Contact Research
Interpret CRM and product activity signals so a solo builder can prioritize outreach, support, and re-engagement without guessing intent.
Overview
Contact-research is an agent skill most often used in Grow (also Launch distribution, Grow support) that interprets contact activity and relationship signals so solo builders can prioritize outreach and lifecycle actions
Install
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill contact-researchWhat is this skill?
- Maps activity signals (email, meetings, docs, logins, events) to intent tiers
- Flags relationship cooling at 30+ and 90+ days of inactivity with recommended tone
- Covers job-change, promotion, and title-shift cues for upgrading account strategy
- Distinguishes support friction from high-engagement community and product usage patterns
- Three signal families: activity, relationship, and job/professional
- Relationship cooling called out at 30+ and 90+ days of no activity
Adoption & trust: 1.6k installs on skills.sh; 19.6k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have scattered CRM, product, and support events but no consistent way to read intent, dormancy, or when a contact’s role change should change your strategy.
Who is it for?
Solo founders doing their own sales and success who want a repeatable rubric before the agent drafts follow-ups or account summaries.
Skip if: Teams that only need raw CRM exports with no interpretation layer, or builders with no named contacts or lifecycle motion yet.
When should I use this skill?
User asks to research a contact, interpret engagement signals, prioritize outreach from CRM or product activity, or summarize relationship health before messaging.
What do I get? / Deliverables
You get a structured read on signal type and relationship health so the next message, check-in, or account plan matches actual engagement instead of a generic cadence.
- Signal-by-signal interpretation aligned to activity, relationship, and job-change tables
- Recommended next action tone (gentle check-in, empathy, upgrade strategy, warm intro angle)
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Grow because contact signals mainly inform retention, sales follow-up, and customer lifecycle decisions after you have users. Lifecycle is the best fit for mapping opens, logins, dormancy, and champion behavior into who to nurture or win back.
Where it fits
After a webinar, rank attendees by event plus login signals before sending personal launch notes.
Before a renewal conversation, classify dormancy versus champion patterns across channels.
When a ticket spike appears, frame it as friction empathy rather than upsell pressure.
During early outreach, note doc-page research signals to tailor a prototype demo ask.
How it compares
Use as a signal-interpretation playbook alongside CRM integrations, not instead of pipeline automation or enrichment APIs.
Common Questions / FAQ
Who is contact-research for?
Solo and indie builders who sell or support their own product and want the agent to reason about contact intent using a shared signal taxonomy.
When should I use contact-research?
Use it in Grow lifecycle when prioritizing follow-ups, in Grow support when tickets imply friction, and at Launch distribution when deciding which warm contacts deserve a personal touch after an event or signup spike.
Is contact-research safe to install?
Review the Security Audits panel on this Prism page and treat any CRM or email context as sensitive; the skill is interpretive guidance and should not replace your data-access policies.
SKILL.md
READMESKILL.md - Contact Research
# Contact Signals — Interpretation Guide ## Contact Signal Types ### Activity Signals | Signal | Interpretation | |--------|---------------| | Email open / reply | Actively aware of your org; replied = higher intent | | Meeting attended | Relationship established; note meeting type (demo, QBR, etc.) | | Community post or reply | Has a question, problem, or idea — high engagement signal | | Support ticket opened | Experiencing friction — empathy opportunity | | Documentation page visited | Researching a specific area — note which pages | | Product login | Active user — check frequency and recency | | Event registered/attended | Strong engagement and intent signal | ### Relationship Signals | Signal | Interpretation | |--------|---------------| | No activity in 30+ days | Relationship cooling — gentle check-in appropriate | | No activity in 90+ days | Dormant — may need re-engagement from a different angle | | Consistent activity across multiple channels | Champion or highly engaged user — high-value contact | | Activity spike after dormancy | Something changed — investigate why | ### Job / Professional Signals | Signal | Interpretation | |--------|---------------| | Recent job change (new company) | Warm intro opportunity at new company; relationship may shift at old one | | Promotion at same company | Growing influence — relationship becomes more valuable | | Title change to decision-maker role | Upgrade the relationship strategy | | Company expansion (new hires in their team) | Budget may be available; expansion opportunity | ## Spark Persona Classification - *Champion* — daily user, advocates internally - *Economic Buyer* — holds budget authority, may not use product directly - *Technical Evaluator* — evaluates fit and integration, influences technical decisions - *End User* — primary product user, influences renewal through NPS/feedback - *Gatekeeper* — controls access, must be navigated carefully ## Conversation Starters A strong starter references something specific, shows homework, opens a door without forcing one, and connects to value. - "I saw your question in the community about [topic] — we just released a feature that addresses exactly that. Would it be useful to walk through it?" - "Your team's usage of [feature] jumped last month — curious if you're running into [common blocker] at that stage." --- name: contact-research description: "Research a specific person using Common Room data. Triggers on 'who is [name]', 'look up [email]', 'research [contact]', 'is [name] a warm lead', or any contact-level question." --- # Contact Research Retrieve a comprehensive contact profile from Common Room. Supports lookup by email, social handle, or name + company. Returns enriched data including activity history, Spark, scores, website visits, and CRM fields. ## Step 1: Locate the Contact Common Room supports multiple lookup methods — use whichever the user has provided: | What the user gives | Lookup method | |---------------------|--------------| | Email address | Look up by email (most reliable) | | LinkedIn, Twitter/X, or GitHub handle | Look up by social handle — specify handle type explicitly | | Name + company | Identity resolution by name + org domain; present matches if ambiguous | | Name only | Search by name; if multiple matches, show a brief list and ask the user to confirm | If no match is found, respond: "Common Room doesn't have a record for this person." Do not speculate or fabricate profile data. ## Step 2: Fetch Contact Fields Use the Common Room object catalog to see available field groups and their contents. For full profiles, request all groups. For targeted questions, request only what's relevant. **Key field groups to know about:** - **Scores** — always return as raw values or percentiles, never labels - **Recent activity** — use `Contact Initiated` filter (last 60 days) for their actions, not your team's - **Website visits** — total count + specific pages (last 12 weeks) - **Spark**