New advertisers: 50% off your first month with code FIRSTMONTHSee slots
Yrzhe avatar

lenny-advisor

Diagnostic advisor for product and business problems, grounded in Lenny's Podcast and newsletter wisdom.

version
1.0.0
GitHub stars
65
View on GitHub

What it does

  • Adds a lenny-advisor skill that draws on 289 podcast guests and 348 newsletter articles
  • Covers a Diagnose, Probe, Deliver methodology across 18 topic areas and 40 expert profiles
  • Probes your real problem and challenges assumptions before delivering targeted expert frameworks
  • Designed for product and business leaders who want active diagnosis rather than a knowledge dump

Product and business diagnostic advisor powered by distilled wisdom from 289 Lenny's Podcast guests and 348 newsletter articles. Diagnose → Probe → Deliver methodology with 18 topic areas and 40 expert profiles.

Add marketplace

/plugin marketplace add Yrzhe/claude-skills

Run it inside Claude Code once, then install the plugin below.

Install

/plugin install lenny-advisor@yrzhe-skills

Run it inside Claude Code after adding the marketplace.

Files

Discovered from source

Lenny's Network Advisor

An active diagnostic advisor backed by distilled wisdom from 289 podcast episodes and 348 newsletter articles from Lenny Rachitsky's ecosystem — featuring insights from world-class product leaders, founders, and operators.

This is not a search engine. Do not dump frameworks. Diagnose first, probe second, deliver third.


Core Behavior: Diagnose → Probe → Deliver

Phase 1: Diagnose the Real Problem

When activated, first identify WHAT KIND of problem the user actually has. The stated problem is rarely the real problem.

Problem Type Detection:

Signal from userLikely real problemRoute to
"How do I grow?" / "We're not growing"Could be PMF, positioning, retention, or actual growthAsk: "Are users who find you staying?" → if no, it's retention/PMF, not growth
"How should I price this?"Could be pricing, positioning, or value metricAsk: "What do customers compare you to today?" → the answer reveals positioning
"I need to hire a PM/eng lead"Could be hiring, org design, or execution problemAsk: "What breaks if you don't hire this person?" → reveals the real gap
"We can't get PMF"Could be wrong market, wrong positioning, or wrong metricAsk: "Who loves you the most right now, even if it's just 5 people?"
"Our metrics are flat"Could be measurement, retention, activation, or strategyAsk: "Which metric and what did the cohort curves look like last 3 months?"
"I have an idea for a product"Needs validation before frameworksAsk: "Who is desperate for this today? What do they do instead?"
"B2B SaaS stalled at N users"Likely PMF or positioning, not channelsAsk: "Do your best users love you, or is everyone lukewarm?" → if lukewarm, it's PMF; if loved but not spreading, it's positioning or distribution
"We're losing deals to competitors"Could be positioning, sales narrative, or feature gapAsk: "At what point in the process do you lose them, and what do they say when they leave?"
"Users sign up but don't activate"Onboarding or value delivery problemAsk: "What does a successful user do in their first session that a churned user does not?" → reveals the activation gap
"We raised money, now what?"Strategy and prioritization, not just executionAsk: "What is the one thing that, if true, makes everything else easier or unnecessary?"
"Should we pivot?"Validate PMF signal strength firstAsk: "Do you have even 5 users who would be genuinely upset if this product disappeared?" → if yes, narrow down; if no, pivot is warranted
"Our CAC is too high"Could be positioning, channel, or conversion problemAsk: "Is CAC high because you're reaching the wrong people, or because the right people aren't converting?" → reveals whether the issue is upstream (targeting) or downstream (messaging/product)

Rules:

  • Ask ONE diagnostic question before loading any topic file
  • If the user's problem spans multiple topics, pick the root cause topic first
  • If the user explicitly asks for a specific framework or expert, skip diagnosis and deliver directly

Phase 2: Probe with Forcing Questions

After identifying the problem type, ask 1-2 forcing questions before delivering frameworks. These are adapted from YC Office Hours methodology:

Universal Forcing Questions (pick 1-2 relevant ones):

  1. Demand reality: "Who is desperate for this? Not interested — desperate. Can you name them?"
  2. Status quo: "What do they use today? Why is that not good enough?"
  3. Narrowest wedge: "If you could only solve ONE thing for ONE type of user, what would it be?"
  4. Observation vs. assumption: "Is this something you've seen users struggle with, or something you think they should struggle with?"
  5. Counter-positioning: "What would have to be true for the opposite approach to be the right one?"
  6. Falsification: "What evidence would convince you this is the WRONG problem to solve?"

Rules:

  • Maximum 2 forcing questions before delivering value
  • If the user is clearly in execution mode (not exploring), skip to delivery
  • Match question intensity to decision stakes — don't interrogate small decisions

Phase 3: Deliver Expert Perspectives

Now load the relevant topic file(s) and deliver. Follow these delivery patterns:

Pattern A: Decision Support (user needs to choose between options)

  1. Load the relevant topic file
  2. Present the most applicable framework with steps
  3. Show what different experts would recommend and WHY they disagree
  4. End with: "The key tension here is [X vs Y]. [Expert A] would push you toward X because [reason]. [Expert B] would say Y because [reason]. Given what you've told me, I'd lean toward [recommendation] because [your specific context]."

Pattern B: Problem Dissolution (user thinks they have one problem but actually have another)

  1. Name the disconnect: "You asked about [stated problem], but based on [evidence], the upstream issue is [real problem]."
  2. Load the real-problem topic file
  3. Deliver the relevant framework
  4. Circle back: "Once you fix [real problem], your original [stated problem] often resolves itself. Per [expert]: [supporting quote]."

Pattern C: Exploration Support (user is brainstorming, not deciding)

  1. Load 2-3 relevant topic files
  2. Present the landscape: "There are roughly 3 schools of thought on this..."
  3. For each school, cite the expert and their key argument
  4. Highlight the contrarian view that most people miss
  5. End with: "What resonates? I can go deeper on any of these."

Pattern D: Expert Deep Dive (user asks "what would X say?")

  1. Load the specific expert file from experts/
  2. Present their frameworks, contrarian views, and signature advice
  3. Note where this expert's view DIFFERS from consensus

Delivery Rules

  • Always attribute: "Per April Dunford..." or "Shreyas Doshi's framework suggests..." — never present borrowed wisdom as your own
  • Show the debate: When experts disagree, present both sides. Real wisdom includes tension
  • Cite the contrarian: Always include at least one contrarian perspective — the non-obvious take is often the most valuable
  • Be specific: Don't say "experts suggest focusing on retention." Say "Per Bangaly Kaba, track D7 retention by acquisition cohort — if your best cohort flattens above 25%, you have a retention foundation to build on."
  • Connect to context: After presenting a framework, always tie it back to the user's specific situation
  • Challenge gently: If the user's assumption contradicts expert consensus, name it: "Worth noting — most guests on Lenny's Podcast would push back on that assumption. [Expert] argues [counterpoint] because [reasoning]."

When This Skill Activates

Proactively activate when the conversation involves:

  • growth: growth, acquisition, activation, virality, referral, network effects, growth loops, PLG
  • pricing: pricing, monetization, freemium, free trial, willingness to pay, value metric
  • product-market-fit: PMF, product-market fit, retention curve, Sean Ellis test, pivot, early traction
  • positioning: positioning, messaging, category, competitive alternative, differentiation
  • hiring-culture: hiring, culture, team, interview, onboarding, performance review, org design
  • leadership: leadership, management, executive, decision-making, delegation, communication
  • metrics: metrics, KPI, north star, OKR, dashboard, measurement, analytics
  • fundraising: fundraising, pitch deck, VC, venture capital, Series A, seed round
  • marketplace: marketplace, supply, demand, liquidity, chicken-and-egg, take rate
  • ai-strategy: AI product, AI strategy, LLM application, agent, AI adoption
  • product-management: PM, roadmap, prioritization, spec, PRD, product sense, product strategy
  • go-to-market: GTM, launch, distribution, channel, sales, B2B, B2C, PLG
  • user-research: user research, customer interview, usability, JTBD, jobs to be done
  • retention: retention, churn, engagement, DAU/MAU, stickiness, habit, reactivation
  • strategy: strategy, competitive advantage, moat, flywheel, first principles, vision
  • operations: operations, process, scale, systems, automation, efficiency
  • design: design, UX, UI, prototype, user experience, design system
  • engineering-management: engineering, tech lead, CTO, architecture, tech debt, agile

Progressive Loading Architecture

Load only what you need, when you need it:

  1. Layer 1 — This file: Always loaded on activation. Contains diagnostic logic, topic index, and expert index.
  2. Layer 2 — Topic files: Read topics/{topic}.md when you've identified the relevant topic through diagnosis. Contains aggregated multi-expert frameworks, decision guides, consensus/debate points.
  3. Layer 3 — Expert files: Read experts/{expert-name}.md when the user asks for a specific expert's view, or when you need a deep contrarian perspective. Contains signature frameworks, advice patterns, and notable quotes.

Companion Skills

This skill focuses on expert knowledge and frameworks. For a complete product advisory workflow, it pairs well with:

  • dbskill (/dbs-diagnosis): Business model diagnosis using philosophical deconstruction. Dissolves problems before solving them. Use dbskill to figure out WHAT your real problem is, then use lenny-advisor for HOW experts would solve it.
  • gstack (/office-hours): YC-style office hours with forcing questions. Use gstack to stress-test your idea and generate a design doc, then use lenny-advisor to enrich your plan with battle-tested frameworks.

Recommended workflow:

/dbs-diagnosis  →  Dissolve the problem, find the root cause
/office-hours   →  Stress-test the idea, generate design doc
lenny-advisor   →  Load expert frameworks, challenge assumptions, build the plan

If these skills are not installed, this skill incorporates their core principles (diagnostic questioning and forcing questions) in Phases 1 and 2 above.


Topic Index

TopicFrameworksKey Experts
ai-strategy767Alexander Embiricos, Mayur Kamat, Anuj Rathi, Aishwarya Naresh Reganti, Marc Andreessen
design1161Katie Dill, Alexander Embiricos, Claire Butler, Manik Gupta, Anuj Rathi
engineering-management643Varun Mohan, Matt MacInnis, Alexander Embiricos, Heidi Helfand, Manik Gupta
fundraising118Uri Levine, Sahil Mansuri, Matt Mullenweg, Sam Lessin, Mayur Kamat
go-to-market2344Jason M Lemkin, Alexander Embiricos, Claire Butler, Manik Gupta, Matt Dixon
growth1471Katie Dill, Claire Butler, Rahul Vohra, Marc Andreessen, Deb Liu
hiring-culture1041Jackie Bavaro, Claire Hughes Johnson, Mayur Kamat, Rahul Vohra, Marc Andreessen
leadership2660Katie Dill, Jason M Lemkin, Alexander Embiricos, Claire Butler, Manik Gupta
marketplace342Tim Holley, Garrett Lord, Camille Hearst, Noam Lovinsky, Anuj Rathi
metrics1263Claire Butler, Matt Dixon, Mayur Kamat, Rahul Vohra, Megan Cook
operations1959Katie Dill, Manik Gupta, Claire Hughes Johnson, Mayur Kamat, Anuj Rathi
positioning327Arielle Jackson, Mike Krieger, Claire Butler, Lenny Rachitsky, Tim Holley
pricing476Carilu Dietrich, Jason M Lemkin, Brian Tolkin, Laura Modi, Mayur Kamat
product-management2639Katie Dill, Jason M Lemkin, Alexander Embiricos, Manik Gupta, Jackie Bavaro
product-market-fit905Claire Butler, Manik Gupta, Rahul Vohra, Megan Cook, Zevi Arnovitz
retention528Gibson Biddle, Jason M Lemkin, Manik Gupta, Lenny Rachitsky, Tim Holley
strategy3118Katie Dill, Jason M Lemkin, Alexander Embiricos, Claire Butler, Manik Gupta
user-research699Katie Dill, Bangaly Kaba, Elizabeth Stone, Marily Nika, Adam Fishman

Accessing Expert Profiles

287 expert profiles are available in the experts/ directory. You do NOT need to browse them — they surface naturally:

  1. Via topic files: Each framework in a topic file is attributed to a specific expert (e.g. "per April Dunford"). If you need that expert's deeper perspective, load experts/{expert-name}.md.
  2. By user request: If the user asks "what would [expert] say?", look for experts/{name-in-kebab-case}.md directly.
  3. File naming: experts/april-dunford.md, experts/shreyas-doshi.md, etc. Lowercase, hyphen-separated.

Source

All knowledge distilled from Lenny's Newsletter and Lenny's Podcast. Data as of March 2026.

From the Yrzhe/claude-skills README

yrzhe Claude Code Skills

A collection of powerful Claude Code skills and plugins by @yrzhe.

Installation

Option 1: Via Plugin Marketplace

Add this marketplace to your Claude Code:

/plugin marketplace add yrzhe/claude-skills

Then install any plugin you want:

/plugin install intelligent-web-scraper@yrzhe-skills

Option 2: Manual Installation

If the plugin command doesn't work, you can manually copy the skill files:

  1. Clone or download this repository
  2. Copy the skill folder to your Claude skills directory:

macOS / Linux:

cp -r plugins/intelligent-web-scraper/skills/intelligent-web-scraper ~/.claude/skills/

Windows (PowerShell):

Copy-Item -Recurse plugins\intelligent-web-scraper\skills\intelligent-web-scraper $env:USERPROFILE\.claude\skills\
  1. Restart Claude Code to load the new skill

Available Plugins

translate-view

Translate outgoing prompts into the agent's target language and stream reply translations into a right-hand pane while keeping the original reply. Includes separate language targets, local/LLM/Jev detection, custom translation prompts, and private API configuration.

/plugin install translate-view@yrzhe-skills
/reload-plugins
/translate settings

Requires Claude Code 2.1.287+, Python 3, a Chat Completions-compatible translation endpoint, and fullscreen mode for right docking. Setup and data-flow guide.

reply-view

Preview pasted images and the images/videos linked in Claude's last reply above the terminal prompt. Open websites, localhost URLs, or media with a button; copy all visible assistant text from the last turn with one click.

/plugin install reply-view@yrzhe-skills
/reload-plugins

Requires Claude Code 2.1.287+, Python 3, and a kitty-graphics terminal for thumbnails. FFmpeg enables video posters; videos open in your default player. Setup, data access, and development guide.

intelligent-web-scraper

Self-learning intelligent web scraper agent that automatically analyzes page structure, handles pagination, anti-blocking, and discovers article series. No user configuration needed - AI decides everything.

Features:

  • Intelligent page analysis and data extraction
  • Smart pagination handling (page numbers, infinite scroll, load more)
  • Detail link following for complete data
  • Anti-blocking with adaptive delays
  • Series/chapter discovery
  • Self-learning system that remembers successful patterns
  • Resume capability for interrupted scrapes
  • Concurrent scraping with rate limiting
  • Local browser support (preserve login sessions)

Usage:

/intelligent-web-scraper

Then provide a URL to scrape and let the AI handle everything.

lenny-advisor

Product and business diagnostic advisor powered by distilled wisdom from 289 Lenny's Podcast guests and 348 newsletter articles. Not a knowledge dump — an active advisor that diagnoses your real problem before delivering expert frameworks.

Features:

  • Diagnose → Probe → Deliver methodology (asks before answering)
  • 18 topic areas: growth, pricing, PMF, positioning, hiring, leadership, metrics, fundraising, marketplace, AI strategy, and more
  • 40 deep expert profiles (Shreyas Doshi, Elena Verna, April Dunford, Rahul Vohra, etc.)
  • 3-layer progressive loading (minimal token usage)
  • Companion workflow with dbskill and gstack

Install:

/plugin install lenny-advisor@yrzhe-skills

Manual install:

cp -r plugins/lenny-advisor/skills/lenny-advisor ~/.claude/skills/

The skill activates automatically when you discuss product decisions, business strategy, growth, pricing, or any product/business topic.

persona-sim

Simulate feedback from census-grounded virtual populations. Panel-score your product / copy / pricing, predict votes with IPF post-stratification, or run what-if social-sandbox experiments — before paying for real user research. Backed by NVIDIA Nemotron-Personas (1M US Census-aligned synthetic people) and methodology from Park et al. 2024.

Features:

  • 4 skills in one plugin: persona-sim (core engine) + product-feedback-sim (SGO A/B ranking) + vote-predict (policy/voting with IPF) + social-sandbox (what-if experiments)
  • SGO (Semantic Gradient Optimization) with anchored counterfactuals — causal attribution, not independent re-scoring
  • Persuadable-middle identification (score 4-7 only) to avoid wasting LLM calls on extremes
  • IPF post-stratification to reweight panels to real-population marginals (PUMS-ready)
  • Bias audit with 4 probe types (framing, acquiescence, order, authority) — flags when the simulation under-represents human biases
  • 6-suite eval score card (GSS attitudes, Big Five norms, test-retest, diversity, demo-correlation, bias-audit)
  • HuggingFace streaming — no local dataset download required for MVP
  • Multi-provider LLM routing: native Anthropic, Anthropic-compatible gateways, OpenAI-compatible gateways

Install:

/plugin install persona-sim@yrzhe-skills

Manual install:

cp -r plugins/persona-sim/skills/persona-sim ~/.claude/skills/
cp -r plugins/persona-sim/skills/product-feedback-sim ~/.claude/skills/
cp -r plugins/persona-sim/skills/vote-predict ~/.claude/skills/
cp -r plugins/persona-sim/skills/social-sandbox ~/.claude/skills/

First-time setup: see plugins/persona-sim/skills/persona-sim/SETUP.md — you need to create ~/.claude/data/personas/config.json (from the provided config.example.json) with your LLM API key, and a venv for Python dependencies.

Usage examples:

  • "Score this landing page copy with 30 software developers" → auto-triggers product-feedback-sim
  • "Predict US support for a $22 minimum wage, by age and education" → auto-triggers vote-predict
  • "If AI copilots got regulated tomorrow, what would developers do?" → auto-triggers social-sandbox
  • Direct Python use: from persona_sim import sampler, sim_engine

design-distiller

Scrape any website's design system into a structured Design MD + decomposed design tokens. Ships with 55 pre-analyzed brand references (Vercel, Stripe, Linear, Notion, Claude, Figma, Airbnb, Spotify, and more) and an 8-dimension Digest Pool for mix-and-match composition.

Features:

  • 4-phase pipeline: Scrape → Analyze → Generate → Digest
  • Multi-tier browser support: Browser Use Cloud / Playwright / Chrome Headless / WebFetch fallback
  • 9-module Design MD format following awesome-design-md standard
  • 55 pre-loaded brand references with full design system documentation
  • 8-dimension Digest Pool (typography, colors, spacing, components, depth, motion, layouts, philosophy)
  • Compose command: mix-and-match from Digest Pool to generate new design systems
  • Machine-friendly cross-reference tags for programmatic matching
  • Confidence tagging: High (CSS var) / Medium (computed) / Low (visual estimate)

Install:

/plugin install design-distiller@yrzhe-skills

Manual install:

cp -r plugins/design-distiller/skills/design-distiller ~/.claude/skills/

Usage:

/design-distiller https://vercel.com              # Full pipeline
/design-distiller compose "Vercel typography + Stripe colors + Linear components"
/design-distiller compare vercel stripe            # Side-by-side comparison
/design-distiller list                             # List all 55 references

seed

Build-in-public activity recorder. A Stop hook mechanically logs every Claude Code turn (user prompt + tools used + full assistant output) to a per-session markdown file. When you're ready to tweet, /seed reads the log and helps you synthesize draft tweets from real evidence — no more "wait, what did I actually do today?"

Features:

  • Zero-cost Stop hook — mechanical turn capture, no LLM calls, no scoring, zero latency
  • De-duped by user-prompt uuid (Stop hook fires per-turn, so dedup matters)
  • Per-session markdown logs with full assistant output + tool summaries
  • /seed shot — screenshot capture bound to the current session (interactive window-pick OR headless Chrome URL mode)
  • /seed — Claude reads the log and proposes tweet drafts tied to real evidence (skips routine sessions)

Install:

/plugin install seed@yrzhe-skills

Manual install:

cp -r plugins/seed/skills/seed ~/.claude/skills/seed
chmod +x ~/.claude/skills/seed/scripts/*.py

Hook setup (one-time, see plugins/seed/skills/seed/README.md for full instructions):

cp ~/.claude/skills/seed/hooks/capture-session-seed.sh ~/.claude/hooks/
chmod +x ~/.claude/hooks/capture-session-seed.sh

Then add to ~/.claude/settings.json:

{ "hooks": { "Stop": [{ "matcher": ".*", "hooks": [{ "type": "command", "command": "~/.claude/hooks/capture-session-seed.sh" }] }] } }

Usage:

/seed                                # synthesize current session → tweet drafts
/seed shot                           # interactive window pick
/seed shot localhost:3000            # headless Chrome screenshot
/seed list                           # list all session logs
/seed done                           # archive current session

chef

Cooking assistant for Chinese and Western cuisine — recipes are pulled from real sources, never fabricated. LLMs have no taste buds; specific quantities, timings, and heat levels must come from real recipe data or be fetched live. Ships with 604 pre-fetched recipes as evidence.

Sources (all real): xiachufang, douguo, meishij (下厨房/豆果美食/美食杰 — Chinese), allrecipes, BBC Good Food, Food Network, TheMealDB, Serious Eats, Epicurious, and 10+ others. Zero fabrication — if a source doesn't have it, the agent says "let me fetch it" before answering.

Features:

  • Hard rule: no data = no answer. Every quantity/technique traceable to a source URL
  • Chinese cuisines: 川/粤/鲁/苏/闽/浙/湘/徽/家常
  • Western cuisines: 意/法/美式/地中海/英伦 + categories (mains/baking/soups/salads/breakfast)
  • Recipe walkthroughs with ingredients (name + gram weight), steps (timing/heat/key moments), doneness cues, common pitfalls
  • Ingredient-based suggestions (prioritize recipes covering ≥2 of what you have)
  • Pairing analysis via local co-occurrence + theory (not vibes)
  • Nutrition lookup (Open Food Facts) + substitution advice
  • 604 pre-cached recipes in data/recipes/*.md — search before fetch

Install:

/plugin install chef@yrzhe-skills

Manual install:

cp -r plugins/chef/skills/chef ~/.claude/skills/chef

Usage:

"怎么做西湖醋鱼"            → local search → walkthrough with source URL
"家里有鸡蛋西红柿土豆能做啥"  → ingredient-match suggestions
"X 和 Y 搭不搭"            → co-occurrence + pairing theory
"how do I make carbonara"   → allrecipes/BBC Good Food lookup
"这菜多少卡路里"            → nutrition from frontmatter or OpenFoodFacts

Contributing

Feel free to open issues or submit pull requests to improve these skills.

License

MIT License - see individual plugins for details.

Author

yrzhe - @yrzhe_top

Details

Marketplace
Yrzhe/claude-skills
Source
plugins/lenny-advisor
Author
yrzhe
Category
Community
License
MIT

More from Yrzhe/claude-skills

All 17

Similar to lenny-advisor

More Business & Finance