saurabhshuklagrowisto

Saurabh AI Systems — AI skill for Claude Code

AI community

AI architect for GTM and martech.

How to install Saurabh AI Systems

This entry records only its repository, not the path inside it, so there is no exact command to give. Open saurabhshuklagrowisto/saurabh-ai-systems and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Saurabh AI Systems does

AI architect for GTM and martech. I design and ship production agentic systems for B2B sales and marketing: lead scraping and scoring with an eval gated learning loop, autonomous CRM enrichment, ABM pipelines, live dashboards that refresh themselves, MCP servers and Claude skills. Built at Growisto.

Alternatives in AI

Firecrawl MCP Server — 🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM c 6.1k ★
Gtm Engineer Skills — Claude Code skill for improving website AEO (AI Engine Optimization) and GEO (Generative Engine Optimization) 761 ★
Ooda Subagents — OODA Loop AI Agents - Observe, Orient, Decide, Act framework for systematic problem-solving 170 ★

README

Saurabh Shukla

AI Architect · Automation and AI · GTM Engineer

Mumbai · Open to remote roles

**I design and run the agent systems that go to market: outbound infrastructure, autonomous CRM agents, MCP servers, and the guardrail layer that keeps them safe in production.**

[![Portfolio](https://img.shields.io/badge/Portfolio-shivsaurabh.netlify.app-2b6cb0?style=flat-square)](https://shivsaurabh.netlify.app) [![LinkedIn](https://img.shields.io/badge/LinkedIn-shivsaurabh-0a66c2?style=flat-square&logo=linkedin&logoColor=white)](https://linkedin.com/in/shivsaurabh) [![Email](https://img.shields.io/badge/Email-contact-d93025?style=flat-square&logo=gmail&logoColor=white)](mailto:officialsaurabhshukla@gmail.com) [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg?style=flat-square)](./LICENSE)

TL;DR

I am a GTM engineer. I build and operate the systems a revenue team actually runs on: autonomous CRM agents, cold email infrastructure at scale, agent workspaces and MCP servers, ABM scoring pipelines, eval-gated Claude skills, and the guardrail layer that stops any of it from doing something expensive.

The work sits across three jobs that usually go to three people. Architecture, because someone has to decide where the model ends and the process begins. Automation, because the system has to run without me at 9am on a Sunday. Go to market, because none of it counts until it books a meeting.

Day to day that means Claude and GPT on the model side with Astra for image, video and same-day site builds, Close CRM and Zoho on the CRM side (HubSpot and Salesforce are the same objects and the same integration surface), SalesBlink, Smartlead, Lemlist, Leadbird, Sendy and Apollo on the outbound side, Clay and Prospectoo for enrichment, n8n and Python holding it together. The full table with the reasoning behind each choice is in [docs/stack.md](./docs/stack.md).

This repo is the proof. Every system here is either runni