Roy Murphy

6 must-read books to understand AI better I've put together a shortlist of the best books to learn more about AI. For more AI trends, resources and ideas go here lnkd.in/exkMZneM

@David_TornAI CLAUDE

I built 131 Claude skills for outbound, content, LinkedIn, SEO, and growth—inside one system. 131 skills. 11 domains. One /bootstrap. And the result? Prospects keep saying: "Your outreach actually sounds like you." That’s not better prompting. That’s system design. ▶️ The foundation (set once) → /bootstrap trains Claude on your brand, voice, and ICP → ICP doc is loaded once—used everywhere automatically → Brand + voice layer ensures every output sounds like you, not a template Most teams skip this. Then wonder why everything feels generic. ▶️ The skill layer → Outbound + email for personalized sequences at scale → LinkedIn, X, YouTube across every format → Content + copy that matches your actual voice → Analytics + research for real signal detection → Strategy for ICP, messaging, and positioning (47 growth + product skills alone) ▶️ The execution layer → Plain-language inputs → auto skill activation → Cross-referencing across brand, voice, and ICP → Built-in grading: If it sounds generic → it’s not specific enough yet Rule: If it could describe another company, it’s not done. ▶️ Repurpose One proven outbound system → Turned into content, SEO, positioning, paid Not copy-paste. Cross-referenced intelligence. ▶️ Maintain → /bootstrap refresh updates everything instantly → Monthly voice updates → Quarterly domain audits The system compounds over time. ▶️ Delivery Runs on Claude Code, Claude Cowork, or any agent-based setup. Flow: Bootstrap → Detect → Activate → Cross-reference → Draft → Grade → Repurpose → Refresh Your skill library isn’t a tool. It’s your GTM brain. Reply “CLAUDE” and I’ll send the full breakdown 👇

@TommiPedruzzi AI

I’m shocked more people aren’t making $10,000/month with Claude. How? AI publishing. I shared this with a retiree... he’s now making $15K every month. I’ve spent 6+ hours breaking down: • The prompts • The exact workflow • The niche research method • How to turn Claude into a content factory If you want the full breakdown, comment 'AI' and I’ll send it over.

@Zephyr_hg IDEAS

50 AI businesses you could start this weekend. Pick one. Every idea comes with a revenue path, MVP scope, and exact tech stack so you're not guessing what to build or how it makes money. Organized into 5 categories: vertical agents, content tools, data infrastructure, edge AI, and services. Medical billing agents. Construction safety cameras. Prompt injection firewalls. Drone inspectors for solar farms. Each one scoped lean enough to validate in 48 hours with a simple ad or DM campaign. No more staring at tech trends trying to figure out where the money actually lives. Pick the lane that fits your skills and ship the tiniest possible version before your competition finds these ideas. Comment "IDEAS" and I'll DM it to you (must be following)

@yanndine MARKETING

I put the entire Claude Design and Claude Skills Marketing Playbook into ONE Notion doc. 6 sections. No fluff. - The three types of Claude skills and the exact build order: brand skills first to define voice and visual identity, function skills second for every repeated marketing task, specialty skills last - plus the project folder structure covering context, skills, templates, outputs, and CLAUDE.md before building anything - How to extract your brand design system in Claude Design in 10-15 minutes and export it as a portable skill file that every other marketing skill calls automatically so every output is on-brand without re-explaining your design system each time - Four function skills to build once and trigger with a slash command: campaign planning that researches via Perplexity MCP and builds a branded slide deck, social content matched to your best-performing posts, carousel design that exports individual slides ready to publish, and animated video that proposes a storyboard before generating any motion graphic - Multi-skill orchestration with routing rules in CLAUDE.md so one campaign brief triggers research, content, creatives, and landing page in the right order with parallel sub-agents handling independent workstreams simultaneously - Notion skills library with auto-sync routine pushing new and updated skills to your team every week at 9am so nobody is manually downloading and reinstalling skill files - Notion Kanban task board setup so teammates drop tasks in, Claude picks them up, assigns the right skills, executes, updates status to Complete, and logs output file paths without anyone writing a prompt This is the setup I would have KILLED for before briefing designers on assets Claude produces in minutes, calling skills one at a time when one brief should run the whole sequence, and manually distributing updated skill files to teammates every time something changed. Like + comment "MARKETING" and I'll send it over (must be connected for priority access)

@AdamrahmanGTM TAM

Just open-sourced the Claude Code skill we use to build every client's TAM. One command. Three MCP servers. End-to-end pipeline from ICP to campaign-ready CSVs. The refreshed 2026 GTM playbook covers: 1 → The code-first revolution (2022 spreadsheet stack vs. 2026 terminal stack) 2 → The 3-stage Scope · Score · Ship system 3 → Data source matrix with CLI commands for every tool 4 → Message frameworks that convert (PQP + PVP, copy-paste formulas) 5 → Platform strategy matrix, AI-first tools ranked 6 → The /tam-map skill, every step in one file 7 → MCP server stack (.mcp.json ready to drop in) 8 → Implementation timeline, days not weeks Bonus: anti-patterns gallery. Six ways to torch your TAM before your first send. 🔥 Like + comment "TAM" and I'll DM you the GitHub repo. [ Must be following to receive ]

@yanndine ROUTINES

I put the entire Claude Routines Playbook into ONE Notion doc. 8 sections. No fluff. - What routines actually are and how they replace n8n: same event fires, Claude reads natural language instructions, output lands in Slack or your CRM without a single drag-and-drop node built - Full routine setup in under 5 minutes: name, description as a numbered SOP, model selection, environment config, trigger, and connectors all from one screen - The three trigger types and when to use each: schedule for fixed cadence workflows, API call for passing data payloads from Claude Code, webhook for firing automatically when Fireflies finishes a transcript or a prospect signs a proposal - How to connect Gmail, Slack, and every other tool via OAuth once and reference them by name in every routine prompt forever - How to write a routine prompt that works every time without you watching: numbered SOP structure, explicit finish line, named connectors, and the three things that make outputs unpredictable - Three production routines worth stealing: daily inbox drafter running at 5:10am, transcript to proposal firing from a Fireflies webhook, and a field monitor sending signal digests to Slack in under 2 minutes of setup - How to convert any existing n8n workflow into a routine by pasting the JSON into Claude Code and letting it translate the node chain into a natural language prompt automatically - The decision rule for routines vs n8n: when to build new, when to convert, and when high-frequency mechanical workflows should stay exactly where they are This is the setup I would have KILLED for before spending hours building n8n node chains for workflows that should have taken 5 minutes to describe in plain language and wire to a connector. Like + comment "ROUTINES" and I'll send it over (must be connected for priority access)

Coding adoption way out in front - and of course it has downstream effect on everything else

@mikefutia PROMPTS

I just built a Claude prompt library that runs your entire DTC marketing operation 🤯 100+ prompts organized by function: competitor research, creative briefs, ad copy, hooks, landing pages, performance analysis, customer review mining, and more. Perfect for DTC brands and agencies who are still prompting Claude from scratch every time they open a new chat, rewriting the same context, and getting generic output that sounds like every other AI-generated ad. This prompt library eliminates the entire loop: → Competitor Research: scrape and analyze competitor ads, extract winning hooks, map creative strategies, build competitive battlecards → Creative Briefs: generate data-backed briefs from ad performance, write iteration briefs, new concept briefs, test plans → Ad Copy & Hooks: 20 hooks across 10 frameworks, full ad copy variations, persona-specific angles, fatigue-busting rewrites → Landing Pages: audit any landing page against DR best practices, clone high-converting advertorial structures, write product page copy → Performance Analysis: audit Google Ads accounts, find wasted spend, build visual dashboards, weekly narrative reports → Customer Intelligence: mine reviews for ad copy language, extract objections, find unexpected use cases, build persona cards from real data → SEO & Content: find keyword gaps, write content in your brand voice, optimize product listings for AI shopping (ChatGPT, Gemini) → Email & SMS: launch sequences, weekly newsletters, abandoned cart flows, post-purchase nurture No more blank-page prompting. No more re-explaining your brand every session. No more generic AI output that sounds like a template. What you get: →100+ copy-paste prompts organized by the 8 functions DTC teams actually run →Every prompt pre-loaded with the context structure Claude needs to give you real output →Prompts that reference your brand voice, your ICPs, and your real data — not generic placeholders →A living library you can customize once and reuse across every campaign I put together the full prompt library as a single downloadable playbook: organized by section, ready to copy-paste into Claude today. Want it for free? > Like this post >Comment "PROMPTS" And I'll send it over (must be following so I can DM)

@swadeshkumar_ CODE thanks

I put the entire Claude Code GTM Engineering Playbook into ONE Notion doc. 8 sections. No fluff. - How to get set up correctly from day one: Pro plan, terminal install across Mac, Linux, and Windows, GUI install via Antigravity or VS Code, and bypass permissions mode - What to put in your project brain file, what to leave out, and how to get Claude to update it automatically when it keeps making the same mistake - How to run plan mode step by step and when to skip it for simple tasks - How to build a skill file from scratch, fix one that keeps failing, and install 5 GTM skills worth building first: lead scraping, email labeling, proposal generation, outbound sequence writing, and client onboarding - MCP install process, token cost checks after every install, the best MCPs for GTM work, and how to cut token usage by 50 to 100x by converting MCPs into skills - Sub-agents and agent teams: the 3 cases where they earn their cost, reliability math for parallel runs, and how to enable parallel variant exploration - What is eating your context before you type anything, how to use /compact and /clear correctly, and model selection for parent vs sub-agents - Modal deployment: any skill as a live URL in under 2 minutes, form interface setup, and connection to n8n, Make, or Zapier This is the setup I would have KILLED for before spending months piecing together how to actually get productive in Claude Code from documentation, YouTube tutorials, and scattered GitHub threads. Like + comment "CODE" and I'll send it over (must be connected for priority access)

@swadeshkumar_ CODE

@AlfieJCarter CODE

I put the entire Claude Code GTM Engineering Playbook into ONE Notion doc. 8 sections. No fluff. - How to get set up correctly from day one: Pro plan, terminal install across Mac, Linux, and Windows, GUI install via Antigravity or VS Code, and bypass permissions mode - What to put in your project brain file, what to leave out, and how to get Claude to update it automatically when it keeps making the same mistake - How to run plan mode step by step and when to skip it for simple tasks - How to build a skill file from scratch, fix one that keeps failing, and install 5 GTM skills worth building first: lead scraping, email labeling, proposal generation, outbound sequence writing, and client onboarding - MCP install process, token cost checks after every install, the best MCPs for GTM work, and how to cut token usage by 50 to 100x by converting MCPs into skills - Sub-agents and agent teams: the 3 cases where they earn their cost, reliability math for parallel runs, and how to enable parallel variant exploration - What is eating your context before you type anything, how to use /compact and /clear correctly, and model selection for parent vs sub-agents - Modal deployment: any skill as a live URL in under 2 minutes, form interface setup, and connection to n8n, Make, or Zapier This is the setup I would have KILLED for before spending months piecing together how to actually get productive in Claude Code from documentation, YouTube tutorials, and scattered GitHub threads. Like + comment "CODE" and I'll send it over (must be connected for priority access)

@AdamrahmanGTM GTM

AI does 90% of our GTM execution. Not prompts you copy-paste into ChatGPT. 12 executable workflows that Claude Code runs autonomously - from first research query to live campaign. Massive unlock for speed to winning GTM across a diverse client base. > 9-dimension market research > TAM database building > ICP scoring > full GTM strategy generation > prospect worldview mining > hidden signal discovery > message-market fit testing > waterfall contact enrichment > local business enrichment (Maps to verified emails) > campaign launch from CSV > 5 Variables performance diagnosis > structured campaign debriefs Clone the repo. Add your API keys. Run it. Reply "GTM" and I'll send you the link.

@mikefutia OS

I just built a Brand Operating System inside Claude Cowork 🤯 A connected system of files that every skill automatically reads from, so your hook writer, brief generator, and script writer all speak in your exact brand voice. All inside Claude Cowork. Perfect for DTC brands and agencies tired of generic AI output that sounds like every other brand in their category. If you're opening a new Claude chat and re-explaining your brand, re-pasting your voice guidelines, and re-describing your customers every single time, a Brand OS fixes the entire loop: → Build 3 foundation files once per brand → Every skill you create reads from the Brand OS automatically → Hook writer pulls your voice + customer pain points → Brief generator pulls your positioning + angles → Script writer pulls the brief + brand DNA → Every output is calibrated to your brand on the first pass No re-briefing Claude on every chat. No editing for an hour to fix generic AI phrasing. No creative that sounds like it could belong to any brand. What you get in the playbook: → The exact Brand OS file structure I use → Templates for all 3 files you can fill in for any brand → The architecture that makes every Claude skill 10x sharper → The exact setup for agencies running a Brand OS per client For agencies: this is how you build a perfect, reusable knowledge base for every client on your roster. Set up the Brand OS once per client, and every campaign after that is already calibrated. I put together a full playbook with the file templates, the architecture, and the exact setup process so you can build your own Brand OS for your brand or your clients. Want it for free? > Like this post > Comment "OS" And I'll send it over (must be following so I can DM)

@trq212 Yep sounds good. Using extensively in GTM, strategy, presentations and more

I want to do some streams where I work with non-technical people using Claude Code to figure out how they might be able to improve their process. My feeling is that just a few tips could make a big difference in efficiency. Any mutuals interested?

@yanndine BIBLE

I'll probably regret leaking this but screw it: Full guide on how to run Claude Code as a GTM engineering system. Setup, CLAUDE.md, skills, MCP servers, parallel agents, slash commands, and the exact GTM workflows to actually build. For 24h, I'm sending it to EVERYONE who likes + comments "BIBLE" (must be connected for priority access)

@yanndine COWORK

I just gave Claude control of my cold email campaigns. Here's what happened: Most cold email managers are stuck in the same loop: ☒ Log into Instantly manually every day ☒ Check metrics one sequence at a time ☒ Pause underperformers by hand ☒ Write new copy with no data to guide it Until we built the opposite. And I just recorded a full walkthrough breaking down the complete system: → How Claude logs into Instantly, reads your dashboard, and flags what's broken → How to set rules so Claude pauses sequences under 1% reply rate automatically → How Claude scales winning sequences by 20% volume without touching a thing → How Claude rewrites losing email steps using only your best-performing copy as reference → How Claude pulls weekly reports and saves them to a local folder - zero dashboard diving This isn't theory or fluff. I'm showing the exact prompts, the folder structure, the permission setup, and the confirmation flow Claude uses before making any changes. The wildest part? We do it all from one Mac with the Claude desktop app. (No extra tools. No dev work. No agency.) No bloated tech stack. No extra headcount. No manual ops work eating your week. This system is built on Computer Use - Claude sees your screen, navigates your tools, and asks for confirmation before anything risky. You stay in control. Claude does the work. Want the full breakdown? Follow me Reply "COWORK" I'll send it straight to your DMs.

@yanndine GTM

A two-person GTM team at a Series B SaaS company closed $2.4M in pipeline in one quarter. No SDRs. No demand gen agency. No paid ads. Signal-based outreach. Intent scoring. AI-sequenced follow-up. Automated reporting. Two GTM engineers running the whole motion - for one quarter. I pulled it apart. Compared it to every system we've built across the GTM teams we've worked with. Then asked myself one question: If I had to reverse engineer this from scratch - what would it actually look like? Turns out the architecture isn't that complicated. I mapped the whole thing into a step-by-step playbook you can upload directly to any LLM. It walks you through building your own version from GTM strategy to fully AI-powered execution. Comment "GTM" and I'll send it over.

@AdamrahmanGTM Prompts thanks

AI does 90% of our initial GTM strategy formulation all in just these 6 prompts. This has been a MASSIVE unlock for speed to winning GTM for our diverse client base. (Comment "Prompts" and I'll DM you a document with all of the prompts.) Here’s what these prompts cover: 1/ Deep Market Research This prompt pulls all relevant information specific to what would be useful for GTM knowledge for the company you're looking to develop a GTM strategy for. The purpose of generating this information is to use it as context for future prompting. 2/ TAM Mapping This prompt will discover all relevant industries & sub-industries that your company could work with, plus statistics on general market size, industry value, and industry growth rates. Outputs from this prompt will also be useful context for other prompts. 3/ ICP Validation This prompt will develop ICPs from the industries uncovered from the TAM Mapping output. It will score each industry segment from highest to lowest priority, find the best fit personas from each industry segment, outline their specific needs & pain points, and craft some messaging ideas around this information. 4/ Company Account Sourcing This deep research prompt will find unique databases for any set of company data that you are looking for. From online directories, to scraping methods, to other niche paid databases - this prompt will give you a list of best fit options for your particular targeting case. 5/ Targeting Keywords Generation This prompt will generate a list of relevant industry and persona keywords to use for specific database filtering for when your developing lists in tools like Apollo. These keywords are typically a lot more accurate than using the general industry filtering. 6/ Messaging Creation This prompt will create multiple email script variations based on the context generated from previous prompts. It'll create unique variations on length of the emails, different offers, pain points, case studies, and complexity. Want these copy-and-paste prompts for yourself? Comment "Prompts" and I'll DM you a document with all of the prompts. (Must be following to receive)

@jspujji GA

My companies close $20M/year on 30-minute Zoom calls. I had an ex-McKinsey consultant reverse-engineer exactly how: – Sales call recordings – Sales scripts – Lead gen systems Reply with “GA” and I'll DM you the copy. Free.

@techxutkarsh COWORK

Claude Cowork is f*cking ridiculous 🤯 One prompt → competitive research, creative briefs, 15 hook variations, and a full performance dashboard. All saved as real files on your computer. All inside Claude Desktop. If you're spending hours every week copy-pasting between tools, pulling competitor ads manually, writing briefs from scratch, and building reports in spreadsheets ... Claude Cowork eliminates the entire loop: → Point it at your project folder with brand voice + context files → It asks YOU clarifying questions instead of guessing → It builds a multi-step plan and executes while you step away → It creates real .docx, .xlsx, .pptx files — not chat responses → It connects to Slack, Google Drive, Airtable, and 50+ tools live No copy-pasting between tools. No babysitting the AI mid-task. No downloading and re-uploading files. What you get: → Competitive research synthesized into actionable creative angles → Ad briefs, hooks, and scripts generated in your brand voice → Interactive HTML dashboards built from your own customer data → Weekly performance reports created while you're getting coffee Built 100% inside Claude Desktop with skills, plugins, and connectors. I put together a full DTC playbook: 10 workflows with copy-paste prompts, the exact setup process, and the weekly operating rhythm I use. Want it for free? > Like this post > Comment "COWORK" And I'll send it over (must be following so I can DM)