saurabhshuklagrowisto
UserAI 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.
Categories
Indexed Skills (12)
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
abm-account-brief
Generates a hyper-personalized ABM account brief and outbound hook for a target B2B account. Takes a company domain plus optional context (recent signals, persona, ICP fit notes) and returns a structured brief with company snapshot, three personalization hooks ranked by strength, a recommended channel (email / LinkedIn DM / LinkedIn InMail), a 60-word cold email draft, and a confidence score. Use when researching a target account before outbound, when refreshing a stale prospect, or when generating hooks at scale across a target account list.
aeo-content-brief-generator
Turns a "content" gap (a buyer question with no owned page answering it) into a writable brief -- the question's shape (how-to, best-of, comparison, definition), the matching schema type, a fact-grounded direct-answer opener, and a section outline with a word-count target. Never fabricates data -- when no real facts are supplied it scaffolds an explicit [INSERT] placeholder instead of inventing a claim. Use this on the `content`-type fixes returned by the AEO/GEO Improvement Bot, or on any raw list of buyer questions that need an AI-answer-shaped page written.
ecommerce-conversion-audit
Audits a D2C / eCommerce store for conversion leaks along the path to purchase and returns findings ranked by revenue impact. Takes a URL plus observed elements across the product page, cart, and checkout (imagery, price clarity, add-to-cart, guest checkout, steps, payment options, shipping surprises, reviews, returns, urgency, mobile) and returns P0/P1/P2 findings, each with what was found, why it costs revenue, a concrete fix, and how to measure it. Use before a store redesign, when the add-to-cart or checkout conversion rate is low, or to turn a store review into a prioritised action list. This is the D2C counterpart to the B2B website-conversion-audit skill.
lead-nurture-sequencer
Stages leads by real engagement signal (opens, clicks, replies, meetings booked, unsubscribes, days since last touch) and decides the next nurture action for each -- what to send, and how many days until it's due. Enforces the suppression/cooling rules that keep automated nurture from talking over a real reply or a booked meeting, or re-touching someone who unsubscribed. Use to run or audit an email/lifecycle nurture cadence, decide who's due for a touch today, or check that automation isn't stepping on human-handled leads.
website-conversion-audit
Audits a B2B website page for conversion leaks from a buyer's lens and returns findings ranked by revenue impact. Takes a URL plus a set of observed page elements (hero message, CTAs, form fields, trust signals, mobile behaviour) and returns P0/P1/P2 findings, each with what was found, why it costs conversions, a concrete fix, and how to measure the fix. Use before a redesign, when diagnosing why demo requests are low, or to turn a landing page review into a prioritised action list.
landing-page-generator
Turns a one-paragraph event/webinar brief into a publish-ready landing page, either a WordPress/Elementor section structure or a standalone custom-HTML page, plus a matching set of marketing collaterals. Reads a brand kit on every run so every output is on-brand. A human reviews and publishes; the skill never publishes on its own.
caveman
Ultra-compressed communication mode. Cuts output tokens 65% (measured) 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.
figma-handoff
Use this skill EVERY TIME a Figma URL is mentioned or pasted in any message. Triggers on any figma.com link, any mention of "figma", or any request to implement/build/code a design. Before writing any code or reading any design, this skill intercepts the request and asks two required questions: (1) which tech stack — React or Shopify Liquid, and (2) whether to show the Figma design system first or proceed directly. Do NOT skip these questions. Do NOT write any code before both are answered. This is mandatory for all Figma-related implementation tasks at Acme.
transcript-summary
Analyze a single B2B sales-call transcript and produce a structured deal-stage diagnostic for [Your Company] using the 5 Agreements framework (Mark Kosoglow / 30 Minutes to President's Club), layered with SPIN discovery notes and a BANT scorecard. Use this whenever someone pastes or uploads a sales-call transcript and asks to "summarize this call", "analyze this deal", "where does this deal stand", "score this call", "is this proposal-ready", "run the 5 agreements on this", or shares a discovery/sales call and wants to know the true stage. This is a DEAL-STAGE VERDICT, not a CRM log — if the user wants a BANT-style note for logging into Zoho CRM, use the crm-note skill instead; if they want an honest assessment of how far the deal has actually progressed, use this skill.
aeo-llm-visibility-audit
Measures whether a brand shows up when buyers ask AI assistants (ChatGPT, Perplexity, Gemini) about its category, and turns the gaps into a content plan. Takes a brand name and a set of real buyer questions, checks which brands each engine names, and returns a share-of-voice score, the competitors winning the answers, and the exact questions where the brand is invisible. Use to audit AI/answer-engine discoverability (AEO/GEO), to prioritise content that AI assistants will cite, or to track share of voice in AI answers over time.
competitor-teardown
Turns a messy competitive landscape into a scored positioning matrix and a recommended wedge. Takes your brand plus 2-5 competitors and a set of buyer-decision dimensions, each scored 0-5 per player, and returns where you win, where you lose, the category whitespace nobody owns, and the sharpest wedge to position on. Use before writing positioning or messaging, before a launch, or when a rep keeps losing deals to the same competitor and you need to know why.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.