Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," "free resource," "ROI calculator," "grader tool," "audit tool," "should I build a free tool," or "tools for lead gen." Use this whenever someone wants to build something useful and give
.claude/skills/free-tools/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 71% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-04 | ✓→✗ | ▼ Worse | 28% | 0% |
You are an expert in engineering-as-marketing strategy. Your goal is to help plan and evaluate free tools that generate leads, attract organic traffic, and build brand awareness.
Check for product marketing context first: If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Before designing a tool strategy, understand:
"Your product is my marketing opportunity." Bezos said "your margin is my opportunity." The engineering-as-marketing version: take a capability others monetize and build a free version as an acquisition channel. Unsplash gave away the stock photos Getty sold — and Getty acquired it. See references/tool-benchmarks.md for named cases and conversion numbers.
| Type | Examples | Best For | |------|----------|----------| | Calculators | ROI, savings, pricing estimators | Decisions involving numbers | | Generators | Templates, policies, names | Creating something quickly | | Analyzers | Website graders, SEO auditors | Evaluating existing work | | Testers | Meta tag preview, speed tests | Checking if something works | | Libraries | Icon sets, templates, snippets | Reference material | | Interactive | Tutorials, playgrounds, quizzes | Learning/understanding |
For detailed tool types and examples: See references/tool-types.md
For named case benchmarks (Unsplash, HubSpot Website Grader, Moz, Buffer, Shopify) with real conversion numbers: See references/tool-benchmarks.md
| Approach | Pros | Cons | |----------|------|------| | Fully gated | Maximum capture | Lower usage | | Partially gated | Balance of both | Common pattern | | Ungated + optional | Maximum reach | Lower capture | | Ungated entirely | Pure SEO/brand | No direct leads |
Tool landing page: "thing] calculator", "thing] generator", "free tool type]"
Supporting content: "How to use case]", "What is concept]"
Free tools attract links because:
When: Unique concept, core to brand, high strategic value, have dev capacity
Options: Outgrow, Involve.me, Typeform, Tally, Bubble, Webflow When: Speed to market, limited dev resources, testing concept
When: Something good exists, white-label available, not core differentiator
Account creation, saving results, advanced features, perfect design, every edge case
Rate each factor 1-5:
| Factor | Score | |--------|-------| | Search demand exists | ___ | | Audience match to buyers | ___ | | Uniqueness vs. existing | ___ | | Natural path to product | ___ | | Build feasibility | ___ | | Maintenance burden (inverse) | ___ | | Link-building potential | ___ | | Share-worthiness | ___ |
25+: Strong candidate | 15-24: Promising | <15: Reconsider
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-13 | pass→pass | 19,848 | 20,447 | +3% | 1 | 1 | 0% | 2,237 | 4,006 | +79% | 0 | 0 | — |
case-14 | pass→pass | 13,912 | 13,094 | -6% | 1 | 1 | 0% | 2,144 | 3,458 | +61% | 0 | 0 | — |
case-01 | fail→fail | 28,617 | 31,570 | +10% | 1 | 1 | 0% | 3,656 | 5,816 | +59% | 0 | 0 | — |
case-02 | fail→pass | 29,015 | 28,915 | -0% | 1 | 1 | 0% | 3,543 | 5,296 | +49% | 0 | 0 | — |
case-03 | fail→fail | 27,306 | 32,720 | +20% | 1 | 1 | 0% | 3,317 | 5,738 | +73% | 0 | 0 | — |
case-04 | pass→fail | 27,192 | 23,520 | -14% | 1 | 1 | 0% | 3,568 | 4,557 | +28% | 0 | 0 | — |
case-05 | pass→fail | 23,343 | 26,454 | +13% | 1 | 1 | 0% | 2,828 | 4,455 | +58% | 0 | 0 | — |
case-06 | pass→pass | 20,610 | 19,107 | -7% | 1 | 1 | 0% | 3,373 | 4,761 | +41% | 0 | 0 | — |
case-07 | fail→pass | 15,868 | 14,525 | -8% | 1 | 1 | 0% | 1,755 | 3,007 | +71% | 0 | 0 | — |
case-08 | fail→pass | 17,035 | 13,236 | -22% | 1 | 1 | 0% | 2,801 | 3,626 | +29% | 0 | 0 | — |
case-09 | pass→pass | 19,731 | 15,088 | -24% | 1 | 1 | 0% | 2,176 | 3,794 | +74% | 0 | 0 | — |
case-10 | pass→fail | 9,101 | 11,425 | +26% | 1 | 1 | 0% | 1,237 | 3,031 | +145% | 0 | 0 | — |
case-11 | pass→pass | 16,899 | 13,699 | -19% | 1 | 1 | 0% | 2,221 | 3,583 | +61% | 0 | 0 | — |
case-12 | pass→pass | 19,693 | 25,170 | +28% | 1 | 1 | 0% | 2,454 | 4,369 | +78% | 0 | 0 | — |
case-15 | fail→pass | 19,219 | 22,287 | +16% | 1 | 1 | 0% | 2,794 | 4,303 | +54% | 0 | 0 | — |
case-16 | pass→pass | 22,734 | 28,123 | +24% | 1 | 1 | 0% | 2,665 | 4,134 | +55% | 0 | 0 | — |
case-17 | fail→fail | 19,495 | 19,256 | -1% | 1 | 1 | 0% | 2,558 | 4,149 | +62% | 0 | 0 | — |
case-18 | pass→pass | 19,522 | 20,518 | +5% | 1 | 1 | 0% | 2,221 | 3,618 | +63% | 0 | 0 | — |
case-19 | pass→pass | 21,851 | 24,114 | +10% | 1 | 1 | 0% | 2,440 | 4,178 | +71% | 0 | 0 | — |
case-20 | fail→fail | 26,274 | 22,393 | -15% | 1 | 1 | 0% | 2,496 | 3,846 | +54% | 0 | 0 | — |
case-21 | pass→pass | 23,421 | 21,743 | -7% | 1 | 1 | 0% | 2,492 | 4,110 | +65% | 0 | 0 | — |
case-22 | pass→pass | 18,580 | 28,085 | +51% | 1 | 1 | 0% | 2,475 | 5,041 | +104% | 0 | 0 | — |
case-23 | pass→pass | 15,415 | 8,252 | -46% | 1 | 1 | 0% | 1,701 | 2,652 | +56% | 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. 23 cases were attempted. The headline lift of +4 percentage points is the difference between those two pass rates over the 23 comparable cases. 3 cases got worse with the skill loaded, and they are 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 7/23/2026 | +23% |
Other measured skills in the registry, with their headline benchmark lift.