Skip to main content
skill CX Codex

icp-deep-scanner — Claude Code skill: data-driven ICP

The icp-deep-scanner skill turns data from connected tools into an Ideal Customer Profile and a persona library. Use it when you need to refresh your ICP or build buyer personas from actual data, not guesses.

MIT 161 installs ★ 440 updated 2026-10-20

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add OneWave-AI/claude-skills --skill icp-deep-scanner -a claude-code
Open on GitHub

What icp-deep-scanner does

The icp-deep-scanner skill scans data from CRM, email, support, reviews, analytics, billing, and databases to produce an Ideal Customer Profile and a reusable persona library. It is read-only by default: no writes or outbound actions happen unless you explicitly ask.

The skill runs in five steps. First it inventories available sources and asks which to scan. Then it pulls firmographics, buyer roles, win/loss reasons, objections, customer language, and economics from each source. Next it writes icp-profile.md with evidence, followed by a personas/ directory with 3–6 archetypes. The final step is a summary, a list of unreachable sources, and the next commands.

If a source needs auth that is not present, the skill adds it to "Sources I could not reach" and moves on. Credentials are taken only from environment variables or the MCP connection itself.

What it helps with

  • build an ICP from real CRM and support data
  • generate a library of buyer personas
  • identify reasons for lost deals
  • extract customer language from reviews
  • feed the customer-panel-of-experts skill

Example prompts for the agent

  • Scan our CRM and support tools, then build the ICP and persona files.
  • Refresh the ICP from the last twelve months of closed-won deals.
  • Generate buyer personas from reviews and billing data.

How to install icp-deep-scanner

1Skills CLI (Vercel)

npx skills add OneWave-AI/claude-skills --skill icp-deep-scanner -a claude-code

2Manually: put the files in place

~/.claude/skills/icp-deep-scanner/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/icp-deep-scanner/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about icp-deep-scanner

How do I install icp-deep-scanner in Claude Code?

Run npx skills add OneWave-AI/claude-skills --skill icp-deep-scanner -a claude-code, then open ~/.claude/skills/icp-deep-scanner/SKILL.md.

What does icp-deep-scanner do?

It scans connected data sources and produces an Ideal Customer Profile plus a persona library. It stays read-only unless you explicitly request changes.

What access does it need?

You need connections to sources like CRM, email, support, reviews, analytics, billing, or a database. Missing auth results in the source being listed as unreachable.

Source text

SKILL.md · MIT
---
name: icp-deep-scanner
description: Deep-scan any tools you connect (CRM, email, support, reviews, analytics, billing, database) to produce a data-grounded Ideal Customer Profile and a reusable persona library. Read-only by default. Use when you need to define or refresh your ICP, build buyer personas from real data instead of guesses, or generate the persona inputs that the customer-panel-of-experts and prospect-panel-simulator skills consume.
tools: Read, Write, Bash, Grep, Glob, WebSearch, WebFetch, Agent
model: inherit
---

# ICP Deep Scanner

Turn the data already sitting in your connected tools into a rigorous, evidence-backed Ideal Customer Profile (ICP) and a library of buyer personas. Most ICPs are invented in a slide deck. This one is reverse-engineered from your actual best customers, your won/lost deals, your support tickets, and your reviews — then written so it can drive real decisions and feed the panel skills.

This skill is the data layer beneath `customer-panel-of-experts`, `prospect-panel-simulator`, and `product-launch-war-room`. Run it first; those skills read the persona library it writes.

## Operating principles (read first)

- **Read-only by default.** You may query and read connected sources. You must NOT create, update, delete, send, or move anything in any connected tool unless the user explicitly asks in this session. Before any write or outbound action, stop and confirm.
- **Least data necessary.** Pull aggregates and representative samples, not entire databases. You are building a profile, not exfiltrating a CRM.
- **PII minimization.** Persona artifacts are archetypes, not dossiers. Do not write real customer names, emails, phone numbers, or account IDs into the output files. Reference real records only as anonymized counts and quotes (quotes scrubbed of identifying detail).
- **Secrets via environment only.** Never read, print, or write credentials. Assume tokens live in environment variables (e.g. `$SUPABASE_TOKEN`, `$OPENAI_API_KEY`) or in the MCP connection itself. If a source needs auth that isn't present, list it under "Sources I could not reach" and continue.
- **Cite the evidence.** Every claim in the ICP must trace to a source. "Buyers are mostly ops leaders" is worthless; "14 of the last 20 closed-won champions held an Operations title (CRM, trailing 12 mo)" is usable.

## Step 1 — Inventory connectable sources

Ask the user which tools to scan, or detect what's available. Map each to what it tells you:

| Source (examples) | What to extract | How to reach it |
|---|---|---|
| CRM (HubSpot, Salesforce, internal) | Closed-won vs closed-lost firmographics, titles of champions/buyers, deal size, sales cycle, win reasons | MCP connector or read-only API |
| Email / calendar | Who actually engages, meeting cadence, recurring objection language | Gmail/Calendar MCP, read-only |
| Support / tickets / chat | Top pain themes, words customers use, where they get stuck | Intercom/Zendesk export, logs |
| Reviews (G2, Capterra, Trustpilot, App Store) | Verbatim value language, switching triggers, deal-breakers | WebFetch / `customer-review-aggregator` |
| Product analytics (GA4, Clarity, Mixpanel) | Activation paths, who sticks, drop-off points | Analytics MCP / API |
| Billing (Stripe, Mercury) | Real revenue concentration, expansion vs churn by segment | Read-only API |
| Database (Supabase/Postgres) | Ground-truth usage and cohort behavior | Read-only SQL via `$SUPABASE_TOKEN` |
| Public web | Firmographic enrichment, market sizing, competitor positioning | WebSearch / WebFetch |

Present the list, mark which are reachable now, and confirm scope before scanning. For a wide scan across many sources, dispatch parallel read-only sub-agents (one per source) and merge their findings — see `/agent-army`.

## Step 2 — Extract signal from each source

For each reachable source, pull:
- **Firmographics** — industry/vertical, company size, geography, business model, tech stack.
- **Who buys** — economic buyer, champion, blocker, end user (titles + seniority, from real deals).
- **Why they buy** — the trigger event, the job-to-be-done, the alternative they abandoned.
- **Why they don't** — top closed-lost reasons, top objections, top churn reasons.
- **Language** — the exact words customers use (mine reviews and tickets; do not paraphrase into marketing-speak).
- **Economics** — ACV, CAC signals, sales-cycle length, expansion behavior, concentration risk.

Record sample sizes and date ranges for everything. Flag anything based on fewer than ~5 data points as "thin signal."

## Step 3 — Synthesize the ICP

Write `icp-profile.md`:

```markdown
# Ideal Customer Profile — {COMPANY}
Generated: {timestamp} · Sources scanned: {list} · Confidence: {High/Med/Low}

## The ICP in one sentence
{Vertical} companies of {size} who {trigger}, evaluated against {alternative}, where the champion is a {title} and the economic buyer is a {title}.

## Firmographic fit (with evidence)
- Industry: ... (evidence: N of M closed-won)
- Size: ...
- Geography / model / stack: ...

## Anti-ICP — who to disqualify
- {Segment} — closes slow, churns fast, low ACV (evidence)

## Buying committee
- Economic buyer · Champion · Blocker · End user — each with real titles + what they care about

## Triggers & jobs-to-be-done
## Top buy reasons / top no-buy reasons (ranked, with counts)
## The customer's own language (verbatim, scrubbed)
## Economics — ACV, cycle, expansion, concentration risk
## Confidence & gaps — what's thin, what to instrument next
```

## Step 4 — Build the persona library

Write `personas/` — one file per persona (3–6 personas: typically the champion, the economic buyer, the blocker, and 1–2 key end users or segment variants). Each persona file is structured so the panel skills can load it directly:

```markdown
---
persona_id: ops-leader-champion
role: Champion
archetype: "VP of Operations at a 50–200 person services firm"
based_on: "12 closed-won champions, CRM trailing 12 mo"
---
# {Archetype name}
- Goals / success metrics:
- Pains (verbatim language):
- What earns trust / what triggers skepticism:
- Buying authority & budget reality:
- Objections they raise (real, from lost deals):
- How they talk (tone, vocabulary, 2–3 scrubbed quotes):
- What would make them a hard NO:
```

Also write `personas/index.md` listing every persona, its role in the committee, and its evidence base.

## Step 5 — Handoff

End with:
- A 5-line ICP summary the user can paste anywhere.
- "Sources I could not reach" and what auth/access would unlock them.
- "Confidence ledger" — which conclusions are strong vs. thin.
- The exact command to run next: `customer-panel-of-experts` (debate a decision with these personas) or `prospect-panel-simulator` (pressure-test a pitch against them).

## Guardrails recap
Read-only unless told otherwise · no secrets in output · personas are archetypes, never dossiers · every claim cites its source and sample size · thin signal is labeled, not hidden.

© OneWave-AI · MIT · OneWave-AI/claude-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set185

The whole set →
claude-landing-composer claude-landing-composer builds custom Next.js landing pages with Tailwind v4 and Motion animations. Useful when you need ready-to-ship marketing sections without typical AI templates. CX Codex +1 178installs claude-design-system-architect claude-design-system-architect is a Claude Code skill that turns a brand brief or existing site into reusable design tokens, component specs, and project files. It defines shared rules for a new product or inconsistent UI. CX Codex +1 172installs prospect-panel-simulator prospect-panel-simulator is a skill that simulates buyer reactions to sales and marketing materials before they go live, surfacing objections and likely next actions. CX Codex +1 164installs customer-panel-of-experts customer-panel-of-experts assembles a panel of buyer personas to debate product changes, price hikes, or launches before committing resources. CX Codex +1 162installs product-launch-war-room product-launch-war-room is a Claude Code skill that tests a launch plan against expert and customer viewpoints, then returns a decision and rollout steps. Run it for a product launch, repricing, or repositioning. CX Codex +1 159installs pricing-change-strategist pricing-change-strategist plans a price increase or tier restructure with churn modeling. CX Codex +1 158installs hyperframes-sales-demo-builder hyperframes-sales-demo-builder — a skill for Claude Code, Codex, Cursor and other platforms that builds a prospect-specific demo video in HyperFrames. CX Codex +1 157installs before-you-build The before-you-build skill identifies the main risk in an idea and suggests a small test before implementation starts. Use it to assess a product, feature, MVP, agent, or automation. CX Codex +1 130installs

Project sponsors

Companies that keep this analytics open