Education - Re-Engage 10K Cold Leads for DTC Skincare

# Education - Re-Engage 10K Cold Leads for DTC Skincare **Category:** Gemini Prompt → Education | **Audience:** Professionals or practitioners using AI for education tasks. | **Delivery:** User-specified channel or workflow **Job:** Improve the named business/performance outcome using a measurable, testable intervention. ## SOURCE INPUT Use this source brief as the authoritative task/scenario. Preserve its supplied numbers, constraints, assets, frameworks and requested deliverables. Separate facts from assumptions; never invent missing evidence. > Treat this as the authoritative source brief. Preserve useful specifics; do not invent facts or turn scenario values into verified claims. > > > Act as Senior Education Strategist for Gemini Prompt (experienced, scaled DTC Skincare to 8-figures, experienced technology/product background, generated substantial commercial experience with this system). CONTEXT: Business: DTC Skincare - $2M ARR, team 42, targeting Gen Z, stage bootstrapped profitable Current: CAC $249, LTV $863, churn 15%, traffic 3834/mo, conversion 2.1% Assets: Shopify 120 SKUs Goal: re-engage 10k cold leads in 30 days Constraint: Budget $3k/mo, GDPR required Tone: scientific McKinsey FRAMEWORK: ICE + structured 4-step. TASK: Complete Education system for Gemini Prompt / DTC Skincare. - common failure modes about education for DTC Skincare - 5 Whys root cause for re-engage 10k cold leads - Hidden cost of failure - Contrarian insight advanced practitioner insight ## LLM instruction variants > Variant A — DIRECT EXECUTION: Optimize concise task completion with explicit deliverables. > Variant B — MULTIMODAL / SOURCE-AWARE: Optimize interpretation of supplied sources or multimodal inputs. > Variant C — RESEARCH / VERIFICATION: Optimize evidence handling, comparison, uncertainty and validation. > Each variant must change the task architecture, not merely the wording. ## METHOD **Workflow:** Task → context → assumptions → staged execution → validation → output contract **Execution** - Diagnose the actual task before prescribing when diagnosis changes the answer. - Make the key strategic/technical/creative decision explicit. - Use concrete instructions, structures, examples, thresholds or implementation details. - Distinguish supplied facts, assumptions and validation needs. - Do not invent capabilities, results, claims or evidence. **Model / delivery** Target model(s): ChatGPT-4o, Claude 3.5, Gemini 1.5. Keep the core solution portable; adapt only relevant model behavior. Delivery context: User-specified channel or workflow; respect its real format, audience and constraints. **Output contract** Return the smallest complete deliverable that solves the job. Include the result, material assumptions, measurable/verifiable success criteria where relevant, and next decision/action when useful. **QA** - task is unambiguous - context is sufficient - assumptions are explicit - output contract is concrete - self-checks are relevant Also check for contradictions, generic recommendations, unusable outputs and constraint violations. ## CONTROLLED VARIANTS Use variants only as real experiments; never as paraphrases. **A — Direct execution:** concise complete execution. Preserve core identity/facts. Define the hypothesis, changed variable, expected effect and decision criterion. **B — Reasoned workflow:** staged analysis and checkpoints. Preserve core identity/facts. Define the hypothesis, changed variable, expected effect and decision criterion. **C — Structured QA:** schema, validation and edge cases. Preserve core identity/facts. Define the hypothesis, changed variable, expected effect and decision criterion. ## FINAL GATE Before answering, ask: Is this specific to the supplied scenario? Is every important instruction actionable? Are assumptions labeled? Is the output genuinely usable? Would a professional get a better result from this than from a generic prompt? If not, revise the weakest part before delivering.