Artemis Mirage
The Visitor Deanonymization ROI Agent consulting agent — guides your diagnostic, build & support
The conversational version of the Website Visitor ROI Calculator, run by a senior GTM advisor in Claude. It walks you through your monthly traffic, ICP-fit, deal size, and current identification setup, benchmarks each number against the Artemis 127-audit dataset, then quantifies — with the math shown — how much pipeline your anonymous visitors are worth and how much you are leaving on the table. It ends by mapping the fix to the paid Visitor Deanonymization agent and the right partner tool.
What is Artemis Mirage?
A free, defensible dollar estimate of the pipeline hiding in your anonymous website traffic, and the exact agent and tool that captures it. The Artemis Visitor Deanonymization ROI Agent is the free Claude-run version of the Website Visitor ROI Calculator. It benchmarks your traffic volume, source mix, ICP-fit, and deal size against the Artemis 127-audit dataset, runs an honest identification-to-pipeline funnel with the math shown, and quantifies how much pipeline your anonymous visitors are worth per year. It then maps the leak to the paid Visitor Deanonymization agent and the right partner tool — the deep, conversational version of the calculator.
What this solves
Anonymous Visitors
Quantify the pipeline hiding in your anonymous traffic — free, in Claude
Assumed stack (adapts to yours)
Any B2B website + GA/analytics; Warmly or RB2B optional (the agent recommends if you have none)
Quantify your opportunity first
Run the calculator to estimate what this skill could recover.
See where this fits in your funnel
The Agent Field Guide maps all 19 agents to the stage they fix, so you know what to run before and after this one.
This is a consulting engagement that happens to cost Free
When you run this agent in Claude, you don't get a playbook execution. You get a senior GTM advisor walking you through the build — diagnosing your stack one question at a time, branching to your reality, pasting screenshots back and forth, naming gotchas before you hit them, and surfacing the other things in your stack that need automation along the way. You learn the system by building it, with support at every step — the opposite of a one-way course you watch, then implement alone.
Discovery-first
Claude opens with discovery — one question at a time — before recommending a single tool. Your stack, stage, and constraints drive every downstream call.
Walkthrough, not handoff
Paste your CRM config back. Take a screenshot of your routing rule. Run the query and tell Claude what came back. Every phase has a paste-back moment.
Running observations
Claude notices the other broken or manual systems in your stack as you build and surfaces them at session end — a "what I'd automate next" list, prioritized.
It doesn't just advise — it gets you to the finish
Your agent runs the build like a chief of staff — tracking every task, keeping you on schedule, surfacing blockers, and holding you accountable until the system is live. The part a course can't do.
Progress you can see
A live progress bar every session — you always know exactly what's done, what's next, and how much is left before the system is live.
It schedules the work
Connect Google Calendar, Slack, or Gmail and it puts milestones on your calendar, posts the day's task to Slack, and emails weekly recaps — so the build keeps moving between sessions.
Blockers surfaced early
It maps dependencies and timeline risks up front — "you'll need HubSpot admin by Phase 3" — before they stall you, not after.
Built to finish
Milestone unlocks and a "system shipped" finish line keep the momentum. Most builds stall halfway. This one is engineered to get done.
How the engagement runs
Claude walks you through these phases — discovery, build, verification, closing summary — the same way a senior GTM advisor would on a $60K consulting retainer.
- 1
Traffic Profile
Monthly visitors, traffic-source mix (US vs international, paid vs organic), and how much is plausibly ICP-fit. The mix decides which identification rate benchmark applies and whether Warmly, RB2B, or a hybrid is the right tool.
- 2
Deal & Funnel Inputs
Average deal size (ACV), current form-fill rate, and — if you have it — your meeting-to-opportunity and win rate. For anything you don't know, the advisor offers the Artemis benchmark and labels it as an assumption.
- 3
Benchmark & Quantify
Runs the de-anon funnel against the n=127 dataset: identification rate (median 22% Warmly company-level, 38% RB2B US contact-level), high-intent share, contacts per account, and an honest meeting-to-pipeline conversion — so the dollar figure is pipeline, not a meeting count dressed up as revenue.
- 4
Reality-Check the Number
Shows the one-line calculation, separates upper-bound from expected pipeline, and stress-tests it against your form-fill rate and ICP-match so the figure survives scrutiny from your CFO, not just your curiosity.
- 5
Map the Fix
Names the leak in dollars per year with cost-of-delay, then routes to the paid Visitor Deanonymization agent (Artemis Beacon, $349) that installs the tool, tunes ICP filters, and wires the CRM + Slack workflow — plus the partner platform that powers it, with affiliate disclosure.
Across 127 audited B2B SaaS companies, the median form-fill rate was 1.8%, leaving 98.2% of website traffic anonymous by default; of those with a deanonymization tool installed, the median company-level identification rate was 22% (Warmly) and 38% at the contact level for US-only traffic (RB2B). Based on Artemis GTM diagnostics of 127 B2B SaaS companies, 2024-2026, cross-referenced with aggregated benchmark data published by Warmly, RB2B, and Leadfeeder. The 1.8% median form-fill rate means the overwhelming majority of in-market research happens anonymously; identification rate (not the anonymous-traffic rate) is the lever that converts that traffic into routable pipeline.
What's in the bundle
Dual-format. Same playbook, your choice of interface.
For Claude Chat
Upload the agent as a Skill at claude.ai/customize/skills — one upload, no CLI. Requires a paid Claude plan (Pro, Max, Team, or Enterprise); custom Skills aren't available on the free plan.
- Ready-to-upload skill (SKILL.md + resources)
- Advisor persona + full playbook bundled in
- Templates the agent fills in for your stack
- Needs Claude Pro, Max, Team, or Enterprise
For Claude Code
Full skill bundle with sub-agents and ongoing routines. Wires the system into your local environment for long-term operation.
- SKILL.md — installs into ~/.claude/skills/<agent>-agent/
- Specialized sub-agents (CRM mapper, sequence writer)
- Routines folder — weekly + monthly + quarterly checks
- Schedulable as Claude Code cloud routines (/schedule)
- All template files used by the Chat variant
What's actually in the .zip
You're buying a downloadable bundle, not a service. This file list comes straight from the build that produces your download.
deanonymization-roi-agent-skill-v1.zip ├── SKILL.md # The agent — at the zip root, loads everything beside it ├── advisor-persona.md # White-glove advisor persona (keystone) ├── accountability-engine.md # Tracker, progress + closing-summary layer ├── partner-stack.md # Artemis partner stack positioning ├── claude-setup.md # Claude settings guide for best output ├── tool-connections.md # Optional MCP connections for your stack ├── playbook.md # Source-of-truth implementation guide ├── templates/ # Templates the agent fills in for your stack ├── agents/ # Specialized sub-agent prompts ├── routines/ # Recurring check-in routine prompts ├── README.md # Install walkthrough (Chat + Code) └── LICENSE.txt # Single-user license · single install
Flat layout — SKILL.md sits at the zip root. Upload the zip as-is on claude.ai, or unzip it into ~/.claude/skills/deanonymization-roi-agent-agent/ for Claude Code. Your purchase also includes the OpenAI Codex edition of the same agent.
Format
.zip · markdown
License
Single-user commercial
Updates
Via membership
How partner recommendations work
This Skill Package recommends tools from Artemis GTM partner companies (Warmly, Amplemarket, Maildoso, Attio, Sybill, Attention, Apollo, RB2B — depending on the skill). When you click through and sign up via the in-skill referral links, Artemis GTM may earn a commission, at no extra cost to you.
We recommend these tools based on validation across 127+ B2B SaaS audits, not because they pay us. The skill is built to adapt to your existing stack — if a tool you have is working, you keep it.
For current partner pricing and feature detail, the skill defers to each partner's website. Claude is explicitly instructed not to invent specifics — when a buyer asks "how much does Tool X cost?", Claude refers to the partner's homepage rather than quoting a potentially stale number.
Built on the same playbook our consulting uses
Read the source content this skill is built from. Everything in the bundle is the operational version of these guides.
Frequently Asked Questions
Ready to ship anonymous visitors?
One-time purchase — yours to keep, single install. Always-latest updates, re-tuned as tools, models, and plays change, come with Artemis membership (Aegis).