abm-specialist
Эксперт ABM. Используй для account-based marketing, target account selection и personalized campaigns.
Best use case
abm-specialist is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Эксперт ABM. Используй для account-based marketing, target account selection и personalized campaigns.
Teams using abm-specialist should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/abm-specialist/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How abm-specialist Compares
| Feature / Agent | abm-specialist | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Эксперт ABM. Используй для account-based marketing, target account selection и personalized campaigns.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Account-Based Marketing Specialist
Strategic expertise in account-based marketing for enterprise growth.
## Core Competencies
### ABM Strategy
- Account selection
- Tier definition
- Persona mapping
- Play development
- Sales alignment
### Campaign Orchestration
- Multi-channel coordination
- Personalization at scale
- Timing and sequencing
- Content mapping
- Touchpoint optimization
### Measurement
- Account engagement scoring
- Pipeline attribution
- ABM ROI
- Coverage metrics
- Influence tracking
## ABM Tier Framework
### Tier 1: Strategic (1:1)
- **Accounts:** 10-50
- **Investment:** High
- **Personalization:** Fully custom
- **Content:** Bespoke for each account
- **Plays:** Executive engagement, custom events
### Tier 2: Scale (1:Few)
- **Accounts:** 50-500
- **Investment:** Medium
- **Personalization:** Industry/segment
- **Content:** Templated with personalization
- **Plays:** Industry campaigns, webinars
### Tier 3: Programmatic (1:Many)
- **Accounts:** 500+
- **Investment:** Lower per account
- **Personalization:** Automated
- **Content:** Dynamic fields
- **Plays:** Targeted advertising, sequences
## ABM Plays
### Executive Engagement
- Executive briefings
- Advisory boards
- VIP events
- Executive sponsorship
### Digital Engagement
- Personalized ads
- Custom landing pages
- Targeted content
- Retargeting
### Direct Engagement
- Direct mail
- Personalized gifts
- Custom experiences
- Field events
## Account Selection Framework
### ICP (Ideal Customer Profile)
```
Firmographic Criteria:
- Industry: SaaS, FinTech, Healthcare
- Company size: 500-5000 employees
- Revenue: $50M-$500M
- Geography: North America, Europe
Technographic Criteria:
- Current tech stack alignment
- Integration compatibility
- Digital maturity level
Intent Signals:
- Researching solution category
- Competitor engagement
- Content consumption patterns
```
### Account Scoring Model
```python
def calculate_account_score(account):
score = 0
# Firmographic fit (40%)
score += firmographic_score(account) * 0.4
# Technographic fit (20%)
score += technographic_score(account) * 0.2
# Intent signals (25%)
score += intent_score(account) * 0.25
# Engagement history (15%)
score += engagement_score(account) * 0.15
return score
def assign_tier(score):
if score >= 80:
return "Tier 1"
elif score >= 60:
return "Tier 2"
else:
return "Tier 3"
```
## Account Engagement Scoring
| Activity | Points |
|----------|--------|
| Website visit | 1 |
| Content download | 5 |
| Event registration | 10 |
| Demo request | 25 |
| Meeting scheduled | 50 |
| Opportunity created | 100 |
## Multi-Threading Strategy
### Persona Map
```
C-Suite:
- CEO: Business outcomes, ROI
- CFO: Cost reduction, efficiency
- CTO: Technical capabilities, security
Directors:
- VP Sales: Revenue impact
- VP Marketing: Pipeline contribution
- VP Operations: Process improvement
Users:
- Managers: Day-to-day workflow
- End users: Ease of use, adoption
```
### Engagement Sequence
```
Week 1: Research & mapping
- Identify all stakeholders
- Map reporting structure
- Find common connections
Week 2-4: Initial outreach
- LinkedIn engagement
- Personalized emails
- Content sharing
Week 5-8: Value delivery
- Custom content
- Industry insights
- Peer introductions
Week 9-12: Meeting conversion
- Multi-threading emails
- Executive referrals
- Event invitations
```
## ABM Tech Stack
- **Orchestration:** 6sense, Demandbase, Terminus
- **Intent Data:** Bombora, G2
- **Advertising:** LinkedIn, Display
- **Personalization:** Mutiny, PathFactory
- **Gifting:** Sendoso, Postal
- **CRM:** Salesforce, HubSpot
- **Analytics:** Tableau, Looker
## Measurement Framework
### Leading Indicators
- Account coverage (% of personas engaged)
- Account engagement score
- Content consumption
- Meeting conversion rate
### Lagging Indicators
- Pipeline generated
- Pipeline velocity
- Win rate by tier
- Average deal size
- Customer acquisition cost
### ROI Calculation
```
ABM ROI = (Revenue from ABM accounts - ABM investment) / ABM investment
ABM Investment includes:
- Technology costs
- Content creation
- Advertising spend
- Events & gifts
- Headcount allocation
```
## Best Practices
1. **Start small** - Pilot with 10-20 accounts before scaling
2. **Align with sales** - Weekly syncs on target accounts
3. **Personalize genuinely** - Generic personalization backfires
4. **Multi-thread early** - Don't rely on single champion
5. **Measure incrementally** - Compare ABM vs non-ABM cohorts
6. **Iterate plays** - Test and optimize continuouslyRelated Skills
jekyll-specialist
Manages the samueltauil.github.io Jekyll site. Use for creating blog posts, updating photography content, editing the home page agent file, modifying styles, and maintaining site structure. Handles posts, photography galleries, resume updates, and GitHub Copilot dark theme customization.
agent-seo-specialist
Expert SEO strategist specializing in technical SEO, content optimization, and search engine rankings. Masters both on-page and off-page optimization, structured data implementation, and performance metrics to drive organic traffic and improve search visibility.
bullmq-specialist
BullMQ expert for Redis-backed job queues, background processing, and reliable async execution in Node.js/TypeScript applications. Use when: bullmq, bull queue, redis queue, background job, job queue.
API Integration Specialist
Expert guidance for designing, integrating, and maintaining third-party APIs with best practices for authentication, error handling, rate limiting, security, and data transformation. Use when integrating external APIs, troubleshooting API issues, implementing OAuth flows, handling webhooks, or building API wrappers and clients.
AI Integration Specialist
Integrate AI tools and APIs into business workflows and applications
agent-laravel-specialist
Expert Laravel specialist mastering Laravel 10+ with modern PHP practices. Specializes in elegant syntax, Eloquent ORM, queue systems, and enterprise features with focus on building scalable web applications and APIs.
security-specialist
安全专家。专注于应用安全、威胁建模、安全合规和数据保护。提供安全审查、漏洞扫描、安全配置和合规检查。用于构建安全可靠的应用系统。
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
large-data-with-dask
Specific optimization strategies for Python scripts working with larger-than-memory datasets via Dask.
langsmith-fetch
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.
langchain-tool-calling
How chat models call tools - includes bind_tools, tool choice strategies, parallel tool calling, and tool message handling
langchain-notes
LangChain 框架学习笔记 - 快速查找概念、代码示例和最佳实践。包含 Core components、Middleware、Advanced usage、Multi-agent patterns、RAG retrieval、Long-term memory 等主题。当用户询问 LangChain、Agent、RAG、向量存储、工具使用、记忆系统时使用此 Skill。