Skip to content
Aakash GuptaAakash Gupta

Claude Code Advanced Masterclass in Under 81 Mins

Carl Vellotti is back. His first episode hit 30,000 views. This time he shows the advanced Claude Code masterclass for PMs. MCPs, Skills, GitHub automation, and end-to-end workflows from survey → PRD → tickets → automation. My Claude Code OS: https://www.news.aakashg.com/p/pm-os Full Writeup: https://www.news.aakashg.com/p/carl-vellotti-podcast-2 Transcript: https://www.aakashg.com/advanced-claude-code-for-product-managers-from-mcps-to-github-automation/ ---- Timestamps: 0:00 - Intro 2:14 - Why Claude Code Hit $1B ARR in 6 Months 9:35 - Ad Start 10:59 - Ad End: Setting Up MCPs 11:04 - Setting Up Linear MCP (Live Demo) 14:07 - Essential MCP Stack for PMs 21:25 - End-to-End PM Workflow Begins 28:00 - Skills Introduction 30:01 - Ad Start 30:53 - Ad End: Skills Deep Dive 38:00 - Image Generation with Gemini API 44:12 - Creating PRD from Survey Analysis 51:00 - Hooks Feature 55:30 - Creating Presentation from PRD 1:01:49 - Creating 19 Engineering Tickets in Linear 1:08:08 - GitHub Integration & Remote Worker Setup 1:19:39 - Outro ---- 🏆 Thanks to our sponsors: 1. Amplitude: The market-leader in product analytics - https://amplitude.com/session-replay?utm_campaign=session-replay-launch-2025&utm_source=linkedin&utm_medium=organic-social&utm_content=productgrowthpodcast 2. Pendo: The #1 software experience management platform - http://www.pendo.com/aakash 3. Jira Product Discovery: Move discovery and roadmapping out of spreadsheets - https://www.atlassian.com/software/jira/product-discovery 4. Miro: The all-in-one collaboration workspace - http://miro.pxf.io/PO4WZX ---- Key Takeaways: 1. Claude Code hit $1B ARR in 6 months - fastest product ever. Anthropic optimized for power users doing deep work. Fewer users, insanely deep usage. Carl: "I spend all day in Claude Code. It gets to the point where you never really have to leave." 2. MCPs connect Claude to everything in 2 minutes - Model Context Protocol invented by Anthropic. One command to install Linear, Google Workspace, Slack. Essential stack: documents first, task management second, communication third, data sources fourth. 3. End-to-end PM workflow takes one morning instead of one week - Survey creation → analysis → PRD → presentation → 19 tickets. All through MCPs. Carl didn't use templates. Opus 4.5 handled everything. 4. Skills are pre-built templates but don't always auto-trigger yet - Solution: specify explicitly. "Create presentation using your presentation skill." Build Skills for anything you do more than twice. That's the compound effect. 5. Real Google Slides, not images - Carl's presentation skill created 19 fully editable slides from PRD. Takes a few minutes because Claude creates slides in parallel. "This is saving you hours. We used to spend entire afternoons turning PRDs into decks." 6. GitHub turns Claude into remote worker - Create issues from your phone. @mention Claude. It works while you're away. Carl's journal is a private GitHub repo. Voice transcriptions → issues → Claude updates markdown. 7. Workflows beat agents for production - Level 1 workflow: 5,000 tokens, 40 seconds. Level 3 agent: 90,000 tokens, 90 seconds. Carl's rule: "If something can be expressed as code, code it. Leave agents for cognitive work." 8. Production best practices separate hobbyists from pros - Set error workflows. Add retry logic (3 attempts, 1-second delays). Pin data during development. Use reasoning effort appropriately. Write detailed tool descriptions. 9. Real challenge is building reusable workflows - Learning basics takes a day. First workflow takes hours. But having 50 workflows built over months means everything is automated. Carl: "Because I have workflows for all these things already built, I can do it all in one shot." 10. Tools improve faster than you can learn them - Carl: "By the time you see this, there might be Claude 5." Your workflows from today will 10x when better models drop. PMs who started 6 months ago aren't just 6 months ahead, they're 100x ahead because systems compound with every improvement. ---- 👨‍💻 Where to find Carl Vellotti: LinkedIn: https://www.linkedin.com/in/carlvellotti/ Twitter/X: https://x.com/carlvellotti Newsletter: The Full-Stack PM 👨‍💻 Where to find Aakash: Twitter: https://www.x.com/aakashg0 LinkedIn: https://www.linkedin.com/in/aagupta/ Newsletter: https://www.news.aakashg.com #claudecode #aipm #productmanagement ---- 🧠 About Product Growth: The world's largest podcast focused solely on product + growth, with over 200K+ listeners. 🔔 Subscribe and turn on notifications to get more videos like this.

Carl VellottiguestAakash Guptahost
Jan 12, 20261h 20mWatch on YouTube ↗

CHAPTERS

  1. 0:00 – 4:11

    Living in Claude Code: the promise of end-to-end PM workflows

    Carl and Aakash set the stage: Claude Code is becoming a place PMs can live all day, not just a chatbot. They preview an advanced masterclass focused on connecting tools, automating repeatable work, and building systems rather than one-off prompts.

    • Claude Code as a “single workspace” for PM tasks
    • Why advanced usage is about systems/workflows, not individual prompts
    • Preview: MCP connections, Skills, and GitHub automation
    • PM work is largely document-centric (Drive/Notion/Confluence)
    • Goal: reduce context-switching and manual UI clicking
  2. 4:11 – 8:29

    Why Claude Code scaled so fast: depth for power users vs generalist tools

    They unpack the reported $1B ARR milestone and why Claude Code keeps winning despite competition. The thesis: Anthropic focuses on deep work/coding workflows, creating highly retained power users, while competitors emphasize general or multimodal capabilities.

    • OpenAI as generalist; Google as multimodal leader; Anthropic as work/coding specialist
    • Claude Code’s “addictive” depth: more tasks stay inside one tool
    • Competitors often copy Claude Code’s already-shipped features
    • MCP as an open standard accelerant for ecosystem adoption
    • Skills emerging as another standard others start to emulate
  3. 8:29 – 11:04

    Productivity gap: turning repeated tasks into reusable workflows (rules/files)

    Carl explains why some users feel Claude Code is slow or unproductive: they operate step-by-step instead of codifying repeatable workflows. Advanced users identify recurring tasks, define rules/templates/files, and then run them in one shot.

    • Beginner pattern: ‘do this… now do this…’ vs workflow-first thinking
    • Define rules/templates so Claude can execute end-to-end
    • Use files as durable context and process definitions
    • Think in terms of a ‘system’ you’re building with Claude
    • Opus 4.5’s autonomy: keep going, unblock itself, validate progress
  4. 11:04 – 17:37

    MCP fundamentals: connecting Claude Code to external tools (Linear demo setup)

    They introduce Model Context Protocol (MCP) as the standard way to connect Claude Code to services like Linear, Google Workspace, Slack, and more. Carl shows how to install an MCP server via a terminal command, authenticate, and immediately gain tool actions inside Claude Code.

    • MCP = standard for LLM-to-service connectivity; install often via one command
    • Restart Claude Code to pick up MCP configuration changes
    • Authentication flow is required (browser approval)
    • Inspecting MCP tools reveals many available actions automatically
    • Demo goal: create real issues in Linear from Claude Code
  5. 17:37 – 20:09

    Essential MCP stack for PMs + context window tradeoffs

    They expand from Linear to what PMs should connect: document systems, support, analytics, CRM, and research tooling. Carl highlights a practical tradeoff: enabling many MCPs can consume context window, so toggle them intentionally.

    • High-impact MCPs: Google Drive/Workspace, Notion, Confluence, Slack
    • PM-critical integrations: Intercom/Zendesk, Dovetail, Salesforce, analytics tools
    • Mindset: always ask ‘does this tool have an MCP?’
    • Toggle MCPs on/off to manage context usage
    • Claude can suggest enabling a relevant MCP when it’s disabled
  6. 20:09 – 21:28

    API vs MCP: when scripts still matter (and why)

    Carl distinguishes MCP integrations from direct API calls. MCPs come with structured tools Claude already understands; APIs require more guidance and usually a script, but unlock access even when no MCP exists.

    • MCP gives a ready-made toolset; API requires instructions + code
    • APIs are ideal when no MCP exists or for specialized capabilities
    • Claude can write the script once; then reuse it as part of workflows
    • Two connectivity patterns: standardized tools vs custom integration code
    • Sets up later image generation and automation examples
  7. 21:28 – 24:38

    End-to-end PM workflow kickoff: survey creation → Google Docs publishing

    They begin the fictional ‘Taskflow’ calendar integration project with user research. Claude generates a survey from local context files, saves it as markdown, and pushes it to Google Docs—illustrating a ‘create locally, publish externally’ workflow.

    • Project narrative: Taskflow to-do app adding calendar integration
    • Claude writes survey using a template + feature context file(s)
    • Google Workspace MCP publishes output directly to Drive/Docs
    • Pro tip: Google Docs ‘paste from markdown’ for clean formatting
    • Foundation for downstream synthesis, PRD, deck, and tickets
  8. 24:38 – 33:13

    Survey response ingestion & synthesis: Skills concept and reliability caveats

    They pull survey responses into Claude Code and attempt to synthesize insights. This becomes a practical lesson in Skills: how they’re meant to auto-trigger on certain tasks, and how in practice you may need to explicitly call the skill to ensure consistent behavior.

    • Pull responses without analysis first, then synthesize separately
    • Skills = reusable, structured templates that should auto-trigger
    • Reality: auto-invocation can be inconsistent; explicit prompting helps
    • Queueing messages lets you chain steps while Claude works
    • Model choice affects speed (Sonnet/Haiku for lighter tasks)
  9. 33:13 – 37:08

    Building a Skills library: GitHub skills, marketplaces (plugins), and safety

    They show multiple ways to acquire and manage Skills: copy from GitHub repos, use plugin marketplaces, or create your own. They also warn about prompt injection when importing third-party skills, especially with ‘dangerously skip permissions’ enabled.

    • Sources: shared GitHub skill repos, trusted newsletters, plugin marketplace
    • Plugin install example: Anthropic ‘document skills’ pack
    • Skills include helpers like ‘skill creator’ and document generation tools
    • Security: prompt injection risk—vet skills before use
    • Practical usage: skills for podcast production, writing/editing, takeaways
  10. 37:08 – 44:07

    Image generation via Gemini API inside Claude Code (env keys + script workflow)

    Carl demonstrates using an API (Gemini/NanoBanana) from Claude Code to generate images, explaining why code-based workflows beat UI-only prompting. They cover .env key hygiene, script reuse, and how a new skill could wrap image generation into a repeatable PM artifact workflow.

    • Store API keys in .env; rely on .gitignore to prevent leaks
    • Claude can generate prompts and call image API from a script
    • Benefits: brand/style files, reusable prompt patterns, parallel variants
    • Idea: create a dedicated ‘NanoBanana prompting’ or image skill
    • Claude validates output and can self-check more effectively with Opus
  11. 44:07 – 50:22

    From research to PRD: drafting and publishing a requirements doc to Google Docs

    They convert synthesized survey insights into a PRD, again publishing it to Google Docs via MCP. The discussion emphasizes how templates and skills can standardize PRD structure and reduce repeated searching for ‘the latest good example.’

    • Claude reads survey synthesis and generates a structured PRD
    • Google Docs publishing as the shareable ‘source of truth’
    • PRD includes research evidence + requirements and rationale
    • Tip: add persistent info (like email) to claude.md for MCP defaults
    • Next step tees up visuals (user journey map) and stakeholder comms
  12. 50:22 – 50:50

    Deck generation from PRD: document skills create real editable slides

    They use Anthropic’s document skills to generate a full presentation from the PRD—producing real, editable slides rather than static images. Carl notes that explicitly instructing Claude to use the presentation skill improves reliability, and highlights Claude Code’s parallel sub-agent execution.

    • Using document skills: PowerPoint/Slides generation via Claude Code
    • Outcome: editable slide objects (not screenshots) with layout/design
    • Parallel slide creation via sub-agents speeds generation vs UI Claude
    • Best practice: explicitly call the presentation skill when needed
    • Future improvement: visual feedback loops (Playwright/Puppeteer) for iteration
  13. 50:50 – 58:36

    Hooks feature: automating actions around tool use and long tasks (notification example)

    Carl introduces Hooks—automation triggers at different stages of a Claude Code session (start/end, tool use, compaction, etc.). They attempt a Mac notification hook for task completion, discuss practical hook ideas, and acknowledge live-demo debugging realities.

    • Hooks trigger on events: session start/end, before/after tool use, compaction
    • Use case: notifications for long-running tasks like deck generation
    • More advanced ideas: auto-run tests, auto-export chat before compaction
    • Hooks enable ‘tight control’ workflows for repeatability and QA
    • Reality: setup may require debugging; feature still evolving
  14. 58:36 – 1:08:08

    PRD refinement and ticket creation: auto-generate prioritized Linear issues

    After incorporating stakeholder meeting notes, Claude generates a full set of engineering tickets directly in Linear with priorities and structured acceptance criteria. They stress that ticket quality tracks PRD specificity, and that connecting to a codebase could further deepen technical detail.

    • Update PRD with stakeholder constraints (e.g., compliance/SSO)
    • Create engineering tickets from PRD directly into Linear via MCP
    • Tickets include overview, requirements, technical considerations, acceptance criteria
    • Automatic prioritization (P1/P2) based on PRD content
    • Better PRD context and codebase access yield more technical tickets
  15. 1:08:08 – 1:20:34

    GitHub integration & ‘remote worker’ mode: @Claude on issues, plus Git basics for PMs

    They show how syncing a repo to GitHub enables Claude to work asynchronously via GitHub issues—useful when you’re away from your computer. Carl explains pull/push/branch/merge at a PM-friendly level and frames GitHub as a simple, powerful file store that Claude is ‘fiercely competent’ with.

    • Sync local work to GitHub so it’s accessible anywhere
    • Install/configure Claude GitHub app and trigger work via @claude on issues
    • Remote use case: capture a requirement on mobile; Claude updates repo before you return
    • Git basics: pull = download, push = upload; branches for safe changes; merge to main
    • Wrap-up mindset: keep experimenting; workflows compound over time

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.