AI Sales Pipeline skill

python3 telemetry/versioncheck.py 2>/dev/null || true

by ericosiu·MIT license·★ 3,615 Stars on the repo·GitHub ↗

Use now

Files of AI Sales Pipeline

ericosiu/main1 file shown
SKILL.md
Show the full text81 lines

AI Sales Pipeline

Preamble (runs on skill start)

# Version check (silent if up to date)
python3 telemetry/version_check.py 2>/dev/null || true

# Telemetry opt-in (first run only, then remembers your choice)
python3 telemetry/telemetry_init.py 2>/dev/null || true

Privacy: This skill logs usage locally to ~/.ai-marketing-skills/analytics/. Remote telemetry is opt-in only. No code, file paths, or repo content is ever collected. See telemetry/README.md.


Complete AI-powered sales pipeline automation: website visitor identification → intent scoring → suppression → campaign routing → dead deal resurrection → trigger prospecting → self-learning ICP optimization.

When to Use

Use this skill when:

  • Setting up automated outbound from website visitor identification (RB2B)
  • Running suppression checks before cold outreach
  • Routing leads to the right cold email campaigns
  • Reviving closed-lost deals from HubSpot
  • Finding companies showing buying signals (new hires, funding, job postings)
  • Analyzing prospect approve/reject patterns to improve ICP targeting

Tools

RB2B Pipeline (visitor → outbound)
Script Purpose Key Command
rb2b_webhook_ingest.py Webhook server + intent scoring python3 rb2b_webhook_ingest.py --serve --port 4100
rb2b_suppression_pipeline.py 5-layer suppression checks python3 rb2b_suppression_pipeline.py --email [email protected]
rb2b_instantly_router.py Full pipeline: score → suppress → route → enroll python3 rb2b_instantly_router.py --serve --port 4100
Deal Intelligence
Script Purpose Key Command
deal_resurrector.py 3-layer dead deal revival (time decay + POC expansion + champion tracking) python3 deal_resurrector.py --top 10 --dry-run
trigger_prospector.py Web signal monitoring (new hires, funding, agency searches) python3 trigger_prospector.py --days 7 --top 15
icp_learning_analyzer.py Learn from approve/reject decisions, recommend ICP changes python3 icp_learning_analyzer.py

Configuration

All scripts use environment variables for API keys and configuration. Copy .env.example to .env and fill in your values.

Required Environment Variables
  • HUBSPOT_API_KEY — HubSpot private app token (Deal Resurrector, Suppression)
  • INSTANTLY_API_KEY — Instantly API key (Router, Suppression)
  • BRAVE_API_KEY — Brave Search API key (Trigger Prospector)
  • DATABASE_URL — PostgreSQL connection string (ICP Analyzer only)
Key Customization Points
  • Intent scoring: Edit PAGE_INTENT_SCORES dict in webhook_ingest to match your URL patterns
  • Agency detection: Edit AGENCY_KEYWORDS_* in router for your market
  • Loss reason scoring: Edit LOSS_REASON_BONUS in deal_resurrector for your close reasons
  • Signal queries: Edit SEARCH_QUERIES in trigger_prospector for your target market
  • Campaign routing: Edit data/campaigns.json with your Instantly campaign UUIDs

Data Flow

RB2B Webhook → Ingest (score) → Suppress (5 layers) → Route (classify) → Instantly
HubSpot CRM  → Deal Resurrector (score + draft emails) → Review Queue
Brave Search → Trigger Prospector (score + enrich) → Outreach Queue
Prospect DB  → ICP Analyzer (learn patterns) → Filter Recommendations

Dependencies

  • Python 3.9+
  • requests (for HubSpot API)
  • psycopg2-binary (for ICP Analyzer only)
  • No other external dependencies — scripts use stdlib HTTP server and urllib
1# AI Sales Pipeline
2 
3## Preamble (runs on skill start)
4 
5```bash
6# Version check (silent if up to date)
7python3 telemetry/version_check.py 2>/dev/null || true
8 
9# Telemetry opt-in (first run only, then remembers your choice)
10python3 telemetry/telemetry_init.py 2>/dev/null || true
11```
12 
13> **Privacy:** This skill logs usage locally to `~/.ai-marketing-skills/analytics/`. Remote telemetry is opt-in only. No code, file paths, or repo content is ever collected. See `telemetry/README.md`.
14 
15---
16 
17Complete AI-powered sales pipeline automation: website visitor identification → intent scoring → suppression → campaign routing → dead deal resurrection → trigger prospecting → self-learning ICP optimization.
18 
19## When to Use
20 
21Use this skill when:
22- Setting up automated outbound from website visitor identification (RB2B)
23- Running suppression checks before cold outreach
24- Routing leads to the right cold email campaigns
25- Reviving closed-lost deals from HubSpot
26- Finding companies showing buying signals (new hires, funding, job postings)
27- Analyzing prospect approve/reject patterns to improve ICP targeting
28 
29## Tools
30 
31### RB2B Pipeline (visitor → outbound)
32 
33| Script | Purpose | Key Command |
34|--------|---------|-------------|
35| `rb2b_webhook_ingest.py` | Webhook server + intent scoring | `python3 rb2b_webhook_ingest.py --serve --port 4100` |
36| `rb2b_suppression_pipeline.py` | 5-layer suppression checks | `python3 rb2b_suppression_pipeline.py --email [email protected]` |
37| `rb2b_instantly_router.py` | Full pipeline: score → suppress → route → enroll | `python3 rb2b_instantly_router.py --serve --port 4100` |
38 
39### Deal Intelligence
40 
41| Script | Purpose | Key Command |
42|--------|---------|-------------|
43| `deal_resurrector.py` | 3-layer dead deal revival (time decay + POC expansion + champion tracking) | `python3 deal_resurrector.py --top 10 --dry-run` |
44| `trigger_prospector.py` | Web signal monitoring (new hires, funding, agency searches) | `python3 trigger_prospector.py --days 7 --top 15` |
45| `icp_learning_analyzer.py` | Learn from approve/reject decisions, recommend ICP changes | `python3 icp_learning_analyzer.py` |
46 
47## Configuration
48 
49All scripts use environment variables for API keys and configuration. Copy `.env.example` to `.env` and fill in your values.
50 
51### Required Environment Variables
52 
53- `HUBSPOT_API_KEY` — HubSpot private app token (Deal Resurrector, Suppression)
54- `INSTANTLY_API_KEY` — Instantly API key (Router, Suppression)
55- `BRAVE_API_KEY` — Brave Search API key (Trigger Prospector)
56- `DATABASE_URL` — PostgreSQL connection string (ICP Analyzer only)
57 
58### Key Customization Points
59 
60- **Intent scoring**: Edit `PAGE_INTENT_SCORES` dict in webhook_ingest to match your URL patterns
61- **Agency detection**: Edit `AGENCY_KEYWORDS_*` in router for your market
62- **Loss reason scoring**: Edit `LOSS_REASON_BONUS` in deal_resurrector for your close reasons
63- **Signal queries**: Edit `SEARCH_QUERIES` in trigger_prospector for your target market
64- **Campaign routing**: Edit `data/campaigns.json` with your Instantly campaign UUIDs
65 
66## Data Flow
67 
68```
69RB2B Webhook → Ingest (score) → Suppress (5 layers) → Route (classify) → Instantly
70HubSpot CRM → Deal Resurrector (score + draft emails) → Review Queue
71Brave Search → Trigger Prospector (score + enrich) → Outreach Queue
72Prospect DB → ICP Analyzer (learn patterns) → Filter Recommendations
73```
74 
75## Dependencies
76 
77- Python 3.9+
78- `requests` (for HubSpot API)
79- `psycopg2-binary` (for ICP Analyzer only)
80- No other external dependencies — scripts use stdlib HTTP server and urllib
81 

Discussion

Alternatives

⚡ NEXUS Quick-Start Guide> Get from zero to orchestrated multi-agent pipeline in 5 minutes.Business & ops · MIT🎯 NEXUS Agent Activation Prompts> Ready-to-use prompt templates for activating any agent within the NEXUS pipeline. Copy, customize the [PLACEHOLDERS], and deploy.Business & ops · MITArbor — Autonomous Optimization via Hypothesis Tree RefinementAutonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.Science · MIT/cs:cro-review — CRO Forcing Questions/cs:cro-review <plan> — Pipeline-paranoid interrogation of revenue, win rate, NRR, and ramp time. Use when the forecast misses pipeline coverage, win rates drop, or before scaling the sales team. · MIT