$ ~/registry/skill/microsoft-solutions-cross-selling-manual-skills-opportunity-scan

SKILL

cross-selling-opportunity-scan

Scan synthetic customer records to find evidence-backed cross-sell product gaps.

Source

GitHub

Updated

2026-08-14

// securityLow risk

Prompt only, no code
Open source

Running security audit…

Credentials
Network egress
Code execution
Data access
Supply chain

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "cross-selling-opportunity-scan" skill from askskill:
1. Download https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/solutions/cross-selling/manual/skills/opportunity-scan/SKILL.md
2. Save it as ~/.claude/skills/opportunity-scan/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Scan a specific synthetic customer opportunity

Prompt

Please run opportunity_scan for synthetic customer CUST-001 and identify product gaps, usage signals, buying signals, and budget timing using evidence only from the two knowledge files in the package.

Expected

Returns a cross-sell opportunity scan based on the fixed synthetic snapshot, including explicit evidence and boundary notes.

Generate a read-only sales support draft

Prompt

Using the synthetic data source, produce a read-only decision-support draft for CUST-001, preserving the Cross-Sell Opportunity Scan, Synthetic Usage Signals, and Evidence boundary markers, with no external data.

Expected

Produces a structured analysis draft for human review, without outreach, CRM updates, or task actions.

// use cases

Sales operations reviews opportunity in a demo account

A sales operations user can use it to inspect product gaps and related signals for synthetic customer CUST-001. The result is a read-only decision-support draft for later human review.

Run an evidence scan within a controlled data boundary

When a team needs to demonstrate opportunity identification within a fixed synthetic snapshot, this skill analyzes only the two packaged knowledge files and does not use external data.

// docs

AI summary

The README describes this skill as a cross-sell opportunity scan agent for sales operations use. It requires the request to match opportunity_scan and limits analysis to the synthetic data source plus the two packaged knowledge files for CUST-001, with no external data or invented facts. The output must preserve fixed section markers and an explicit evidence boundary, and all findings are read-only drafts for human review rather than operational actions.

Show full docs ▾

Cross-Selling Opportunities Agent — Opportunity Scan

Persona

Sales Operations Manager

Input contract

Operation: opportunity_scan
Data source: synthetic only
Use only the two uploaded knowledge files in this package.

Guardrails

Use only the fixed synthetic snapshot; do not browse, enrich, infer, invent, or use external data.
Treat every message, assignment, mitigation, recommendation, commercial value, and next step as a draft for authorized human review.
Do not send outreach, update CRM, assign owners, create tasks or alerts, activate workflows, schedule meetings, change forecasts, approve pricing, deliver proposals, alter subscriptions, or contact customers.

Procedure

Confirm that the request matches opportunity_scan.
Read the synthetic records and operating rules before analyzing.
Use exact synthetic identifiers when evidence is available; do not invent missing records.
Produce the exact fixed-snapshot evidence with the required Cross-Sell Opportunity Scan, Synthetic Usage Signals, Evidence boundary anchors.
End with the evidence boundary below.

Evidence boundary

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.

Locked demo prompt

Scan synthetic customer CUST-001 for product gaps, usage signals, buying signals, and budget timing.

Expected evidence marker

The response must include Cross-Sell Opportunity Scan, Synthetic Usage Signals, Evidence boundary and preserve the explicit synthetic evidence boundary.

// FAQ

What does this skill do?

It scans the synthetic ownership record for customer CUST-001 to find evidence-backed cross-sell product gaps and summarize usage signals, buying signals, and budget timing.

What data sources can it use?

The documentation says it can use only the synthetic data source and only the two uploaded knowledge files in the package, with no browsing, enrichment, or external data.

Does it automatically perform sales actions?

No. The output is explicitly limited to a read-only decision-support draft and must not send outreach, update CRM, create tasks or alerts, or trigger approvals, pricing, or customer communication.