The problem
Why this system exists
Personalized sales collateral is usually slow to research and build, while generic decks fail to show a prospect that you understand their market and current GTM situation.
Sales Enablement
Microsite Pipeline
Turns one sales lead into a researched, personalized eight-page sales microsite and PDF using sourced company data.
The outcome
What it produces
A repeatable local pipeline that researches a company, generates TAM, ICP, and sales-signal insights, then renders an on-brand HTML page and PDF without fabricating missing data.
System overview
How the playbook moves from input to outcome.
Each stage has one job. The sequence stays visible while the active state moves through the system.
01
Lead
Start with a person and company domain.
02
Enrich
Research the person, company, stack, traffic, ads, and brand.
03
Synthesize
Generate sourced TAM, ICP segments, and sales signals.
04
Validate
Drop unsupported fields and check required core outputs.
05
Render
Create a personalized HTML microsite and printable PDF.
Inputs
What the system needs
- LinkedIn profile or lead name
- Company domain
- Anthropic API key
- Optional enrichment-provider keys
Outputs
What comes out
- Eight-page personalized sales deck
- Shareable HTML microsite
- Printable PDF
- Long-form research brief
- Reviewable follow-up page draft
Real output
What the pipeline actually produces.
These are real example pages shipped with the public repository, using a fictional company in the data slots.
Inside the repository
The important pieces, without the file-system noise.
The explainer shows the operating structure. The repository remains the source of truth for complete setup and implementation details.
microsite-pipeline/
- 01src/pipeline.ts: dependency-ordered runner
- 02src/steps/: twelve research and enrichment stages
- 03src/pure/: deterministic, tested transformations
- 04templates/: two microsite design systems
- 05prompts/: research and synthesis instructions
- 06scripts/: setup, run, inspect, serve, and approve
Guardrails
What the system deliberately protects.
- Missing sources remove a field instead of producing a fabricated value.
- Draft follow-up pages require explicit approval before deployment.
- Every pipeline step records provider, state, and cost.
- Completed steps are idempotent and do not rerun unless forced.
Quick start
From repository to first useful run.
- 01Install dependencies and Playwright Chromium.
- 02Run the guided setup and add the keys you want to use.
- 03Run doctor to see which stages will execute or skip.
- 04Provide one lead and company domain.
- 05Review the generated HTML, PDF, and research output.
Adapt the system
Want a version built around your market, tools, and sales process?
Keep exploring
Related playbooks
Claude Code SkillsOpen source
GTM Flywheel
Fifteen structured Claude Code skills that turn ICP research, signal scoring, outbound copy, campaign analytics, and sales intelligence into one compounding GTM system.
ICP Research
Signal Scoring
Cold Email
A versioned set of operating skills with scoring models, decision trees, templates, and quality checks that Claude Code can apply consistently to your own data.
Company OSOpen source
GTM OS Kit
A Company OS starter kit that gives Claude persistent business context, reusable GTM skills, workflow commands, and safety hooks.
Clone
Interview
Structure
A portable, version-controlled Company OS centered on CLAUDE.md, supported by structured business context, playbooks, reusable skills, hooks, and workflow commands.