Warmly Visitor Intelligence — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Warmly Visitor Intelligence (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Warmly identifies anonymous website visitors by IP-to-company reverse lookup, third-party data overlays, and (where consented) contact-level deanonymization. For an MSP or B2B sales team, the practical outputs are:
That is the raw material for prioritizing outreach: warm > cold, deep engagement > a single bounce, target ICP > unrelated traffic.
| Task | Tool |
|---|---|
| "Who visited the site today?" | list_warm_visitors |
| "Which companies are showing pipeline-grade engagement this week?" | list_warm_accounts |
| "Are we about to run out of identifications?" | get_credits_remaining |
list_warm_visitors is the right starting point when you want contact-level signal (a named person you can email/call). list_warm_accounts is right when you want to triage at the account level (which companies are worth a salesperson's time at all).
list_warm_accounts to pull current account-level engagement.list_warm_visitors filtered to those companies to pull individual contact-level signal.Each visitor/account in Warmly's response includes intersection flags indicating whether the company or contact already exists in your CRM. Use this to route:
Pair the Warmly tools with the HubSpot, ConnectWise, or Autotask plugins to do the lookups in-place.
The raw payload exposes pageviews and session timing — derive a simple score (pageviews * recency_weight + session_minutes) rather than asking Claude to eyeball "high engagement." Surface only the top decile to outreach queues so SDR attention isn't diluted.
Before launching a workflow that depends on Warmly identifications scaling up (e.g. "enrich every visitor for the next 30 days"), call get_credits_remaining and confirm the balance covers expected volume. Identifications silently stop when the credit budget is exhausted — already-identified visitors stay visible, but new ones don't appear.
For an MSP-specific motion, the practical combinations are:
list_warm_accounts filtered to visits on the security/M365/Azure audit pages → SDR sequence offering a free audit assessment.Run these as repeatable workflows rather than one-off lookups — the value of visitor identification compounds when it consistently feeds the outreach engine.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.