Purpose
Produce clear, decision-ready profiles of the distinct seller segments on an ecommerce platform — so product teams can prioritize features, tailor onboarding, and remove activation barriers for each type of seller rather than treating supply as one undifferentiated group.
When to Use
Invoke this skill when the user asks to:
- Profile the different types of sellers or merchants on their platform
- Build seller personas for onboarding, activation, or lifecycle work
- Understand why certain seller types stall during activation
- Prioritize roadmap features by which seller segment they serve
- Segment the supply side of a marketplace for GTM or pricing decisions
- Identify which seller segment to focus growth investment on next
Inputs Required
Before starting, collect:
- Platform type: What the platform is and how sellers use it (marketplace, storefront builder, SaaS + payments, etc.)
- Known seller types: Any seller categories already observed (physical goods, services, digital products, subscriptions, etc.)
- Business model: How the platform makes money from sellers (take rate, subscription, listing fees, payment processing)
- Activation definition: What counts as an "activated" seller (first listing, first sale, first payout, N sales in 30 days)
- Current pain point: Where sellers are stalling, churning, or underperforming — if known
- Data available: Any behavioral or revenue data on seller cohorts that can inform the profiles
- Decision at hand: What the profiles will be used to decide (roadmap, onboarding redesign, pricing, targeting)
If seller types or activation definition are missing, default to the four most common ecommerce seller archetypes (physical goods, services, digital products, subscription/recurring) and a "first successful sale" activation event — note the assumption.
Instructions
Step 1: Define the Segmentation Axis
Before profiling, establish what actually separates these sellers behaviorally — not just what they sell.
- Anchor segmentation on jobs-to-be-done and operating model, not surface product category
- Common axes: fulfillment model (ship vs. deliver vs. instant download vs. book time), inventory presence (stock vs. no-stock), transaction frequency (one-time vs. recurring), and seller sophistication (side hustle vs. established business)
- Name the 5-7 segments explicitly and state, in one line each, what makes them behaviorally distinct
Step 2: Build a Profile for Each Segment
For each of the 5-7 segments, produce a structured profile with these fields:
Segment name and one-line definition A memorable label (e.g., "Handmade Physical Sellers," "Service Providers," "Digital Creators," "Subscription Sellers") plus a single sentence on who they are.
Primary job-to-be-done The core outcome this seller hires the platform to accomplish. Frame as "When I , I want to , so I can ___."
Top 3 needs The specific capabilities this segment depends on, ranked by importance. Be concrete — "inventory sync across channels," not "good tools."
Activation barriers (3-4) The specific friction points that prevent this segment from reaching first success. Distinguish setup barriers (before listing) from momentum barriers (before first sale) from retention barriers (after first sale).
Success indicators The 2-3 measurable signals that this segment is thriving — the metrics that predict retention and expansion for this specific seller type (e.g., for services: booking fill rate; for digital: repeat purchase rate; for physical: reorder velocity).
Monetization fit How well the platform's business model matches this segment's economics, and where the pricing tension is (e.g., high-take-rate erodes thin physical margins; subscription pricing fits recurring digital sellers).
Highest-leverage intervention The single product change that would most improve this segment's activation or retention.
Step 3: Cross-Segment Comparison
Build a comparison table across all segments with columns for: segment, primary JTBD, top activation barrier, key success metric, and monetization fit (High / Medium / Low). This makes the tradeoffs visible at a glance.
Step 4: Prioritization Recommendation
Based on activation difficulty, monetization fit, and the user's stated decision, recommend which 1-2 segments to prioritize and why. Be opinionated. Name the segment to invest in, the segment to deprioritize, and the reasoning tied to the platform's business model.
Output Format
- Structure: Segmentation rationale → 5-7 full segment profiles → cross-segment comparison table → prioritization recommendation
- Length: 1,100–1,500 words
- Format: Structured profiles with labeled fields, one comparison table, prose recommendation
- Sections: Segmentation axis → Segment profiles (one block each) → Comparison table → Prioritization recommendation
- Tone: Product strategy — evidence-minded, specific, decision-oriented; no persona fluff or invented demographics
Quality Checklist
Before delivering output, verify:
- [ ] Exactly 5-7 segments are profiled, each behaviorally distinct (not just different product categories)
- [ ] Every profile includes all seven fields (definition, JTBD, needs, barriers, success indicators, monetization fit, intervention)
- [ ] Activation barriers are separated into setup / momentum / retention — not lumped together
- [ ] Success indicators are measurable metrics specific to the segment, not generic "high engagement"
- [ ] The comparison table includes every profiled segment with all five columns filled
- [ ] The prioritization recommendation names a specific segment and ties the reasoning to the platform's business model
Notes
- The most common mistake is segmenting by what sellers sell rather than how they operate — a coach selling a course and a coach selling live sessions behave very differently on the same platform
- Physical goods sellers usually stall at setup (inventory, shipping config); service sellers stall at momentum (getting the first booking); digital sellers stall at retention (one-and-done buyers) — barrier location is the most actionable output
- If behavioral data is provided, use it to validate or challenge the assumed barriers rather than restating the data back
- Monetization fit is where roadmap and pricing tension surface — flag any segment the platform serves well but monetizes poorly, since that's a strategic decision, not a product bug
How to use this skill
This file is a Claude Code skill in Anthropic's standard format — markdown with YAML frontmatter at the top.
Installing in Claude Code:
~/.claude/skills/<folder-name>/SKILL.md— auto-loads in every session anywhere on your machine (recommended for skills you'll use across multiple projects)<your-project>/.claude/skills/<folder-name>/SKILL.md— auto-loads only when working in that project (recommended for project-specific skills)
Restart Claude Code or open a new session to register.
Using in Claude.ai, ChatGPT, Gemini, or other AI tools:
- Drag this file into a new chat, or copy and paste its contents
- Send your task or request as your next message — the AI will apply the skill where it fits
For Claude Code skill details: https://docs.anthropic.com/en/docs/claude-code/skills