Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create or update a reusable product marketing context document with positioning, audience, ICP, use cases, and messaging. Use at the start of a project to avoid repeating core marketing context across tasks.
.claude/skills/sickn33-product-marketing-context/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 61% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-17 | ✓→✗ | ▼ Worse | 56% | 0% |
You help users create and maintain a product marketing context document. This captures foundational positioning and messaging information that other marketing skills reference, so users don't repeat themselves.
The document is stored at .agents/product-marketing-context.md.
First, check if .agents/product-marketing-context.md already exists. Also check .claude/product-marketing-context.md for older setups — if found there but not in .agents/, offer to move it.
If it exists:
If it doesn't exist, offer two options:
Most users prefer option 1. After presenting the draft, ask: "What needs correcting? What's missing?"
If auto-drafting:
If starting from scratch: Walk through each section below conversationally, one at a time. Don't dump all questions at once.
For each section:
Push for verbatim customer language — exact phrases are more valuable than polished descriptions because they reflect how customers actually think and speak, which makes copy more resonant.
If multiple stakeholders are involved in buying, capture for each:
The JTBD Four Forces:
After gathering information, create .agents/product-marketing-context.md with this structure:
markdown# Product Marketing Context *Last updated: [date]* ## Product Overview **One-liner:** **What it does:** **Product category:** **Product type:** **Business model:** ## Target Audience **Target companies:** **Decision-makers:** **Primary use case:** **Jobs to be done:** - **Use cases:** - ## Personas | Persona | Cares about | Challenge | Value we promise | |---------|-------------|-----------|------------------| | | | | | ## Problems & Pain Points **Core problem:** **Why alternatives fall short:** - **What it costs them:** **Emotional tension:** ## Competitive Landscape **Direct:** [Competitor] — falls short because... **Secondary:** [Approach] — falls short because... **Indirect:** [Alternative] — falls short because... ## Differentiation **Key differentiators:** - **How we do it differently:** **Why that's better:** **Why customers choose us:** ## Objections | Objection | Response | |-----------|----------| | | | **Anti-persona:** ## Switching Dynamics **Push:** **Pull:** **Habit:** **Anxiety:** ## Customer Language **How they describe the problem:** - "[verbatim]" **How they describe us:** - "[verbatim]" **Words to use:** **Words to avoid:** **Glossary:** | Term | Meaning | |------|---------| | | | ## Brand Voice **Tone:** **Style:** **Personality:** ## Proof Points **Metrics:** **Customers:** **Testimonials:** > "[quote]" — [who] **Value themes:** | Theme | Proof | |-------|-------| | | | ## Goals **Business goal:** **Conversion action:** **Current metrics:**
.agents/product-marketing-context.md/product-marketing-context anytime to update it."| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 11,585 | 1,727 | -85% | 1 | 1 | 0% | 1,913 | 2,087 | +9% | 0 | 0 | — |
case-02 | fail→fail | 4,054 | 8,849 | +118% | 1 | 1 | 0% | 660 | 2,813 | +326% | 0 | 0 | — |
case-03 | fail→fail | 18,781 | 3,157 | -83% | 1 | 1 | 0% | 3,433 | 2,067 | -40% | 0 | 0 | — |
case-04 | fail→fail | 10,884 | 4,884 | -55% | 1 | 1 | 0% | 1,723 | 2,704 | +57% | 0 | 0 | — |
case-05 | fail→fail | 11,930 | 6,399 | -46% | 1 | 1 | 0% | 2,074 | 2,936 | +42% | 0 | 0 | — |
case-06 | pass→pass | 14,394 | 10,397 | -28% | 1 | 1 | 0% | 2,314 | 3,473 | +50% | 0 | 0 | — |
case-07 | pass→pass | 11,496 | 6,696 | -42% | 1 | 1 | 0% | 1,797 | 2,584 | +44% | 0 | 0 | — |
case-08 | pass→pass | 14,546 | 8,620 | -41% | 1 | 1 | 0% | 2,423 | 3,208 | +32% | 0 | 0 | — |
case-09 | pass→pass | 13,287 | 7,771 | -42% | 1 | 1 | 0% | 2,272 | 3,129 | +38% | 0 | 0 | — |
case-10 | fail→pass | 16,773 | 7,217 | -57% | 1 | 1 | 0% | 2,620 | 3,103 | +18% | 0 | 0 | — |
case-11 | fail→pass | 12,833 | 10,140 | -21% | 1 | 1 | 0% | 2,212 | 3,551 | +61% | 0 | 0 | — |
case-12 | pass→pass | 13,278 | 10,572 | -20% | 1 | 1 | 0% | 2,172 | 3,547 | +63% | 0 | 0 | — |
case-13 | fail→pass | 12,351 | 2,532 | -79% | 1 | 1 | 0% | 1,961 | 2,253 | +15% | 0 | 0 | — |
case-14 | pass→pass | 11,677 | 4,411 | -62% | 1 | 1 | 0% | 1,903 | 2,523 | +33% | 0 | 0 | — |
case-15 | fail→fail | 8,606 | 1,960 | -77% | 1 | 1 | 0% | 1,479 | 2,187 | +48% | 0 | 0 | — |
case-16 | pass→pass | 10,978 | 7,395 | -33% | 1 | 1 | 0% | 1,787 | 3,033 | +70% | 0 | 0 | — |
case-17 | pass→fail | 9,718 | 5,195 | -47% | 1 | 1 | 0% | 1,755 | 2,740 | +56% | 0 | 0 | — |
case-18 | fail→fail | 6,552 | 1,771 | -73% | 1 | 1 | 0% | 1,128 | 2,138 | +90% | 0 | 0 | — |
case-19 | fail→pass | 10,225 | 3,759 | -63% | 1 | 1 | 0% | 1,843 | 2,393 | +30% | 0 | 0 | — |
case-20 | pass→pass | 6,006 | 11,251 | +87% | 1 | 1 | 0% | 1,015 | 3,275 | +223% | 0 | 0 | — |
case-21 | pass→pass | 11,300 | 10,875 | -4% | 1 | 1 | 0% | 2,064 | 3,811 | +85% | 0 | 0 | — |
case-22 | pass→fail | 5,329 | 12,453 | +134% | 1 | 1 | 0% | 1,009 | 4,381 | +334% | 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. 22 cases were attempted, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +9 percentage points is the difference between those two pass rates over the 21 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.
Other measured skills in the registry, with their headline benchmark lift.