Artemis Vector
The Lead Scoring Agent consulting agent — guides your diagnostic, build & support
A Claude-orchestrated implementation package that builds your full lead scoring stack: fit model from your ICP, intent model from enrichment + visitor signals, threshold tuning against your real conversion data, BDR queue routing, and decay scheduling. Includes ongoing routines that re-tune thresholds monthly so the score does not drift as your funnel changes.
What is Artemis Vector?
Builds a two-model lead score (firmographic fit + behavioral intent) BDRs actually trust. The Artemis Lead Scoring skill is a Claude-orchestrated implementation package that builds your full scoring stack: a Pain-First fit model from your ICP, a behavioral intent model from enrichment + visitor signals, threshold tuning validated against your real conversion data, BDR queue routing, and decay scheduling. Includes monthly threshold-tuning and quarterly fit-model refresh routines so the score does not drift.
What this solves
Unqualified Lead Volume
Fit + intent scoring your BDRs actually trust
Assumed stack (adapts to yours)
HubSpot or Salesforce + enrichment (Amplemarket or Apollo) + Warmly for intent
This is a consulting engagement that happens to cost $349
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 $40K consulting retainer.
- 1
Discovery
Pull your closed-won + closed-lost data. Map current ICP + scoring (if any) + conversion baseline.
- 2
Fit Model
Build the firmographic + technographic fit score using the Pain-First framework. Tested against your real wins.
- 3
Intent Model
Layer in behavioral signals: visitor identification, content engagement, sequence opens, ICP-match recency.
- 4
Threshold + Routing
Combine scores, set thresholds against your conversion data, and wire BDR queue rules + handoff SLAs.
- 5
Decay + Refresh
Apply decay schedules so stale leads do not poison the queue. Includes the LeadScoreDecayExplained framework.
- 6
Install Routines
Monthly threshold-tuning routine and quarterly fit-model refresh routine so the score stays honest as your funnel evolves.
81% of B2B SaaS companies between $1M-$100M ARR have lead scoring tools configured at the field level but no operational model that routes leads to the right rep in under 5 minutes. Based on diagnostics of 127 companies in 2024-2026: 103/127 (81%) had a lead scoring tool installed (HubSpot Lead Scoring, Salesforce Einstein, or third-party) with property fields configured, but no documented model translating scores into routing actions. Median time from lead creation to first rep contact was 42 hours; the subset with an operational scoring model (n=23) routed in under 8 minutes on average.
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 (drops into ~/.claude/skills/)
- Specialized sub-agents (CRM mapper, sequence writer)
- Routines folder — weekly + monthly + quarterly checks
- CronCreate-ready scheduled prompts
- All template files used by the Chat variant
What's actually in the .zip
You're buying a downloadable bundle, not a service. Here's the exact file structure.
lead-scoring-skill-v1/ ├── README.md # Buyer install picker (Chat vs Code) ├── shared/ │ ├── playbook.md # Source-of-truth implementation guide │ ├── partner-stack.md # Artemis partner stack positioning │ └── templates/ │ ├── README.md # Template inventory + scaffolding │ └── (skill-specific templates) ├── claude-chat/ │ └── system-prompt.md # Paste into a Claude Project ├── claude-code/ │ ├── SKILL.md # Drops into ~/.claude/skills/lead-scoring/ │ ├── agents/ │ │ └── (2-3 sub-agent .md files) │ └── routines/ │ └── (3 CronCreate-ready routine .md files) └── LICENSE.txt # Single-user license · single install · updates via Artemis membership
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 unqualified lead volume?
One-time purchase — yours to keep, single install. Always-latest updates, re-tuned as tools, models, and plays change, come with Artemis membership (Aegis).