Purpose
Diagnose where a product assortment overlaps against itself, quantify which SKUs are likely cannibalizing each other, and surface the unclaimed positioning territory the brand should own next — so every product has a distinct reason to exist and the line grows the category instead of splitting it.
When to Use
Invoke this skill when the user asks to:
- Audit a product line for redundancy or overlapping positioning
- Diagnose why two or more SKUs are stealing sales from each other
- Decide whether a new SKU adds distinct value or duplicates an existing one
- Find whitespace or unclaimed segments in their category to expand into
- Rationalize an assortment before a portfolio cull or reset
- Give each product a clearer, more differentiated positioning angle
Inputs Required
Before starting, collect:
- Assortment list: The SKUs to analyze — name and 1-line description each (aim for 5–30 SKUs)
- Category: The market or product category the line competes in
- Positioning per SKU: Current claim, angle, or "reason to buy" for each product (if known)
- Price points: Price or price tier for each SKU
- Target buyer per SKU: Who each product is meant for (persona, use case, or occasion)
- Sales/velocity data: Revenue, units, or a High/Mid/Low velocity flag per SKU (optional but sharpens cannibalization calls)
- Strategic intent: Any SKUs meant to be launched, protected, or considered for cut
If price tier or target buyer is missing for some SKUs, infer from the description and flag the assumption. If no velocity data is provided, run the analysis on positioning overlap alone and note where sales data would change the conclusion.
Instructions
Step 1: Build the Positioning Matrix
Map every SKU across two axes to make overlap visible:
- Axis 1 — Buyer/Occasion: Who buys it or when it's used (e.g., everyday vs. gifting, beginner vs. pro, budget vs. premium buyer)
- Axis 2 — Primary benefit/angle: The dominant reason-to-buy (e.g., convenience, performance, indulgence, value, sustainability)
Plot each SKU as a coordinate. Two or more SKUs landing in the same cell are the primary overlap candidates. Note clusters (crowded cells) and empty cells (potential whitespace).
Step 2: Score Positioning Overlap
For each pair of SKUs sharing a cell or adjacent cells, assess overlap across four dimensions:
- Target buyer overlap: Same persona/occasion? (Yes/Partial/No)
- Benefit overlap: Same primary reason-to-buy? (Yes/Partial/No)
- Price proximity: Within 15% of each other's price point? (Yes/No)
- Substitutability: Could a shopper reasonably pick either one for the same job? (High/Medium/Low)
Assign each pair an Overlap Score: High (3–4 dimensions match), Medium (2 match), Low (0–1 match).
Step 3: Flag Cannibalization Risk
Overlap becomes cannibalization when SKUs compete for the same wallet without expanding the market. For each High/Medium overlap pair, classify the risk:
- True cannibalization: Same buyer, same job, similar price — one SKU absorbs the other's demand. If velocity data shows one dominating, the weaker SKU is the cannibalization victim.
- Healthy laddering: Overlap in benefit but clear price/tier separation (good/better/best) — this is intentional and defensible, not a problem.
- Occasion-splitting: Same buyer, different use occasions — acceptable if the occasion difference is real and communicated.
For each true-cannibalization pair, name the likely loser, the estimated demand overlap (High/Med/Low), and the recommended resolution: Merge, Reposition, Re-tier, or Cut.
Step 4: Identify Whitespace Opportunities
From the empty and thinly-occupied cells in the matrix, surface unclaimed territory. For each whitespace opportunity, assess:
- The gap: What buyer/occasion + benefit combination is unserved
- Demand signal: Is there evidence the gap is real (adjacent category trends, competitor absence, buyer complaints) — or is it empty for a reason?
- Fit with the brand: Can this line credibly own it, or would it stretch the brand too far?
- Effort to enter: Reposition an existing SKU / extend the line / new development
Rank whitespace opportunities by a simple Opportunity Score: demand strength × brand fit ÷ effort. Flag any "empty for a reason" cells so the user doesn't chase dead space.
Step 5: Per-SKU Differentiation Plan
For every SKU in the assortment, deliver a one-line differentiation directive:
- Keep as-is: Positioning is distinct — protect it, name the angle it owns
- Sharpen: Positioning is fuzzy — give it a tightened, single-owner angle no other SKU claims
- Reposition: Overlapping — move it to a distinct buyer/benefit cell (specify the new cell)
- Re-tier: Same angle as another SKU — separate on price/quality laddering (specify tier)
- Cut/Merge: Redundant with no path to distinction — consolidate into the stronger SKU
Every SKU must end with a distinct reason-to-buy that no sibling SKU duplicates.
Step 6: Prioritized Action Summary
Rank the top 5–8 moves by impact, combining cannibalization fixes and whitespace plays. Each action names the SKU(s) affected, the move, and the expected outcome (recovered demand, new segment captured, line simplified).
Output Format
- Structure: Six sections following the steps; positioning matrix as a labeled grid or table; overlap and cannibalization as structured pairs; whitespace and per-SKU plans as ranked lists
- Length: 1,000–1,400 words
- Format: Structured document with one table (positioning matrix), bulleted pair analyses, and ranked lists
- Sections: Positioning Matrix → Overlap Scores → Cannibalization Risk → Whitespace Opportunities → Per-SKU Differentiation Plan → Prioritized Action Summary
- Tone: Merchandising strategist — decisive and portfolio-minded; names winners and losers rather than hedging
Quality Checklist
Before delivering output, verify:
- [ ] Every SKU from the provided assortment appears in the positioning matrix (count them against the input list)
- [ ] Each High/Medium overlap pair is classified as true cannibalization, healthy laddering, or occasion-splitting — not left ambiguous
- [ ] Every true-cannibalization pair has a named resolution (Merge/Reposition/Re-tier/Cut)
- [ ] Whitespace opportunities are ranked and any "empty for a reason" cells are flagged as such
- [ ] Every SKU has a differentiation directive and a distinct reason-to-buy no sibling duplicates
- [ ] The action summary is ranked by impact, not listed arbitrarily
Notes
- Overlap is not automatically bad — good/better/best laddering is deliberate overlap. The skill distinguishes intentional laddering from accidental cannibalization; don't recommend cutting a tiered SKU just because it shares a benefit angle.
- When velocity data is provided, let it break ties: the lower-velocity SKU in a true-cannibalization pair is almost always the one to reposition or cut.
- The most common finding in a bloated line is three SKUs fighting over one cell while two adjacent cells sit empty — reposition the weakest into the whitespace rather than cutting it outright.
- If the assortment exceeds ~30 SKUs, cluster by sub-category first and run the matrix within each cluster to keep the analysis legible.
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