---
name: buyer-signal-research
description: "Find and qualify prospective companies using dated evidence, ICP fit and duplicate-aware research. Use for buyer signal research tasks; select only the requested methods."
metadata:
  version: "1.0.0"
---

# Buyer Signal Research

Find and qualify prospective companies using dated evidence, ICP fit and duplicate-aware research.

## OLLIE Runtime integration

Use relevant methods under the active OLLIE Operator. Read live Workspace Context and tenant bindings for client facts, account identity, goals, permissions and required inputs. Consume ask-ollie-authority-core for authority, outloop-access-fallback for access and recovery, email-lifecycle-core for communication, and the bootstrapper Runtime Contract for execution ownership and completion. This skill introduces no scheduler, independent permission policy or competing Runtime owner.

Discover the active Workspace’s approved capabilities before choosing API or browser access. Use Outloop for external service actions and the host’s supported tools for local artifacts. A product name in this package is not an access grant. Never import private account configuration or follow a source method that bypasses host restrictions. Apply the current task’s authorization; a library update does not grant permission to send, publish or activate a campaign.

## Required inputs

- Workspace ICP and exclusions
- Search markets and evidence window
- Existing prospect inventory
- Qualification rubric

Use for prospect-company discovery and market radar work. Read [qualification and research yield](references/qualification.md).

## Establish what counts as a buyer

Translate the current workspace ICP into observable criteria and explicit exclusions. Separate a buyer from an implementation partner, a product vendor, a staffing company and a person seeking employment. Hiring is an intent signal, not proof that a company serves external clients or has a purchasing need.

## Search and qualify

Combine service pages, case studies, hiring evidence, directories and public discussions according to the brief. Record source URL, observation date, relevant excerpt or paraphrase and confidence per criterion. Use multiple independent sources for ambiguous positives; label missing evidence rather than rewarding keyword matches.

## Reconcile the research set

Canonicalize company domains for comparison, retaining separate entities where corporate structure matters. Match against current CRM records before proposing creates. Keep disqualified records and their reasons in the private research ledger so the next run does not rediscover the same noise. Expiry dates are task inputs, not permanent truth about a company.

## Deliver usable next actions

Return qualified, uncertain and excluded sets with reasons; recommend a bounded next research or outreach action for each qualified company. Creating a prospect record does not authorize contact or auto-approve fit. Report source coverage and research limitations alongside totals.

## Completion

Verify findings against source evidence and read back every resulting artifact or authorized change. Distinguish a saved draft, queued job, active workflow and completed delivery. Return the requested outcome, evidence, output location and precise outstanding dependencies. Complete independent work when one dependency is unavailable. Package validation and synthetic fixtures do not establish real host import or provider execution.

Read [evaluation scenarios](references/evaluation.md) when testing this skill.