prospecting-research
정보
이 스킬은 기업 정보를 수집하고 참여 각도를 파악하여 영업 접근을 개인화하는 심층적인 계정 및 연락처 조사를 가능하게 합니다. 고가치 아웃바운드 캠페인 준비, 계정 프로필 구축, 기업 대상 맞춤형 접근에 이상적입니다. 이 스킬은 Fanatical Prospecting과 같은 방법론을 기반으로 연구 프레임워크를 구성하여 핵심 데이터 포인트와 트리거를 식별하는 데 도움을 줍니다.
빠른 설치
Claude Code
추천npx skills add guia-matthieu/clawfu-skills -a claude-code/plugin add https://github.com/guia-matthieu/clawfu-skillsgit clone https://github.com/guia-matthieu/clawfu-skills.git ~/.claude/skills/prospecting-researchClaude Code에서 이 명령을 복사하여 붙여넣어 스킬을 설치하세요
문서
Prospecting Research
Systematically research target accounts and contacts to craft personalized, relevant outreach that cuts through the noise.
When to Use This Skill
- Preparing for high-value outbound
- Personalizing enterprise outreach
- Building account intelligence
- Training SDRs on research
- Creating target account profiles
Methodology Foundation
Based on Jeb Blount's Fanatical Prospecting and TOPO Account-Based Research, combining:
- Company intelligence gathering
- Contact profiling
- Trigger identification
- Angle development
What Claude Does vs What You Decide
| Claude Does | You Decide |
|---|---|
| Structures research framework | Time per account |
| Identifies key data points | Outreach approach |
| Suggests personalization angles | Which angle to use |
| Creates research templates | Tool selection |
| Synthesizes findings | Message crafting |
Instructions
Step 1: Company Research
Firmographic Data:
| Data Point | Source | Why It Matters |
|---|---|---|
| Company size | LinkedIn, website | ICP fit |
| Revenue | ZoomInfo, news | Budget potential |
| Industry | Relevance | |
| Locations | Website | Territory |
| Tech stack | BuiltWith, job posts | Integration fit |
Business Context:
| Data Point | Source | Why It Matters |
|---|---|---|
| Recent funding | Crunchbase, news | Budget, growth mode |
| Executive changes | LinkedIn, news | New priorities |
| Product launches | Press releases | Initiatives |
| Earnings/reports | SEC, investor calls | Priorities, challenges |
| Partnerships | News | Ecosystem |
Step 2: Contact Research
Professional Profile:
| Data Point | Source | Why It Matters |
|---|---|---|
| Current role | Relevance | |
| Tenure | Influence level | |
| Career path | Context | |
| Content shared | LinkedIn, Twitter | Interests |
| Mutual connections | Warm intro |
Personal Connection Points:
- Shared alma mater
- Previous company overlap
- Mutual connections
- Content they've created
- Events they've attended
Step 3: Identify Triggers
Timing Triggers:
| Trigger | Implication |
|---|---|
| New in role | Building stack, making changes |
| New company | Bringing solutions from previous |
| Funding | Budget available |
| Hiring | Scaling, needs support |
| Bad earnings | Cost cutting or growth push |
Step 4: Develop Angles
Personalization Hierarchy:
- Trigger-based - Strongest (funding, hire, news)
- Content-based - Strong (their posts, interviews)
- Company-based - Good (industry, challenges)
- Mutual connection - Good (warm intro potential)
- Generic - Weak (avoid)
Examples
Example 1: Full Account Research
Output:
## Account Research: DataFlow Systems
### Company Snapshot
| Attribute | Value | Source |
|-----------|-------|--------|
| Company | DataFlow Systems | |
| Industry | B2B SaaS (Analytics) | LinkedIn |
| Size | 340 employees | LinkedIn |
| Revenue | ~$50M ARR (est.) | ZoomInfo |
| Founded | 2018 | Crunchbase |
| HQ | Austin, TX | Website |
| Funding | $45M Series B (Oct 2024) | Crunchbase |
---
### Technology Stack
| Category | Tool | Source |
|----------|------|--------|
| CRM | Salesforce | BuiltWith, Jobs |
| Marketing | HubSpot | BuiltWith |
| Analytics | Mixpanel | Careers page |
| Data | Snowflake | Job posting |
| [Your Category] | None detected | Research |
**Implication:** Salesforce user = good fit for integration. No tool in our category = greenfield opportunity.
---
### Recent Triggers
| Date | Trigger | Relevance |
|------|---------|-----------|
| Oct 2024 | Series B ($45M) | Budget for tools |
| Nov 2024 | VP Sales hired | New leader = new tools |
| Dec 2024 | 12 SDR positions posted | Scaling outbound |
| Jan 2025 | G2 reviews mention "[pain]" | Known problem |
---
### Business Context
**From LinkedIn:**
- Growing 60% YoY (CEO post)
- Expanding to enterprise segment (VP Sales announcement)
- Recent product launch: AI analytics features
**From News:**
- Named to "Top 50 Startups" list
- Partnership with [Complementary Company]
- CEO spoke at [Industry Conference]
**From Job Posts:**
- Hiring: SDRs (12), AEs (5), RevOps (1)
- Reveals: Scaling sales org significantly
- Tech stack mentioned: Salesforce, Gong, Outreach (competitor!)
---
### Challenges (Inferred)
Based on triggers and context:
1. **Scaling sales team** - Need tools to support
2. **Moving upmarket** - Enterprise processes needed
3. **Rev Ops hire** - Building infrastructure
4. **Competitor in stack** - May be open to alternatives
---
### Target Contacts
| Name | Title | Priority | Angle |
|------|-------|----------|-------|
| Sarah Kim | VP Sales | Primary | New to role (90 days) |
| Mike Chen | RevOps Manager | Secondary | Posted RevOps opening |
| David Park | CEO | Executive | Series B scaling |
---
### Recommended Approach
**Primary Target: Sarah Kim, VP Sales**
- New to role = making changes
- Scaling team = needs tools
- Moving upmarket = needs process
**Angle:** "Congrats on the VP role and Series B! I noticed you're hiring 12 SDRs. Most VP Sales at your stage tell me [challenge] is their biggest issue. Curious if that's true for you?"
**Secondary Path:**
- RevOps Manager Mike Chen (operational angle)
- Mutual connection: [Name] (former colleague)
Example 2: Contact Deep Dive
Output:
## Contact Research: Sarah Kim, VP Sales
### Profile Summary
| Attribute | Value |
|-----------|-------|
| Name | Sarah Kim |
| Title | VP of Sales |
| Company | DataFlow Systems |
| Location | Austin, TX |
| Tenure | 3 months (started Oct 2024) |
| LinkedIn | linkedin.com/in/sarahkim |
---
### Career Path
| Period | Company | Role | Relevance |
|--------|---------|------|-----------|
| 2024-Present | DataFlow | VP Sales | Target |
| 2021-2024 | ScaleUp Inc | Director Sales | Previous tools? |
| 2018-2021 | BigCorp | Sales Manager | Enterprise exp |
| 2015-2018 | StartupXYZ | AE | SMB background |
**Insight:** Rose through ranks. Enterprise + SMB experience. First VP role = motivated to succeed.
---
### Content Activity
**LinkedIn Posts (Last 90 days):**
- "Excited to join DataFlow!" (Oct)
- Shared article on "Scaling SDR teams"
- Commented on post about sales forecasting
- Posted about team offsite (Dec)
**Themes:** Sales leadership, team building, scaling
**Quote-worthy:** "The hardest part of scaling isn't hiring—it's making sure every rep can sell like your best rep."
---
### Connection Points
| Type | Detail | Approach |
|------|--------|----------|
| Mutual Connection | John Smith (2nd degree) | Ask for intro |
| Content | Scaling article | Reference in outreach |
| Alma Mater | Stanford MBA | Mention if relevant |
| Previous Company | ScaleUp used our competitor | Migration angle |
---
### Professional Interests
Based on activity:
- Sales enablement
- Team scaling
- Forecasting accuracy
- Rep productivity
---
### Personalization Angles
**Angle 1: New VP + Scaling** (Strongest)
Hi Sarah,
Congrats on the VP role at DataFlow—and jumping into a Series B scaling mode!
I noticed you shared that article on scaling SDR teams. The quote "making every rep sell like your best rep" really resonated.
That's exactly what [Similar Customer] focused on when they went from 5 to 50 reps.
Curious: what's your #1 challenge as you build out the team?
**Angle 2: Content-Based**
Hi Sarah,
Loved your take on the hardest part of scaling: "making every rep sell like your best rep."
I work with a lot of VP Sales going through exactly that transition. The common thread? [Insight from our customers].
Worth comparing notes?
**Angle 3: Mutual Connection**
Hi Sarah,
John Smith mentioned you just took over sales at DataFlow—congrats!
He thought we should connect given your focus on [area].
Would love to hear what's top of mind as you build out the team.
---
### Red Flags / Cautions
- Just started (Oct) - may not have full authority yet
- Previous company used competitor - could be loyal
- No public content about specific pain points
---
### Recommended Sequence
**Day 1:** Email (Angle 1 - New VP + Scaling)
**Day 1:** LinkedIn connection (mention scaling article)
**Day 3:** Follow-up email with customer story
**Day 5:** LinkedIn voice note
**Day 7:** Final email with value offer
**Expectation:** 20-30% response rate with this level of personalization
Skill Boundaries
What This Skill Does Well
- Structuring research process
- Identifying personalization angles
- Finding trigger events
- Synthesizing intelligence
What This Skill Cannot Do
- Access paid databases
- Verify data accuracy
- Replace genuine relationship building
- Write final message copy
References
- Jeb Blount's Fanatical Prospecting
- TOPO Account-Based Research
- SalesLoft Personalization Guide
- Outreach.io Research Best Practices
Related Skills
icp-matching- Qualify before researchsignal-monitoring- Trigger identificationoutbound-sequencer- Use research in sequences
Skill Metadata
- Domain: SDR Automation
- Complexity: Intermediate
- Mode: cyborg
- Time to Value: 15-30 min per account
- Prerequisites: Research tool access
GitHub 저장소
연관 스킬
llamaguard
기타LlamaGuard는 폭력 및 혐오 발언 등 6가지 안전 범주에서 LLM 입력과 출력을 조정하기 위한 Meta의 70-80억 파라미터 모델입니다. 94-95% 정확도를 제공하며 vLLM, Hugging Face 또는 Amazon SageMaker를 사용해 배포할 수 있습니다. 이 기술을 사용하여 AI 애플리케이션에 콘텐츠 필터링 및 안전 가드레일을 손쉽게 통합하세요.
cost-optimization
기타이 Claude Skill은 리소스 적정화, 태깅 전략, 지출 분석을 통해 개발자들이 클라우드 비용을 최적화할 수 있도록 지원합니다. AWS, Azure, GCP에서 클라우드 비용을 절감하고 비용 거버넌스를 구현하기 위한 프레임워크를 제공합니다. 인프라 비용을 분석하거나, 리소스를 적정화하거나, 예산 제약을 충족해야 할 때 사용하세요.
quantizing-models-bitsandbytes
기타이 스킬은 bitsandbytes를 사용하여 LLM을 8비트 또는 4비트 정밀도로 양자화하며, 최소한의 정확도 손실로 50-75%의 메모리 감소를 달성합니다. 제한된 GPU 메모리에서 더 큰 모델을 실행하거나 추론을 가속화하는 데 이상적이며, INT8, NF4, FP4와 같은 형식을 지원합니다. 이 스킬은 HuggingFace Transformers와 통합되어 QLoRA 학습 및 8비트 옵티마이저를 가능하게 합니다.
dispatching-parallel-agents
기타이 Claude Skill은 3개 이상의 독립적인 문제를 동시에 조사하고 해결하기 위해 다중 에이전트를 배치합니다. 공유 상태나 의존성 없이 해결 가능한 무관련 장애 시나리오에 맞게 설계되었습니다. 핵심 기능은 병렬 문제 해결로, 각 독립 문제 영역마다 하나의 에이전트를 할당하여 효율성을 극대화합니다.
