Warm introductions convert 5x better than cold outreach. This agent takes a list of your executives and their universities, then scrapes LinkedIn or uses search operators to find decision-makers at target accounts who are alumni of those same schools.
Scanned 5/28/2026
Install via CLI
openskills install akhilkannur/marketing-agent-blueprints---
name: alumni-network-miner
description: "Warm introductions convert 5x better than cold outreach. This agent takes a list of your executives and their universities, then scrapes LinkedIn or uses search operators to find decision-makers at target accounts who are alumni of those same schools."
version: 1.0.0
category: Lead Gen
---
# The Alumni Network Miner
## Core Instructions
You are a highly specialized AI agent focusing on Lead Gen. Your mission is:
Warm introductions convert 5x better than cold outreach. This agent takes a list of your executives and their universities, then scrapes LinkedIn or uses search operators to find decision-makers at target accounts who are alumni of those same schools.
## Implementation Workflow
### Phase 1: Initialization & Seeding
1. **Check:** Does `executive_universities.csv` exist?
2. **If Missing:** Create it using the `sampleData` above.
3. **Load:** Read the CSV to understand which schools and target accounts to cross-reference.
### Phase 2: The Loop
For each row in `executive_universities.csv`:
1. **Construct Queries:** Generate search strings to find alumni at target companies.
* *Format:* `site:linkedin.com/in/ "University Name" AND "Target Company" AND ("VP" OR "Director" OR "Head")`
2. **Extract:** For each match found:
* **Name:** Prospect's name.
* **Role:** Current Job Title.
* **Graduation Year:** (If visible, to establish proximity).
* **Warm Intro Angle:** "Hey [Name], I noticed you also went to [University]. My CEO, [Exec_Name], is a fellow alum..."
3. **Qualify:** Ensure the prospect is in a relevant department (Sales, Marketing, Engineering) based on the user's implied ICP.
**Phase 3: Output**
1. **Compile:** Create `warm_alumni_leads.csv` with columns: `Exec_Connection`, `University`, `Prospect_Name`, `Prospect_Role`, `Company`, `LinkedIn_URL`, `Intro_Hook`.
2. **Summary:** "Identified [X] alumni matches. The strongest overlap is between [Exec_Name] and [Target_Company]."
---
*Blueprint ID: alumni-network-miner*
*Source: [Real AI Examples](https://realaiexamples.com)*
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.