prospecting-partner

name	prospecting-partner
description	Use when researching, qualifying, segmenting, prioritizing, or preparing target lists for prospects, partners, investors, BD contacts, customers, advisors, or outreach campaigns.

Prospecting Partner

Prospecting Partner turns a market or relationship question into an evidence-backed target map. It does not send outreach and should not produce final send-ready copy unless the user also asks for Outreach Engine work.

Required Startup

1. Find the nearest company-context.yaml from the current directory upward.
2. Read it before doing research. Use it to identify:
   • company id and aliases
   • Folio tenant
   • GitHub org and local repos
   • Google Workspace profile
   • task source of truth
   • outreach approval boundaries
3. If no company context exists, ask one concise question before proceeding unless the company is obvious from the working directory.

Source Order

Prefer owned context before broad external research:

1. company-context.yaml, AGENTS.md, CLAUDE.md, CONTEXT.md, and STATUS.md
2. Folio tenant from company context
3. Local repos and safe workspaces listed in company context
4. Google Drive through the configured gws-account profile when relevant
5. msgvault or Folio email corpus for relationship history
6. Web research for current facts, company pages, executives, funding, recent news, and source links

Use web research for external company/person facts that may have changed. Do not invent emails, titles, funding status, or relationship history.

Operating Rules

• Keep Prospecting Partner separate from Outreach Engine.
• Output evidence, fit, priority, and recommended next action.
• Do not send email, create calendar invites, publish materials, or modify CRM systems unless explicitly asked.
• Mark confidence and source quality. Distinguish known facts from inference.
• Respect sensitive paths and read-only paths in company-context.yaml.
• Use only the task systems, GitHub workspaces, and source repositories listed in company-context.yaml.
• Do not copy sensitive source materials into public repositories or target-list outputs.

Deliverable Shape

Use this structure unless the user asks for a specific format:

## Target Thesis
One paragraph explaining the segment and why it matters.

## Priority Targets
| Priority | Target | Segment | Why Now | Evidence | Relationship Path | Next Action | Confidence |
|---|---|---|---|---|---|---|---|

## Exclusions
Targets intentionally skipped and why.

## Follow-Up Work
Specific research gaps, CRM updates, or outreach-drafting handoff items.

Fit Scoring

Use a simple 1-5 score when prioritization is useful:

• 5: strong strategic fit, timely trigger, accessible path, and clear next action
• 4: strong fit with one missing signal
• 3: plausible but needs more evidence
• 2: weak fit or poor timing
• 1: avoid for now

Always explain the score in plain language.

Company-Specific Defaults

Keep company-specific defaults in the nearest company-context.yaml, not in the public skill. Useful fields include:

company_id: example-company
aliases: ["Example Co"]
folio_tenant: example-company
research:
  priority_segments:
    - customers
    - partners
    - investors
  safe_workspaces:
    - example-workspace
  sensitive_paths:
    - private/

If no company context exists, ask for the company and target segment before researching.