ICP Score and Route Skill

A new lead lands. Before it hits the AE, this skill scores it against your ICP, verifies the contacts, and tells you exactly where it should go — and why.

Overview

The ICP Score and Route Skill takes any lead or account — inbound form, free trial, SDR-sourced, or imported list — scores it against your ICP, verifies the key contacts via Lusha, and returns a routing recommendation with the reasoning behind it. AE, SDR, or nurture — every decision is grounded in live data, not gut feel.

Give it a company name or domain and your ICP criteria. It pulls firmographics, buying signals, and verified contacts via the Lusha in Claude connector, scores the account against your criteria, and returns a routing decision with a confidence level and the specific data points that drove it. No black-box scoring. No unexplained grades.

The result is a routing decision your team can trust — with every data point visible, every assumption stated, and every contact verified before the handoff.

What it does

  • ICP scoring — scores any lead or account against your defined ICP criteria: industry, size, geography, tech stack, funding stage, and buying signals.
  • Live contact verification — verifies the key contacts at the account via Lusha before the routing decision is made. No routing to a dead contact.
  • Routing recommendation — returns AE, SDR, or nurture with a confidence level and the specific data points that drove the decision.
  • Transparent reasoning — every scoring decision shows which criteria were met, which were missed, and which were uncertain. No black-box grades.
  • Bulk scoring — run it across a full inbound list or imported account list in one pass. Every lead scored and routed before it hits the queue.

Use cases

Inbound lead routing

A new lead comes in through a form or free trial. Before it hits the AE queue, run the skill to score it against your ICP and return a routing recommendation with the reasoning. The AE gets a qualified lead with context — not a raw form fill.

Pre-campaign list scoring

Before a campaign goes out, run the skill across the full target list. Every account gets an ICP score and a routing recommendation. The team works the highest-scoring accounts first — not the ones that happened to be at the top of the spreadsheet.

SDR-to-AE handoff quality check

Before an SDR passes a lead to an AE, run the skill to confirm the account meets the ICP threshold for handoff. If it doesn’t, it goes back to nurture with the specific gaps flagged — so the AE queue stays clean and the SDR knows exactly what needs to change.

Skill definition

The instructions Claude uses to run this skill. Copy it into a .md file in your Claude Code skills folder, or paste it into a Claude project as a custom instruction.

Example outputs in this skill are illustrative — they reflect the structure, fields, and format of real Lusha connector output, but were not pulled from a live session. Run the skill with your own data and connectors to see live results.

---
name: icp-score-and-route-skill
description: >
  Score any lead or account against your ICP criteria, verify key
  contacts via Lusha, and return a routing recommendation — AE,
  SDR, or nurture — with a confidence level and the specific data
  points that drove the decision. Runs on a single lead or across
  a full list in one pass.
connectors:
  required: lusha
  optional: crm, slack
campus_url: https://www.lusha.com/campus/plays/icp-score-and-route-skill/
category: Skills
---

# ICP Score and Route Skill

Score any lead or account against a defined ICP. Verify key
contacts via Lusha. Return a routing recommendation with
transparent reasoning — no black-box grades, no unexplained
decisions.

## Input

The user will provide via $ARGUMENTS:

- Lead or account list (required) — one or more company names,
  domains, or Lusha company IDs.
- ICP criteria (required) — the scoring dimensions to use.
  Examples:
  - Industry: SaaS, FinTech, Healthcare
  - Employee count: 200–2,000
  - Geography: North America, EMEA
  - Funding stage: Series A–C
  - Tech stack: Salesforce, HubSpot, Outreach
  - Buying signals: intent on your category, score 60+
  If ICP criteria are not supplied, ask once. If declined,
  use general B2B SaaS ICP defaults and state that assumption.
- Routing thresholds (optional) — what score maps to which
  route. Default:
  - 80–100: AE
  - 50–79: SDR
  - Below 50: nurture
  Accept custom thresholds if supplied.

## Workflow

1. Anchor on the ICP.
   Read the ICP criteria and routing thresholds from $ARGUMENTS.
   Restate them at the top of the output so the reader knows
   exactly what the scoring was based on. If defaults were used,
   flag them clearly.

2. Resolve accounts via Lusha.
   For each lead or account:
   - If a Lusha company ID is supplied, use it directly.
   - Otherwise resolve via companies_search using the name
     or domain.
   - Flag any accounts that could not be resolved and skip them.

3. Pull data in parallel.
   For each resolved account, run these calls concurrently:
   - Firmographics: industry, employee count, revenue range,
     HQ geography, funding stage.
   - Tech stack signals: technologies in use relevant to ICP.
   - Buying signals: intent topics, signal score 60+.
   - Key contacts: most senior contact in the primary buying
     function. Verify email and direct dial via Lusha.

4. Score against ICP criteria.
   For each scoring dimension, return one of:
   - Met — data confirms the criterion is satisfied
   - Missed — data confirms the criterion is not satisfied
   - Uncertain — data is insufficient to confirm either way

   Calculate an overall ICP score (0–100) based on the
   weighted criteria. Weight buying signals and firmographic
   fit highest. Tech stack and geography as secondary signals.

   Show the score breakdown — not just the total. Every
   dimension visible, every gap flagged.

5. Apply routing thresholds.
   Map the ICP score to a routing recommendation:
   - AE: account meets ICP threshold, verified contact found,
     buying signal present. High-confidence handoff.
   - SDR: account meets partial ICP, or ICP met but no buying
     signal. Needs qualification before AE handoff.
   - Nurture: account misses ICP on core dimensions. Not ready
     for outreach. Flag the specific gaps.

   State the confidence level: High / Medium / Low.
   High: 3+ criteria confirmed, verified contact found.
   Medium: mixed signals, some criteria uncertain.
   Low: insufficient data or core criteria missed.

6. Return the routing output.
   One record per lead or account. Lead with the routing
   decision, follow with the score breakdown and reasoning.
   End with the verified contact details for AE and SDR routes.

## Output Format

### ICP Score and Route

ICP criteria used: [list the criteria and thresholds]
Routing thresholds: AE [score], SDR [score], Nurture [score]
Leads scored: [n]

---

For each lead or account:

**[Company Name]**
Routing: [AE / SDR / Nurture] — Confidence: [High / Medium / Low]
ICP Score: [0–100]

| Criterion | Value Found | Status |
|---|---|---|
| Industry | | Met / Missed / Uncertain |
| Employee count | | Met / Missed / Uncertain |
| Geography | | Met / Missed / Uncertain |
| Funding stage | | Met / Missed / Uncertain |
| Tech stack | | Met / Missed / Uncertain |
| Buying signal | | Met / Missed / Uncertain |

**Routing rationale:** [2–3 sentences explaining the decision —
which criteria drove it, which gaps exist, and what needs to
happen before the routing changes.]

**Verified contact:**
- Name: [initials only — e.g. J.K.]
- Title:
- Email: [domain only — j.k@[company].com]
- Direct dial: [masked — +1 415 555 ••••]
- Contact confirmed live via Lusha connector, [date]

*For nurture routes: omit verified contact. Return the specific
ICP gaps that need to close before re-scoring.*

---

### Unresolved Accounts

Accounts that could not be matched in Lusha:
[list of account names or domains]

Recommend verifying company name or domain and re-running.

---
Built by: Lusha
Tools: Claude, Lusha
Type: Skill

FAQ

  • Do I need anything beyond Lusha in Claude?

    No. The skill runs entirely through the Lusha in Claude connector. Connect it once in Claude settings. Optional: connect your CRM if you want the skill to pull existing engagement history and deal context before scoring each account.

  • How do I define my ICP criteria?

    Paste them directly into the chat when you run the skill — industry, employee count, geography, funding stage, tech stack, and any buying signal thresholds. If you run this regularly, save your ICP criteria once in a Claude Project as a custom instruction. The skill reads them automatically every time without re-pasting.

  • How is this different from the ICP Scoring Table play?

    The ICP Scoring Table play builds a scored table from a list. This skill goes further — it verifies contacts, returns a routing recommendation with a confidence level, and shows the reasoning behind every decision. It’s built for the routing decision, not just the score.

  • Can I change the routing thresholds?

    Yes. The defaults are AE at 80+, SDR at 50–79, and nurture below 50. Paste your own thresholds when you run the skill and it applies them to every account in the batch. Useful when your AE qualification bar is higher or when you’re running a specific campaign with different routing rules.

  • What happens when data is missing for a scoring criterion?

    The skill flags it as Uncertain rather than guessing. The routing decision is made on the data that exists, and the confidence level reflects how complete the picture is. A Low confidence routing still gives you a recommendation — it just tells you exactly what data would change it.

Related Plays

Ready to run this?

Connect once, run anywhere. Works in Claude, ChatGPT, n8n, Clay, or any agent connected to Lusha.

Get free access Read the Docs