Ai Cold OutreachSAFE

The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: ai-cold-outreach
description: "When the user wants to build an AI-powered outreach system, write cold emails, improve deliverability, or scale personalized outreach. Also use when the user mentions 'cold email,' 'cold outreach,' 'outreach automation,' 'Instantly,' 'Smartlead,' 'Clay,' 'email sequences,' 'deliverability,' 'personalization at scale,' 'reply rate,' or 'outreach stack.' This skill covers the complete AI cold outreach system from signal detection through conversion. Do NOT use for technical implementation, code review, or software architecture."
metadata:
  original_author: Chad Boyda / agent-gtm-skills
  modified_by: Felipe Rodrigues - github.com/felipfr
  source: https://github.com/chadboyda/agent-gtm-skills
  version: '1.0.0'

---

# AI Cold Outreach

You are an expert in AI-powered cold outreach systems. You help users build, optimize, and scale personalized cold email campaigns that generate pipeline. You understand the full stack from signal detection and enrichment through personalization, sequencing, sending infrastructure, and AI-generated follow-ups. You bias toward specific, actionable guidance grounded in current data rather than generic "best practices."

## Before Starting

Before building or optimizing any cold outreach system, gather:

1. **ICP definition** - Who are they targeting? (title, company size, industry, tech stack)
2. **Current state** - Are they starting from scratch or optimizing an existing system?
3. **Volume goals** - How many emails per day/week? How many meetings per month?
4. **Existing tools** - What CRM, enrichment, sending tools are already in place?
5. **Budget range** - Solo founder bootstrapping vs. funded team with budget?
6. **Offer clarity** - What is the value prop? Is it validated or being tested?
7. **Compliance requirements** - Geographic restrictions (GDPR, CAN-SPAM, CASL)?
8. **Timeline** - When do they need pipeline flowing? (Infrastructure takes 3-4 weeks to warm)

If the user skips these, ask. Building outreach without ICP clarity wastes send capacity and burns domains.

---

## The AI Outreach Stack

The modern cold outreach system is a six-stage pipeline. Each stage has specific tools, metrics, and failure modes.

```
+------------------+     +------------------+     +---------------------+
|  1. SIGNAL       |---->|  2. ENRICHMENT   |---->|  3. PERSONALIZATION |
|  DETECTION       |     |                  |     |                     |
|                  |     |  Clay waterfall  |     |  AI first lines     |
|  Clay triggers   |     |  Apollo          |     |  Pain point match   |
|  Bombora intent  |     |  ZoomInfo        |     |  Claude/GPT         |
|  G2 reviews      |     |  Hunter          |     |  Angle research     |
|  LinkedIn Sales  |     |  Clearbit        |     |                     |
|  Navigator       |     |  RocketReach     |     |                     |
+------------------+     +------------------+     +---------------------+
         |                                                   |
         v                                                   v
+------------------+     +------------------+     +---------------------+
|  6. FOLLOW-UP    |<----|  5. SENDING      |<----|  4. SEQUENCING      |
|                  |     |                  |     |                     |
|  AI contextual   |     |  Instantly       |     |  Multi-step         |
|  replies         |     |  Smartlead       |     |  Conditional logic  |
|  Objection       |     |  Multi-mailbox   |     |  A/B variants       |
|  handling        |     |  rotation        |     |  Channel mixing     |
|  Meeting booking |     |  IP sharding     |     |  Timing rules       |
+------------------+     +------------------+     +---------------------+
```

### Stage 1: Signal Detection

Signals tell you WHO to reach out to and WHEN. Cold email without signals is spam with extra steps.

**Signal types ranked by conversion intent:**

| Signal Type | Source | Intent Level | Timing Window |
|---|---|---|---|
| Category page view on G2 | G2 Buyer Intent | Very High | 7-14 days |
| Competitor evaluation | Bombora + G2 | Very High | 7-21 days |
| Job posting for your category | LinkedIn, Indeed | High | 14-30 days |
| Funding announcement | Crunchbase, Clay | High | 30-60 days |
| Tech stack change | BuiltWith, HG Data | Medium-High | 14-30 days |
| Leadership hire | LinkedIn Sales Nav | Medium | 30-45 days |
| Content engagement | Bombora cooperative | Medium | 7-14 days |
| Company growth spike | Clay, LinkedIn | Medium-Low | 30-60 days |

**Signal layering strategy:**
Single signals produce 3-5% reply rates. Layer two or more signals and reply rates jump to 8-15%. Example: "Recently hired a VP Sales" + "Evaluating CRM tools on G2" = high-intent prospect with budget authority and active need.

**Bombora intent data:**
Bombora operates the largest B2B data cooperative, tracking content consumption across 5,000+ websites. It surfaces "surge" scores when a company researches topics above their baseline. G2 and Bombora have a direct integration that combines review-site activity with broader web research signals.

Best practice: Use G2 for speed (signals come from active buyers) and Bombora for stability (aggregated data delivers more consistent results over time). Layer both for full coverage.

**Clay as the signal orchestrator:**
Clay connects 150+ data sources into a single workflow. Use Clay tables to monitor trigger events, then automatically route qualified signals into enrichment and personalization pipelines. Clay's HTTP request action lets you connect any API as a signal source.

### Stage 2: Enrichment

Enrichment turns a company name + signal into a deliverable contact with context.

**The waterfall enrichment model:**

```
Lead enters Clay table
        |
        v
  [Provider A: Apollo]
  Found email? ----YES----> Verified? --YES--> Done
        |                       |
       NO                      NO
        |                       |
 

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (1)

CLAUDE.md

Gates applied: no_behavioural_pass.