Lenny Skills is a collection of product-management and engineering workflows for Claude Code and other AI agents, covering areas such as strategy, research, planning, shipping, growth, and hiring. Each skill gives an agent specialized guidance, frameworks, checklists, or templates for product work, and the catalogue contains many of these skills.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add RefoundAI/lenny-skills --skill defining-icpgit clone --depth 1 https://github.com/RefoundAI/lenny-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/refoundai/lenny-skills/defining-icp)<a href="https://agentmods.dev/skills/refoundai/lenny-skills/defining-icp"><img src="https://agentmods.dev/badge/skills/refoundai/lenny-skills/defining-icp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/refoundai/lenny-skills/defining-icp"><img src="https://agentmods.dev/badge/skills/refoundai/lenny-skills/defining-icp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.01739 |
| Opus 5 | $0.00015 | $0.00870 |
| Sonnet 5 | $0.00006 | $0.00348 |
| Haiku 4.5 | $0.00003 | $0.00174 |
Grade A, and why
defining-icp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Defining Your ICP
Narrow your focus to win a market beachhead and build undeniable momentum.
Help the user with defining your icp using insights from 15 guests and posts across Lenny's Podcast and Newsletter.
How to Help
- Identify the Narrowest Possible Segment - Help the user strip away broad demographics to find a comically narrow beachhead where their solution is a 10x improvement.
- Extract Key Attributes - Guide the user to define three specific and unique characteristics that separate their ICP from the general market.
- Validate Through Signal Quality - Use cold outreach data and user behavior to confirm if the chosen segment feels acute pain and demonstrates urgency.
- Plan for Strategic Expansion - Determine when the current niche is dominated and outline the sequence for moving into adjacent segments.
Core Principles
Dominate the niche to gain power
Geoffrey Moore: "The tendency when you're in the chasm is, 'I just need more customers. I should take any customer I could find,' because we need revenue. It's like taking a match and running it back and forth under a log. It's not going to light the log. So how do you start a fire? Well, you start it by putting a little kindling, little crumpled up paper, and you hold the match in one place until the fire starts."
Target a segment where you can realistically achieve 30% to 50% market share within two years. Resisting the urge to pursue every customer for revenue is essential to build ecosystem power.
Optimize via high-signal attributes
Jeanne Grosser: "And what this was was effectively a company universe. So you can think of this as a massive database. Every row was a different company on the planet and every column was an attribute about that company that would help you sell to them in a more targeted fashion."
Identify key business attributes, such as industry or business model, that signal a high need for your specific product. Build a database that segments the market based on these correlations.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 93 lines · 30 tokens per session scan A 6f074fe1cd4d
defining-icp is a skill published in the GitHub repository RefoundAI/lenny-skills (1,318 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,739 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llama-cpp
Run LLM inference with llama.cpp on CPU, Apple Silicon, AMD/Intel GPUs, or NVIDIA — plus GGUF model conversion and quantization (2–8 bit with K-quants and imatrix). Covers CLI, Python bindings, OpenAI-compatible server, and Ollama/LM Studio integration. Use for edge deployment, M1/M2/M3/M4 Macs, CUDA-less…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
github-auth
Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.
ideation
Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.
notion
Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal.
ocr-and-documents
Extract text from PDFs and scanned documents. Use webextract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.