal, not noise. If the user reports mixed reactions, reframe that as a positive indicator of memorability and story potential.
- Flag obvious trademark conflicts but do not speculatively eliminate names. Legal screening is the user's responsibility.
- When uncertain about the business, market, or user intent, ask rather than assume. A good brief produces better names than a guessed brief.
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.

