ABM Campaign — DIY Playbook skill

ABM campaign skill for Claude Code: run a full Account-Based Marketing campaign end-to-end — from ICP definition to live LinkedIn Ads.

by explorium-ai·MIT license·★ 197 Stars on the repo·GitHub ↗

Use now

Inside this skill

SKILL.md · the author's own words
# ABM Campaign — DIY Playbook

This skill walks you through a full ABM campaign end-to-end, using Claude Code as the orchestration layer. You bring your ICP definition an…

**What you'll build:**
1. A scored, filtered account list sourced from Vibe Prospecting
2. Segment-specific ad creatives (HTML templates + optional Figma assets)
3. LinkedIn matched audiences populated with your target accounts
4. Live LinkedIn campaigns with personalized ads
5. An ongoing monitoring and optimization loop

**No personal keys are stored in this skill.** You provide credentials at runtime via environment variables or interactive prompts. See [`s…

---

## Prerequisites

Word-for-word excerpt, not a result. Read the full SKILL.md ↓

Files of ABM Campaign — DIY Playbook

explorium-ai/main1 file shown
SKILL.md
Show the full text245 lines

ABM Campaign — DIY Playbook

This skill walks you through a full ABM campaign end-to-end, using Claude Code as the orchestration layer. You bring your ICP definition and credentials; Claude handles the rest.

What you'll build:

  1. A scored, filtered account list sourced from Vibe Prospecting
  2. Segment-specific ad creatives (HTML templates + optional Figma assets)
  3. LinkedIn matched audiences populated with your target accounts
  4. Live LinkedIn campaigns with personalized ads
  5. An ongoing monitoring and optimization loop

No personal keys are stored in this skill. You provide credentials at runtime via environment variables or interactive prompts. See setup.md before starting.


Prerequisites

Complete setup.md first. It covers:

  • Vibe Prospecting login (npx @vibeprospecting/vpai@latest)
  • LinkedIn Ads API credentials
  • Figma access token (optional)

Campaign Phases

Phase 1 — Build the Account List

Goal: Translate your ICP into a concrete list of target companies.

Read 01-account-list.md before running any Vibe Prospecting commands.

Quick steps:

  1. Define your ICP (industry, company size, geography, tech stack, funding stage, intent signals)
  2. Use autocomplete to normalize filter values
  3. Fetch matching companies with fetch-entities (sample 5 first, then full export)
  4. Save to abm-accounts-raw.csv
# Example: US SaaS companies, 100-1000 employees, using Salesforce
npx @vibeprospecting/vpai@latest autocomplete \
  --args '{"field":"linkedin_category","query":"software"}' \
  --tool-reasoning 'Building ABM account list for SaaS ICP'

npx @vibeprospecting/vpai@latest fetch-entities \
  --args '{
    "entity_type": "business",
    "filters": {
      "linkedin_category": {"values": ["Software Development"]},
      "company_headcount_range": {"values": ["101-250","251-500","501-1000"]},
      "company_country_code": {"values": ["US"]},
      "company_tech_stack_tech": {"values": ["Salesforce"]}
    },
    "page_size": 5
  }' \
  --tool-reasoning 'Sample fetch for ABM account list'

Output: abm-accounts-raw.csv


Phase 2 — Enrich & Score the Accounts

Goal: Add firmographic and technographic data, then score and filter to your best-fit accounts.

Read 02-enrich-score.md for scoring model details.

Quick steps:

  1. Match raw companies to Vibe business IDs
  2. Enrich with firmographics, technographics, funding-and-acquisitions
  3. Apply ICP scoring formula (Claude computes a fit score 0–100)
  4. Filter to accounts above your threshold (suggested: score ≥ 60)
  5. Save to abm-accounts-scored.csv and abm-accounts-final.csv
# Match company names to IDs
npx @vibeprospecting/vpai@latest match-business \
  --args '{"businesses_to_match": [{"name":"Acme Corp","domain":"acme.com"}]}' \
  --tool-reasoning 'Matching accounts for enrichment'

# Enrich firmographics + technographics
npx @vibeprospecting/vpai@latest enrich-business \
  --args '{
    "business_ids": ["biz_xxx"],
    "enrichments": ["firmographics","technographics","funding-and-acquisitions"]
  }' \
  --tool-reasoning 'Enriching accounts for ABM scoring'

Output: abm-accounts-final.csv (scored, filtered list)


Phase 3 — Create the Ad Templates

Goal: Generate reusable, segment-specific ad templates using Claude Code.

Read 03-ad-templates.md for template structure and design system integration.

Quick steps:

  1. Define your ad segments (e.g., "Enterprise Fintech", "Mid-Market SaaS", "Startup")
  2. Specify your design system or brand colors/fonts (or use defaults)
  3. Claude generates HTML/CSS templates for each LinkedIn ad format:
    • Single Image (1200×628 px)
    • Carousel cards (1080×1080 px)
    • Spotlight ad (300×250 px)
  4. Templates use placeholders: {{company_name}}, {{company_logo}}, {{headline}}, {{body_copy}}
  5. Output files saved under creative/templates/

Tell Claude:

"Create LinkedIn ad templates for these segments: [list]. Use these brand colors: [hex]. Use this value prop: [text]."

Output: creative/templates/<segment>-single.html, creative/templates/<segment>-carousel.html


Phase 4 — Personalize the Creative

Goal: Dynamically update creative elements per account using Figma MCP (or a code-based approach).

Read 04-personalize-figma.md for the Figma MCP workflow and code-based fallback.

Option A — Figma MCP (recommended for polished output):

  1. Share your Figma design file URL
  2. Claude reads the template frames via Figma MCP
  3. For each account, Claude swaps: company logo, company name, segment headline
  4. Exports PNG assets per account

Option B — Code-based (no Figma):

  1. Claude uses the HTML templates from Phase 3
  2. Injects per-account data using a Python/Node script
  3. Renders to PNG using puppeteer or playwright
  4. Saves under creative/personalized/<company_domain>/
# Install rendering dependencies (Option B)
npm install -g playwright
playwright install chromium

Output: creative/personalized/<company_domain>/<format>.png


Phase 5 — Push Audiences to LinkedIn Ads

Goal: Create a LinkedIn matched audience from your account list and upload company data.

Read 05-linkedin-audiences.md for the full API workflow.

Quick steps:

  1. Set LinkedIn credentials as environment variables (see setup.md)
  2. Create a DMP segment (matched audience)
  3. Upload your company list (domain-based matching — LinkedIn matches ~40–60% of lists)
  4. Wait for audience to populate (typically 24–48 hours for >300 companies)
# Step 1: Create matched audience
curl -s -X POST "https://api.linkedin.com/v2/dmpSegments" \
  -H "Authorization: Bearer $LINKEDIN_ACCESS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "ABM Target Accounts — Q3 2025",
    "accessPolicy": "PRIVATE",
    "destinations": [{"destination": "urn:li:sponsoredAccount:'$LINKEDIN_AD_ACCOUNT_ID'"}],
    "type": "COMPANY"
  }'

# Note the returned segment ID, then upload company list (see 05-linkedin-audiences.md)

Output: LinkedIn DMP Segment ID saved to linkedin-audience-id.txt


Phase 6 — Create & Launch the Campaigns

Goal: Create campaign groups, campaigns, and ad creatives in LinkedIn Campaign Manager.

Read 06-campaign-management.md for full campaign creation and monitoring.

Quick steps:

  1. Create a campaign group per segment
  2. Create campaigns targeting your matched audience + segment filters
  3. Upload personalized creatives as sponsored content
  4. Set budget, schedule, and bid strategy
  5. Launch

Monitoring loop (ongoing):

  • Claude checks campaign analytics daily
  • Flags underperforming ads (CTR < 0.4%, CPC > $15)
  • Suggests copy/creative tweaks
  • Refreshes audience as new accounts are added

Full Pipeline Checklist

[ ] setup.md — credentials configured
[ ] 01-account-list.md — account list built and exported
[ ] 02-enrich-score.md — accounts enriched, scored, filtered
[ ] 03-ad-templates.md — ad templates created per segment
[ ] 04-personalize-figma.md — creatives personalized per account
[ ] 05-linkedin-audiences.md — matched audience created and populated
[ ] 06-campaign-management.md — campaigns live and monitored

File Outputs Reference

File Phase Description
abm-accounts-raw.csv 1 Raw account list from Vibe Prospecting
abm-accounts-scored.csv 2 Accounts with enrichment + fit scores
abm-accounts-final.csv 2 Filtered best-fit accounts (score ≥ threshold)
creative/templates/ 3 HTML/CSS ad templates per segment
creative/personalized/ 4 Per-account rendered ad images
linkedin-audience-id.txt 5 LinkedIn DMP segment ID
campaign-ids.json 6 Campaign group, campaign, creative IDs
campaign-report.csv 6 Daily analytics export

Troubleshooting

Problem Solution
Vibe Prospecting auth fails Run setup from setup.md → Vibe section
LinkedIn 401 Unauthorized Access token expired — re-run OAuth flow in setup.md
Audience too small (<300) Broaden ICP filters in Phase 1; LinkedIn needs 300+ matched companies to serve ads
Low audience match rate Use company domains (not just names) in Phase 5 upload for better matching
Figma MCP not available Use Option B (code-based) in Phase 4
Creatives rejected by LinkedIn Check LinkedIn ad specs in 03-ad-templates.md
1---
2name: abm-campaign
3description: "ABM campaign skill for Claude Code: run a full Account-Based Marketing campaign end-to-end — from ICP definition to live LinkedIn Ads. Builds targeted account lists with Vibe Prospecting, enriches and scores companies with real-time B2B data, generates personalized ad creatives with Claude Code and Figma, pushes matched audiences to LinkedIn Ads, and monitors campaigns daily at scale. The complete GTM skill for AI-driven account-based marketing in Claude Code, Codex, Hermes-Agent, and OpenClaw. No agency needed."
4compatibility: "Requires: Vibe Prospecting CLI (npx @vibeprospecting/vpai@latest), Figma MCP (optional, for dynamic creative), LinkedIn Ads API credentials"
5metadata:
6 version: "1.0.0"
7---
8 
9# ABM Campaign — DIY Playbook
10 
11This skill walks you through a full ABM campaign end-to-end, using Claude Code as the orchestration layer. You bring your ICP definition and credentials; Claude handles the rest.
12 
13**What you'll build:**
141. A scored, filtered account list sourced from Vibe Prospecting
152. Segment-specific ad creatives (HTML templates + optional Figma assets)
163. LinkedIn matched audiences populated with your target accounts
174. Live LinkedIn campaigns with personalized ads
185. An ongoing monitoring and optimization loop
19 
20**No personal keys are stored in this skill.** You provide credentials at runtime via environment variables or interactive prompts. See [`setup.md`](references/setup.md) before starting.
21 
22---
23 
24## Prerequisites
25 
26Complete [`setup.md`](references/setup.md) first. It covers:
27- Vibe Prospecting login (`npx @vibeprospecting/vpai@latest`)
28- LinkedIn Ads API credentials
29- Figma access token (optional)
30 
31---
32 
33## Campaign Phases
34 
35### Phase 1 — Build the Account List
36 
37**Goal:** Translate your ICP into a concrete list of target companies.
38 
39Read [`01-account-list.md`](references/01-account-list.md) before running any Vibe Prospecting commands.
40 
41**Quick steps:**
421. Define your ICP (industry, company size, geography, tech stack, funding stage, intent signals)
432. Use `autocomplete` to normalize filter values
443. Fetch matching companies with `fetch-entities` (sample 5 first, then full export)
454. Save to `abm-accounts-raw.csv`
46 
47```bash
48# Example: US SaaS companies, 100-1000 employees, using Salesforce
49npx @vibeprospecting/vpai@latest autocomplete \
50 --args '{"field":"linkedin_category","query":"software"}' \
51 --tool-reasoning 'Building ABM account list for SaaS ICP'
52 
53npx @vibeprospecting/vpai@latest fetch-entities \
54 --args '{
55 "entity_type": "business",
56 "filters": {
57 "linkedin_category": {"values": ["Software Development"]},
58 "company_headcount_range": {"values": ["101-250","251-500","501-1000"]},
59 "company_country_code": {"values": ["US"]},
60 "company_tech_stack_tech": {"values": ["Salesforce"]}
61 },
62 "page_size": 5
63 }' \
64 --tool-reasoning 'Sample fetch for ABM account list'
65```
66 
67**Output:** `abm-accounts-raw.csv`
68 
69---
70 
71### Phase 2 — Enrich & Score the Accounts
72 
73**Goal:** Add firmographic and technographic data, then score and filter to your best-fit accounts.
74 
75Read [`02-enrich-score.md`](references/02-enrich-score.md) for scoring model details.
76 
77**Quick steps:**
781. Match raw companies to Vibe business IDs
792. Enrich with `firmographics`, `technographics`, `funding-and-acquisitions`
803. Apply ICP scoring formula (Claude computes a fit score 0–100)
814. Filter to accounts above your threshold (suggested: score ≥ 60)
825. Save to `abm-accounts-scored.csv` and `abm-accounts-final.csv`
83 
84```bash
85# Match company names to IDs
86npx @vibeprospecting/vpai@latest match-business \
87 --args '{"businesses_to_match": [{"name":"Acme Corp","domain":"acme.com"}]}' \
88 --tool-reasoning 'Matching accounts for enrichment'
89 
90# Enrich firmographics + technographics
91npx @vibeprospecting/vpai@latest enrich-business \
92 --args '{
93 "business_ids": ["biz_xxx"],
94 "enrichments": ["firmographics","technographics","funding-and-acquisitions"]
95 }' \
96 --tool-reasoning 'Enriching accounts for ABM scoring'
97```
98 
99**Output:** `abm-accounts-final.csv` (scored, filtered list)
100 
101---
102 
103### Phase 3 — Create the Ad Templates
104 
105**Goal:** Generate reusable, segment-specific ad templates using Claude Code.
106 
107Read [`03-ad-templates.md`](references/03-ad-templates.md) for template structure and design system integration.
108 
109**Quick steps:**
1101. Define your ad segments (e.g., "Enterprise Fintech", "Mid-Market SaaS", "Startup")
1112. Specify your design system or brand colors/fonts (or use defaults)
1123. Claude generates HTML/CSS templates for each LinkedIn ad format:
113 - Single Image (1200×628 px)
114 - Carousel cards (1080×1080 px)
115 - Spotlight ad (300×250 px)
1164. Templates use placeholders: `{{company_name}}`, `{{company_logo}}`, `{{headline}}`, `{{body_copy}}`
1175. Output files saved under `creative/templates/`
118 
119Tell Claude:
120> "Create LinkedIn ad templates for these segments: [list]. Use these brand colors: [hex]. Use this value prop: [text]."
121 
122**Output:** `creative/templates/<segment>-single.html`, `creative/templates/<segment>-carousel.html`
123 
124---
125 
126### Phase 4 — Personalize the Creative
127 
128**Goal:** Dynamically update creative elements per account using Figma MCP (or a code-based approach).
129 
130Read [`04-personalize-figma.md`](references/04-personalize-figma.md) for the Figma MCP workflow and code-based fallback.
131 
132**Option A — Figma MCP (recommended for polished output):**
1331. Share your Figma design file URL
1342. Claude reads the template frames via Figma MCP
1353. For each account, Claude swaps: company logo, company name, segment headline
1364. Exports PNG assets per account
137 
138**Option B — Code-based (no Figma):**
1391. Claude uses the HTML templates from Phase 3
1402. Injects per-account data using a Python/Node script
1413. Renders to PNG using `puppeteer` or `playwright`
1424. Saves under `creative/personalized/<company_domain>/`
143 
144```bash
145# Install rendering dependencies (Option B)
146npm install -g playwright
147playwright install chromium
148```
149 
150**Output:** `creative/personalized/<company_domain>/<format>.png`
151 
152---
153 
154### Phase 5 — Push Audiences to LinkedIn Ads
155 
156**Goal:** Create a LinkedIn matched audience from your account list and upload company data.
157 
158Read [`05-linkedin-audiences.md`](references/05-linkedin-audiences.md) for the full API workflow.
159 
160**Quick steps:**
1611. Set LinkedIn credentials as environment variables (see [`setup.md`](references/setup.md))
1622. Create a DMP segment (matched audience)
1633. Upload your company list (domain-based matching — LinkedIn matches ~40–60% of lists)
1644. Wait for audience to populate (typically 24–48 hours for >300 companies)
165 
166```bash
167# Step 1: Create matched audience
168curl -s -X POST "https://api.linkedin.com/v2/dmpSegments" \
169 -H "Authorization: Bearer $LINKEDIN_ACCESS_TOKEN" \
170 -H "Content-Type: application/json" \
171 -d '{
172 "name": "ABM Target Accounts — Q3 2025",
173 "accessPolicy": "PRIVATE",
174 "destinations": [{"destination": "urn:li:sponsoredAccount:'$LINKEDIN_AD_ACCOUNT_ID'"}],
175 "type": "COMPANY"
176 }'
177 
178# Note the returned segment ID, then upload company list (see 05-linkedin-audiences.md)
179```
180 
181**Output:** LinkedIn DMP Segment ID saved to `linkedin-audience-id.txt`
182 
183---
184 
185### Phase 6 — Create & Launch the Campaigns
186 
187**Goal:** Create campaign groups, campaigns, and ad creatives in LinkedIn Campaign Manager.
188 
189Read [`06-campaign-management.md`](references/06-campaign-management.md) for full campaign creation and monitoring.
190 
191**Quick steps:**
1921. Create a campaign group per segment
1932. Create campaigns targeting your matched audience + segment filters
1943. Upload personalized creatives as sponsored content
1954. Set budget, schedule, and bid strategy
1965. Launch
197 
198**Monitoring loop (ongoing):**
199- Claude checks campaign analytics daily
200- Flags underperforming ads (CTR < 0.4%, CPC > $15)
201- Suggests copy/creative tweaks
202- Refreshes audience as new accounts are added
203 
204---
205 
206## Full Pipeline Checklist
207 
208```
209[ ] setup.md — credentials configured
210[ ] 01-account-list.md — account list built and exported
211[ ] 02-enrich-score.md — accounts enriched, scored, filtered
212[ ] 03-ad-templates.md — ad templates created per segment
213[ ] 04-personalize-figma.md — creatives personalized per account
214[ ] 05-linkedin-audiences.md — matched audience created and populated
215[ ] 06-campaign-management.md — campaigns live and monitored
216```
217 
218---
219 
220## File Outputs Reference
221 
222| File | Phase | Description |
223|------|-------|-------------|
224| `abm-accounts-raw.csv` | 1 | Raw account list from Vibe Prospecting |
225| `abm-accounts-scored.csv` | 2 | Accounts with enrichment + fit scores |
226| `abm-accounts-final.csv` | 2 | Filtered best-fit accounts (score ≥ threshold) |
227| `creative/templates/` | 3 | HTML/CSS ad templates per segment |
228| `creative/personalized/` | 4 | Per-account rendered ad images |
229| `linkedin-audience-id.txt` | 5 | LinkedIn DMP segment ID |
230| `campaign-ids.json` | 6 | Campaign group, campaign, creative IDs |
231| `campaign-report.csv` | 6 | Daily analytics export |
232 
233---
234 
235## Troubleshooting
236 
237| Problem | Solution |
238|---------|----------|
239| Vibe Prospecting auth fails | Run setup from [`setup.md`](references/setup.md) → Vibe section |
240| LinkedIn 401 Unauthorized | Access token expired — re-run OAuth flow in [`setup.md`](references/setup.md) |
241| Audience too small (<300) | Broaden ICP filters in Phase 1; LinkedIn needs 300+ matched companies to serve ads |
242| Low audience match rate | Use company domains (not just names) in Phase 5 upload for better matching |
243| Figma MCP not available | Use Option B (code-based) in Phase 4 |
244| Creatives rejected by LinkedIn | Check LinkedIn ad specs in [`03-ad-templates.md`](references/03-ad-templates.md) |
245 

Discussion

Alternatives

AI Sales Team — Main OrchestratorYou are a comprehensive AI sales intelligence and outreach system for Claude Code. You help founders, sales teams, agency owners, and…Sales & ecommerce · MITAuto research publicAutonomous cold email campaign launcher. Takes one target company domain, scrapes their website, generates an ICP with Claude, pulls matching leads via Prospeo, enriches emails + company descriptions, personalizes each lead with parallel Claude Code Task sub-agents (A/B/C variants), and uploads as a live Smartlead campaign. Uses local JSON files for state (no database required). Use for automated daily campaign launches after you have an initial `client-profile.yaml` from /icp-onboarding. Triggers on "auto-research", "launch an automated campaign", "daily campaign", "run the research loop".Sales & ecommerce · MITAccount contact shortlistContact data skill for Claude Code and Codex: build a ranked shortlist of decision-makers and contacts at a target company for outbound prospecting, deal acceleration, or renewal/expansion plays. Returns verified contact data including email, phone, LinkedIn profile, title, seniority, and department. Provide a company name or domain plus optional seniority focus or use case. Use for contact data enrichment, LinkedIn profile lookup, and building outbound contact lists. Works in Claude Code, Codex, Hermes-Agent, and OpenClaw.Business & ops · MITAccount fit rankLead scoring and buying signals skill for Claude Code and Codex: rank a list of accounts by ICP fit, buying intent, real-time trigger events, and workforce momentum. Returns composite score (0-100), tier (A/B/C), and a 'why now' signal per account. Use for account-based selling, ABM list prioritization, territory planning, signal-based selling, and buyer-intent ranking. Triggers on 'score these accounts', 'rank by ICP fit and intent', 'prioritize this account list', 'which accounts have the strongest buying signals', 'ICP scoring', 'account prioritization'. Works in Claude Code, Codex, Hermes-Agent, OpenClaw, and Claude Cowork.Sales & ecommerce · MIT