Relationship Intelligence turns scattered signals about a person into a short answer: who matters, for which opportunity, what already happened, who owns the relationship and what to do next. It keeps people, companies, evidence and interaction events separate, and it counts only verified touches.
It evaluates client, recruiting, partnership, sponsorship and acquisition fit as five separate lanes, each with its own evidence and freshness rules. An offline helper script summarizes deduplicated interaction events.
What You Get
- A data contract for people, companies, properties, observations and interaction events
- Rules for linking identities, with merge provenance that can be reversed
- A touch summary that separates owner-personal, team, automated, inbound and unknown-author events
- Five fit lanes with S, A, B, C, D and Unknown tiers and freshness requirements
- A team review view spec with filters for lane, owner, source, date and reply state
- An evaluation and staged rollout guide: read-only, shadow routing, then a small approved live batch
Common Use Cases
- Consolidating several lead feeds into one reviewable list of people and prior contact
- Deciding whether a lead is a client, hire, partner, sponsor or acquisition target
- Checking what contact already happened before anyone sends outreach
- Rolling out advisory fields in a CRM with a rollback plan
What Makes It Unique
Most lead enrichment skills score a contact once. This one scores five lanes independently, treats unknown as its own state, keeps coverage gaps visible and refuses to claim no prior contact when a source was not searched. It sets approval and consent boundaries for alerts and CRM writes.
Under The Hood
This is mostly a prose workflow with two reference documents and one small Python helper, touch_summary.py, which reads normalized JSON and summarizes verified interaction events. The helper makes no network calls and writes nothing to a CRM. The skill tells the agent to run the repository’s version check when available, to respect existing telemetry consent and to pass only the skill name, elapsed time, success and version to the telemetry logger. Research steps send the agent to approved professional sources or an authorized enrichment provider, and CRM writes or alerts need the user’s specific approval.