$ loading_
Explain synthetic cross-sell affinity rules and benchmark assumptions from fixed evidence.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "cross-selling-product-affinity" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/solutions/cross-selling/manual/skills/product-affinity/SKILL.md 2. Save it as ~/.claude/skills/product-affinity/SKILL.md 3. Reload skills and tell me it's ready
Please run product_affinity. Use only the two knowledge files in this package and the synthetic snapshot to explain the product affinity rules and benchmark assumptions, without treating them as real conversion performance. The output must include "Product Affinity Matrix", "Response Assumption", and "Evidence boundary".
A read-only explanation summarizing synthetic product relationships, response assumptions, and the evidence boundary, clearly stating that they are not actual business results.
Review the following draft under the product_affinity rules, identify statements that incorrectly present synthetic benchmarks as observed conversion performance, and rewrite them into a compliant version. Keep the Evidence boundary.
Returns a list of out-of-bounds statements and a revised explanation that emphasizes the content is only synthetic test evidence and decision support.
Based on the uploaded synthetic records, produce a product-affinity explanation in the required structure: first Product Affinity Matrix, then Response Assumption, and finally Evidence boundary. Do not use external data and do not invent missing records.
An analysis that follows the fixed template, uses available synthetic identifiers and evidence, and does not expand beyond the provided information.
A data analyst or product manager can use it to review product affinity rules and benchmark assumptions while making clear they come from a synthetic snapshot, not real conversion performance. It fits internal demos or methodology reviews.
Marketing or sales enablement teams can use it to organize a product affinity matrix with response assumptions and an evidence boundary. This helps avoid presenting test evidence as executed customer actions or business outcomes.
When drafting an analysis, it can check whether synthetic names, counts, percentages, or projections are being mistaken for real observed data. It is useful for pre-publication content review.
The document defines this skill as a read-only product-affinity analysis agent for an enablement context. It only supports the product_affinity operation and must use only the two knowledge files in the package plus a fixed synthetic snapshot, with no browsing, enrichment, or invented records. Responses must include Product Affinity Matrix, Response Assumption, and Evidence boundary, and clearly state that all figures and projections are synthetic test evidence rather than real conversion performance or completed actions.
Enablement Manager
product_affinitysynthetic onlyproduct_affinity.Product Affinity Matrix, Response Assumption, Evidence boundary anchors.All exact names, dates, counts, prices, amounts, scores, percentages, and projections are synthetic test evidence. The response is read-only decision support. Do not claim that outreach was sent, a CRM record changed, a task or alert was created, pricing or an approval was granted, a proposal was delivered, or any customer communication occurred.
Explain the synthetic product-affinity and benchmark assumptions without treating them as observed conversion performance.
The response must include Product Affinity Matrix, Response Assumption, Evidence boundary and preserve the explicit synthetic evidence boundary.
No. The documentation states that the data source is synthetic only, and all names, dates, counts, prices, scores, percentages, and projections must be treated as synthetic test evidence.
No. Both the description and the documentation require it to explain product affinity and benchmark assumptions without treating them as observed conversion performance.
The documentation requires the response to include the anchors "Product Affinity Matrix", "Response Assumption", and "Evidence boundary", while preserving the explicit synthetic evidence boundary.
Draft prioritized amendment positions and legal escalation points for contract renegotiations.
Rank a fictional contract portfolio to prioritize legal review attention.
Analyze loyalty tier thresholds, perks, progress, and tradeoffs without changing status.
Compare contract clauses against internal policy requirements and identify gaps.
Generate a synthetic points summary explanation without changing the ledger.
Scan synthetic customer records to find evidence-backed cross-sell product gaps.
Compare synthetic cross-sell portfolio value scenarios for human-reviewed decision support.
Draft prioritized cross-sell recommendations and a reviewable engagement plan from synthetic data.
Extract shared principles from skills and turn them into maintainable rule files.
Prepare reviewable retention and service-recovery options for churn-related customer cases.
Get a synthetic health overview of a loyalty program without changing it.
Turn raw research feedback into structured insights and prioritized recommendations.