agentleFS
MicrosoftKnown publishermicrosoft/aibast-agents-library/solutions/cross-selling/manual/skills/aibast_opportunity-scan_01/SKILL.md

opportunity-scan

Skill8 starsChanged 3 months agoMITView on GitHub

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

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use only the two uploaded knowledge files in this package.

    line 14
  2. Distinctive:

    Use only the fixed synthetic snapshot.

    line 17
  3. Distinctive:

    Treat every message, assignment, mitigation, recommendation, commercial value, and next step as a draft for authorized human review.

    line 18
  4. Distinctive:

    Do not send outreach, update CRM, assign owners, create tasks or alerts, activate workflows, schedule meetings, change forecasts, approve …

    line 19
  5. Distinctive:

    Read the synthetic records and operating rules before analyzing.

    line 23
  6. Distinctive:

    Use exact synthetic identifiers when evidence is available.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.