スキル一覧に戻る

icp-matching

guia-matthieu
更新日 2 days ago
2 閲覧
111
20
111
GitHubで表示
その他ai

について

このスキルは、Claudeが企業情報、技術環境、行動パターンの基準を用いて、理想顧客プロファイルに照らして見込み客を評価・選別することを可能にします。リードスコアリングモデルの構築、インバウンドリードの選別、アウトバウンド対象アカウントの優先順位付けに活用されます。本スキルはICPフレームワークを構造化し、ユーザーが定義した基準に基づいてスコアを算出します。

クイックインストール

Claude Code

推奨
メイン
npx skills add guia-matthieu/clawfu-skills -a claude-code
プラグインコマンド代替
/plugin add https://github.com/guia-matthieu/clawfu-skills
Git クローン代替
git clone https://github.com/guia-matthieu/clawfu-skills.git ~/.claude/skills/icp-matching

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

ICP Matching

Systematically evaluate prospects against your Ideal Customer Profile to prioritize high-fit accounts and improve SDR efficiency.

When to Use This Skill

  • Building lead scoring models
  • Qualifying inbound leads
  • Prioritizing outbound target accounts
  • Refining ICP definitions
  • Training SDRs on qualification

Methodology Foundation

Based on TOPO ICP Framework and Gartner B2B Buying Research, combining:

  • Firmographic fit (company attributes)
  • Technographic fit (tech stack)
  • Behavioral signals (intent data)
  • Persona fit (contact attributes)

What Claude Does vs What You Decide

Claude DoesYou Decide
Structures ICP frameworkICP criteria values
Scores prospects against ICPPass/fail thresholds
Identifies fit gapsPrioritization rules
Suggests disqualificationException handling
Ranks prospect listsTerritory assignments

Instructions

Step 1: Define ICP Dimensions

Firmographic Criteria:

AttributeIdealAcceptableDisqualify
Company Size100-100050-2000<25 or >5000
Revenue$10M-$500M$5M-$1B<$2M
IndustrySaaS, TechProfessional ServicesGovernment
GeographyUS, CanadaUK, EUAPAC
Growth StageSeries A-CSeed, Series D+Pre-seed

Technographic Criteria:

AttributeIdealAcceptableDisqualify
CRMSalesforceHubSpotNone
Tech StackModernMixedLegacy only
CompetitorsNone installedEvaluatingLocked in

Persona Criteria:

AttributeIdealAcceptableDisqualify
TitleVP/DirectorManagerCoordinator
DepartmentSales, MarketingRevOpsIT
Decision PowerBudget authorityInfluencerUser only

Step 2: Weight and Score

Scoring Model:

ICP Score =
  (Firmographic × 40%) +
  (Technographic × 30%) +
  (Persona × 30%)

Each dimension: 0-100 points

Score Interpretation:

ScoreFitAction
80-100ExcellentPrioritize immediately
60-79GoodStandard outreach
40-59FairNurture, low priority
<40PoorDisqualify

Step 3: Apply to Prospects

For each prospect:

  1. Gather available data
  2. Score each dimension
  3. Calculate weighted score
  4. Classify and prioritize

Examples

Example 1: ICP Definition

Output:

## Ideal Customer Profile: B2B Sales Tech Company

### Tier 1 (Excellent Fit - 80-100)
**These are your ideal targets. Prioritize always.**

**Company:**
- Size: 100-500 employees
- Revenue: $20M-$200M ARR
- Stage: Series B or C funded
- Industry: B2B SaaS
- Growth: 30%+ YoY
- Location: US/Canada

**Technology:**
- CRM: Salesforce
- Stack: Modern (cloud-native)
- Current solution: None or legacy competitor

**Buyer:**
- Title: VP Sales, CRO, Head of Sales
- Reports to: CEO/COO
- Budget: >$50K annually

---

### Tier 2 (Good Fit - 60-79)
**Worth pursuing with standard effort.**

**Company:**
- Size: 50-100 OR 500-1000 employees
- Revenue: $10M-$20M OR $200M-$500M
- Stage: Series A or D
- Industry: B2B Tech (not pure SaaS)
- Location: UK, EU

**Technology:**
- CRM: HubSpot
- Stack: Mix of modern/legacy
- Current solution: Considering change

**Buyer:**
- Title: Director of Sales Ops
- Reports to: VP Sales
- Budget: $25K-$50K annually

---

### Tier 3 (Fair Fit - 40-59)
**Nurture only. Don't prioritize.**

**Company:**
- Size: 25-50 OR 1000-2000 employees
- Revenue: $5M-$10M
- Stage: Seed
- Industry: Professional services

**Buyer:**
- Title: Sales Manager
- Budget: <$25K

---

### Disqualified (Score <40)
**Do not pursue. Auto-reject.**

- Company size <25 employees
- Revenue <$2M
- Industry: Government, Education, Non-profit
- Geography: APAC, LATAM (no support)
- Competitor locked in (multi-year contract)
- No CRM in use
- Title: Individual contributor

Example 2: Prospect Scoring

Input:

Score this prospect:

Company: GrowthTech Inc
Employees: 280
Revenue: $45M (estimated)
Industry: B2B SaaS
Founded: 2019
Location: Austin, TX
Recent news: Series B ($30M) in January

Tech Stack:
- CRM: Salesforce Enterprise
- Marketing: Marketo
- No sales engagement tool

Contact: Jennifer Wu
Title: VP of Revenue Operations
LinkedIn: Active, posts about sales productivity
Previous company: Used our competitor

Output:

## ICP Match: GrowthTech Inc

### Overall Score: 92/100 ⭐ EXCELLENT FIT

---

### Firmographic Score: 95/100

| Criteria | Finding | Points |
|----------|---------|--------|
| Size (280 emp) | ✅ Ideal (100-500) | 20/20 |
| Revenue ($45M) | ✅ Ideal ($20-200M) | 20/20 |
| Industry (B2B SaaS) | ✅ Ideal | 20/20 |
| Stage (Series B) | ✅ Ideal | 20/20 |
| Location (US) | ✅ Ideal | 15/15 |
| **Subtotal** | | **95/100** |

### Technographic Score: 90/100

| Criteria | Finding | Points |
|----------|---------|--------|
| CRM (Salesforce) | ✅ Ideal | 35/35 |
| Stack (Modern) | ✅ Marketo + SF | 25/25 |
| Competition | ✅ None installed | 30/30 |
| **Subtotal** | | **90/100** |

### Persona Score: 92/100

| Criteria | Finding | Points |
|----------|---------|--------|
| Title (VP RevOps) | ✅ Decision maker | 35/35 |
| Department | ✅ Revenue Operations | 25/25 |
| Activity | ✅ Active on LinkedIn | 15/20 |
| Previous | ✅ Knows competitor | 15/15 |
| **Subtotal** | | **92/100** |

---

### Weighted Total

(95 × 0.40) + (90 × 0.30) + (92 × 0.30) = 38 + 27 + 27.6 = 92.6 → 92/100


---

### Match Summary

**🎯 Tier 1: Excellent Fit**

**Strengths:**
1. Perfect company size/stage/industry
2. Salesforce user (easy integration story)
3. VP RevOps = ideal buyer persona
4. Recent funding = budget available
5. No competitor installed = greenfield

**Conversation Angles:**
1. "Congrats on Series B! How is that affecting your sales team scale?"
2. "I noticed you're not using a sales engagement tool yet—most RevOps leaders at your stage are building that out now."
3. "Given your Salesforce/Marketo stack, our integration would be seamless."

**Risk Factors:**
- None identified

**Priority: Immediate outreach**
Add to top of SDR queue. High-value, high-probability.

Skill Boundaries

What This Skill Does Well

  • Structuring ICP frameworks
  • Scoring prospects systematically
  • Identifying fit gaps
  • Prioritizing outreach

What This Skill Cannot Do

  • Access company databases
  • Verify data accuracy
  • Know internal buying dynamics
  • Predict conversion likelihood

When to Escalate to Human

  • ICP definition changes
  • Borderline accounts
  • Strategic target accounts
  • Exception requests

References

  • TOPO ICP Framework
  • Gartner B2B Buying Research
  • SalesLoft ICP Best Practices
  • Outreach.io Target Account Model

Related Skills

  • lead-scoring - RevOps scoring model
  • signal-monitoring - Intent data
  • prospecting-research - Deep account research

Skill Metadata

  • Domain: SDR Automation
  • Complexity: Intermediate
  • Mode: centaur
  • Time to Value: 2 hours for ICP, 5 min per prospect
  • Prerequisites: ICP criteria definition

GitHub リポジトリ

guia-matthieu/clawfu-skills
パス: skills/sdr-automation/icp-matching
0
ai-skillsanthropicclaude-codeclaude-skillsmarketingmcp-server

関連スキル

llamaguard

その他

LlamaGuardは、暴力やヘイトスピーチなど6つの安全性カテゴリーにおいて、LLMの入力と出力をモデレートするMetaの70-80億パラメータモデルです。94〜95%の精度を提供し、vLLM、Hugging Face、Amazon SageMakerを使用してデプロイ可能です。このスキルを使用して、AIアプリケーションにコンテンツフィルタリングと安全策を簡単に統合できます。

スキルを見る

cost-optimization

その他

このClaudeスキルは、リソースの適正サイジング、タグ付け戦略、支出分析を通じて、開発者がクラウドコストを最適化することを支援します。AWS、Azure、GCPにわたるクラウド支出の削減とコストガバナンスの実施のためのフレームワークを提供します。インフラコストの分析、リソースの適正サイジング、または予算制約への対応が必要な際にご利用ください。

スキルを見る

quantizing-models-bitsandbytes

その他

このスキルは、bitsandbytesを使用してLLMを8ビットまたは4ビット精度に量子化し、精度の低下を最小限に抑えつつ50〜75%のメモリ削減を実現します。限られたGPUメモリでより大規模なモデルを実行したり、推論を高速化するのに理想的で、INT8、NF4、FP4などのフォーマットをサポートしています。HuggingFace Transformersと統合され、QLoRAトレーニングや8ビットオプティマイザーを可能にします。

スキルを見る

dispatching-parallel-agents

その他

このClaudeスキルは、複数のエージェントを配備し、3つ以上の独立した問題を並行して調査・修正します。共有状態や依存関係がなく解決可能な、無関係な障害が発生するシナリオ向けに設計されています。中核となる機能は並列問題解決であり、効率を最大化するために独立した問題領域ごとに1つのエージェントを割り当てます。

スキルを見る