Agent skill · Design & Presentation

lean-ux-canvas

Guide teams through Lean UX Canvas v2. Use when framing a business problem, surfacing assumptions, and defining what to learn next.

deanpetersgithub.com/deanpetersGitHub ↗
claude-codeNOASSERTION
Install
npx skills add deanpeters/Product-Manager-Skills --skill lean-ux-canvas --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 3
SKILL.md size: 24 KB
Bundled scripts: none
Path: skills/lean-ux-canvas/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 6,255
Language: Shell
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

The skill walks through the Lean UX Canvas (v2) process, prompting the agent to guide a workshop that frames a business problem, defines measurable business outcomes, identifies target users, clarifies user outcomes and benefits, brainstorms potential solutions, formulates testable hypotheses, and plans learning with small experiments. It emphasizes treating solutions as hypotheses and centers on learning and validation before building.

How it works

  • It operates as an interactive session that covers 8 canvas boxes in sequence, with prompts and options at each step.
  • Step 0 gathers context (business and user context) to seed the canvas.
  • Question 1 (Box 1) collects the current problem description, changes, and why it matters; user can choose to describe, have the agent identify, or be guided to a starter skill.
  • Question 2 (Box 2) focuses on measurable business outcomes (leading indicators preferred) and provides options to specify or derive metrics.
  • Question 3 (Box 3) asks which user types to focus on, offering options to use existing personas, identify target users, or create new personas using a companion skill.
  • Question 4 (Box 4) explores user outcomes and benefits (empathy/importance, not metrics); prompts options to describe, identify, or research with jobs-to-be-done resources.
  • Question 5 (Box 5) solicits potential solutions (features, policies, models); treats them as hypotheses and prompts for at least 3 candidates.
  • Question 6 (Box 6) constructs testable hypotheses by combining Boxes 2–5 content using a defined template; the agent proposes hypotheses and offers accept/edit options.
  • It references a facilitation source (workshop-facilitation) and the template structure for full fill-in, and notes that the interactive skill will run through 8 adaptive questions with guidance.

When to use it

  • Use when framing a business problem before solutioning.
  • Use to surface and test assumptions in cross-functional workshops.
  • Use to convert vague initiatives into hypotheses and learning goals.
  • Use for planning discovery sprints or MVPs and when stakeholders focus on solutions prematurely.

What it can touch

  • Tools: claude-code is listed as a declared tool.
  • It uses the interactive workflow to collect inputs and generate hypotheses and learning plans.

Caveats

  • The description emphasizes learning and experimentation rather than committing to features.
  • It frames hypotheses as testable and avoids treating solutions as guaranteed outcomes.
  • It is designed to be used with a structured workshop protocol and references an auxiliary facilitation skill for workflow.
From the SKILL.md

## Purpose Guide product managers through creating **Jeff Gothelf's Lean UX Canvas (v2)**—a one-page facilitation tool that frames work around a **business problem to solve**, not a **solution to implement**. Use this to align cross-functional teams around core assumptions, craft testable hypotheses, and ensure learning happens every sprint by exposing gaps in understanding (problem, users, value, and why the solution should work). This is not a roadmap or feature list—it's an **"insurance policy"** that turns assumptions into experiments before committing to full development. The canvas shifts conversations from **outputs** to **outcomes** and ensures teams build the right thing, not just build things right. ## Input **Works best with:** The business problem you're framing — or the solution idea you're being handed, which the canvas will reframe as a problem. **Also useful:** Known users, evidence so far, and what the team already believes (assumptions to surface). Anything supplied with the invocation itself — text after the skill name, a pasted context dump, or an appended `ARGUMENTS:` line — counts as answers already given. Use it and skip whatever it covers; don't re-ask. **Ar

What's inside
Steps it walks through
  1. Purpose
  2. Input
  3. Key Concepts
  4. What is the Lean UX Canvas?
  5. Canvas Structure (8 Boxes)
  6. Why This Works
  7. Key Distinctions (Avoid Confusion)
  8. Anti-Patterns (What This Is NOT)
  9. When to Use This
  10. Facilitation Source of Truth
  11. Application
  12. Step 0: Gather Context
  13. Question 1: Business Problem (Box 1)
  14. Question 2: Business Outcomes (Box 2)
Ships with 2 files
  • examples/sample.md
  • template.md
More from Product-Manager-Skills
All skills →
About this skill
What does the lean-ux-canvas skill do?

Guide teams through Lean UX Canvas v2. Use when framing a business problem, surfacing assumptions, and defining what to learn next.

How do I install it?

Run `npx skills add deanpeters/Product-Manager-Skills --skill lean-ux-canvas --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From deanpeters/Product-Manager-Skills, a repository with 6,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going