Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate and evaluate names for a product, feature, or release. Use when asked to name a product/feature/company, brainstorm naming options, or choose between name candidates. Produces a shortlist of names across naming strategies, each with rationale, plus an evaluation against clear criteria (clarity, fit, memorability, availability checks to run) and a recommendation — not just a random list.
.claude/skills/mohitagw15856-product-naming/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 63% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 34% | 0% |
A name has to do a lot of work: signal what the thing is, fit the brand, be easy to say and remember, and not already be taken. This skill generates candidates across different naming strategies and then evaluates them against criteria — so you get a defensible shortlist and a recommendation, not a brainstorm dump.
Given "name our new analytics feature", produce names anyway — infer the audience, the brand feel, and what the name must convey, and label assumptions. Always flag that trademark, domain, and existing-use checks are required before adopting any name — propose, don't certify availability.
Ask for these only if they aren't already provided (else infer and label):
1. Direction — a line on what the name should achieve and the strategy mix that fits.
2. Candidates by strategy — a shortlist grouped by approach, each with a one-line rationale:
| Strategy | Examples | Feel | |---|---|---| | Descriptive | (says what it does) | clear, SEO-friendly, lower distinctiveness | | Evocative / metaphor | (suggests a quality) | memorable, needs context | | Invented / coined | (new word) | ownable, needs building | | Compound / blend | (two ideas joined) | balance of clarity + distinctiveness |
3. Evaluation — score the top candidates against criteria:
| Name | Clear | On-brand | Memorable | Easy to say/spell | Extensible | Notes | |---|---|---|---|---|---|---|
4. Recommendation — the top pick (or 2), why, and the checks to run before committing: trademark search, domain/handle availability, existing-product collision, and meaning in target languages.
Brand & product naming practice — strategy-driven generation, criteria-based evaluation, and pre-adoption availability/meaning checks.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 36,591 | 21,034 | -43% | 1 | 1 | 0% | 2,972 | 3,347 | +13% | 0 | 0 | — |
case-02 | fail→fail | 25,245 | 20,326 | -19% | 1 | 1 | 0% | 3,151 | 2,766 | -12% | 0 | 0 | — |
case-03 | pass→pass | 24,289 | 20,647 | -15% | 1 | 1 | 0% | 2,727 | 3,230 | +18% | 0 | 0 | — |
case-04 | pass→pass | 21,274 | 16,774 | -21% | 1 | 1 | 0% | 1,574 | 2,618 | +66% | 0 | 0 | — |
case-05 | fail→fail | 29,663 | 20,726 | -30% | 1 | 1 | 0% | 2,021 | 2,842 | +41% | 0 | 0 | — |
case-06 | pass→pass | 10,965 | 14,195 | +29% | 1 | 1 | 0% | 1,424 | 2,202 | +55% | 0 | 0 | — |
case-07 | pass→pass | 24,036 | 28,254 | +18% | 1 | 1 | 0% | 2,882 | 3,818 | +32% | 0 | 0 | — |
case-08 | fail→pass | 25,598 | 21,485 | -16% | 1 | 1 | 0% | 2,820 | 3,019 | +7% | 0 | 0 | — |
case-09 | fail→pass | 32,755 | 36,150 | +10% | 1 | 1 | 0% | 3,125 | 3,998 | +28% | 0 | 0 | — |
case-10 | pass→pass | 25,594 | 14,528 | -43% | 1 | 1 | 0% | 2,800 | 3,086 | +10% | 0 | 0 | — |
case-11 | pass→pass | 18,233 | 20,288 | +11% | 1 | 1 | 0% | 1,751 | 3,167 | +81% | 0 | 0 | — |
case-12 | fail→fail | 29,707 | 30,337 | +2% | 1 | 1 | 0% | 3,414 | 4,816 | +41% | 0 | 0 | — |
case-13 | pass→pass | 30,053 | 25,211 | -16% | 1 | 1 | 0% | 3,541 | 4,056 | +15% | 0 | 0 | — |
case-14 | pass→fail | 22,106 | 25,464 | +15% | 1 | 1 | 0% | 2,585 | 3,567 | +38% | 0 | 0 | — |
case-15 | fail→pass | 31,011 | 29,259 | -6% | 1 | 1 | 0% | 4,400 | 3,960 | -10% | 0 | 0 | — |
case-16 | fail→pass | 19,844 | 17,417 | -12% | 1 | 1 | 0% | 1,882 | 3,076 | +63% | 0 | 0 | — |
case-17 | pass→pass | 20,946 | 15,049 | -28% | 1 | 1 | 0% | 2,657 | 3,490 | +31% | 0 | 0 | — |
case-18 | pass→pass | 19,507 | 15,658 | -20% | 1 | 1 | 0% | 3,003 | 3,252 | +8% | 0 | 0 | — |
case-19 | fail→pass | 35,418 | 23,074 | -35% | 1 | 1 | 0% | 2,869 | 3,852 | +34% | 0 | 0 | — |
case-20 | fail→pass | 16,411 | 33,380 | +103% | 1 | 1 | 0% | 2,225 | 2,974 | +34% | 0 | 0 | — |
case-21 | fail→fail | 40,433 | 36,821 | -9% | 1 | 1 | 0% | 3,233 | 3,747 | +16% | 0 | 0 | — |
case-22 | pass→pass | 19,214 | 15,393 | -20% | 1 | 1 | 0% | 2,448 | 3,255 | +33% | 0 | 0 | — |
case-23 | fail→pass | 23,730 | 16,499 | -30% | 1 | 1 | 0% | 3,510 | 2,899 | -17% | 0 | 0 | — |
case-24 | fail→pass | 18,392 | 23,020 | +25% | 1 | 1 | 0% | 2,739 | 3,746 | +37% | 0 | 0 | — |
case-25 | pass→pass | 21,697 | 21,254 | -2% | 1 | 1 | 0% | 3,029 | 3,729 | +23% | 0 | 0 | — |
case-26 | fail→pass | 17,495 | 16,802 | -4% | 1 | 1 | 0% | 2,708 | 2,991 | +10% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 26 cases were attempted. The headline lift of +31 percentage points is the difference between those two pass rates over the 26 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.