New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Lean Canvas

by borghei in borghei/Claude-Skills

Lean Canvas (Ash Maurya) — startup adaptation of the Business Model Canvas for capturing assumptions and unfair advantages in early-stage products.

MITAuto-check passedProduct & Project Management

Install Lean Canvas

skills CLI
$ npx skills add borghei/Claude-Skills --skill lean-canvas -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install borghei/Claude-Skills lean-canvas --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/project-management/strategy-frameworks/lean-canvas .claude/skills/lean-canvas && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
lean-canvas
GitHub stars
881
Token cost
~1.8k tokens
SKILL.md length
851 words
Files
5 (incl. scripts, references, assets)
Skills in repo
349
Repo updated
First seen
Licence
MIT

At a glance

Lean Canvas (Ash Maurya) — startup adaptation of the Business Model Canvas for capturing assumptions and unfair advantages in early-stage products.

  • Works in 7 steps: Problem-Segment first → Existing alternatives → Unique Value Proposition → …
  • Tasks that involve Product strategy
  • SKILL.md covers When to use this skill, The 9 Lean Canvas blocks, Lean Canvas vs BMC and Clarify First, plus 6 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Lean Canvas is an agent skill from borghei/Claude-Skills. Lean Canvas (Ash Maurya) — startup adaptation of the Business Model Canvas for capturing assumptions and unfair advantages in early-stage products. Use at the idea, pre-PMF, or pivot stage, or when you need a 1-page model fast.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts, reference files and assets (for example `assets/lean_canvas_template.md`, `references/lean-canvas-framework.md` and `references/lean-startup-anti-patterns.md`).

It sits in Product & Project Management, covering Product strategy and Startup and business strategy. The repository describes itself as: 385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit… The licence is MIT.

When your agent uses it

  • Tasks that involve Product strategy
  • Tasks that involve Startup and business strategy

Example prompts

  • “/lean-canvas”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Problem-Segment first
  2. Existing alternatives
  3. Unique Value Proposition
  4. Solution (3 features max)
  5. Unfair Advantage
  6. Channels, Revenue, Costs, Metrics
  7. Run lean_canvas_validator.py

What it can do on your machine

Read from SKILL.md and the folder at commit 4a698e8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lean Canvas loads about 1.8k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 851 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from borghei/Claude-Skills at commit 4a698e8, republished under its MIT licence (© borghei). 851 words, ~1,822 tokens.

Download SKILL.mdSave it as .claude/skills/lean-canvas/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
lean-canvas
description
Lean Canvas (Ash Maurya) — startup adaptation of the Business Model Canvas for capturing assumptions and unfair advantages in early-stage products. Use at the idea, pre-PMF, or pivot stage, or when you need a 1-page model fast.
license
MIT + Commons Clause
metadata.version
1.0.0
metadata.author
borghei
metadata.category
project-management
metadata.domain
strategy-frameworks
metadata.updated
2026-05-27
metadata.python-tools
lean_canvas_validator.py
metadata.tech-stack
lean-canvas, ash-maurya, lean-startup, problem-solution-fit

Lean Canvas

A 9-block startup canvas adapted from BMC. Replaces 4 BMC blocks (Key Resources, Activities, Partnerships, Customer Relationships) with startup-focused ones (Problem, Solution, Key Metrics, Unfair Advantage).

When to use this skill

  • Early-stage (pre-PMF) product or company
  • Capturing assumptions that need testing
  • 20-minute model sketch (BMC takes longer)
  • Pivot conversations — what would change?
  • Stress-testing unfair advantage before building

The 9 Lean Canvas blocks

  1. Problem — Top 3 problems for the segment
  2. Customer Segments — Target customers (especially Early Adopters)
  3. Unique Value Proposition — Single, clear, compelling message
  4. Solution — Top 3 features that solve the problems
  5. Channels — Path to customers
  6. Revenue Streams — Revenue model + LTV + revenue forecast
  7. Cost Structure — Customer acquisition cost + distribution + people + hosting
  8. Key Metrics — Key activities you measure
  9. Unfair Advantage — Something that cannot be easily copied or bought

Lean Canvas vs BMC

Lean CanvasBMC
ProblemKey Partnerships
SolutionKey Activities
Key MetricsKey Resources
Unfair AdvantageCustomer Relationships

Same outer shape; different inner emphasis. Use Lean when problem + unfair advantage matter more than ops detail.

Clarify First

Before building the canvas, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • The specific early-adopter segment — named, not "everyone" (the Problem, UVP, and Channels blocks all hinge on a concrete early adopter)
  • The top 3 problems — for that segment (the Problem block; if you can't name them you have an idea, not a startup)
  • Existing alternatives — how customers solve this today (signals whether the problem is real; "they live with it" is important signal)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Workflow

Step 1 — Problem-Segment first

Start with Problem and Customer Segments. If you can't list the top 3 problems for a specific segment, you don't have a startup — you have an idea.

Step 2 — Existing alternatives

Within Problem block, list how customers solve this today. If the answer is "they don't / they live with it," that's important signal.

Step 3 — Unique Value Proposition

A single sentence that:

  • Names the early-adopter segment
  • States the differentiating outcome
  • Distinguishes from existing alternatives

Template: "[Outcome] for [segment] that [differentiator]."

Step 4 — Solution (3 features max)

Limit to 3. Founders always want to list 10. Resist.

Step 5 — Unfair Advantage

The hardest block. What do you have that no one can easily copy?

  • Insider information / domain
  • Personal authority / reputation
  • Dream team
  • Personal endorsements
  • Existing customer base
  • Network effects already in motion
  • Patented IP

If empty: most startups have nothing yet. Mark explicitly + plan how to build one.

Step 6 — Channels, Revenue, Costs, Metrics

Fill remaining blocks. Be specific.

Step 7 — Run lean_canvas_validator.py

Audit for: missing blocks, generic content, no early adopter named, no existing alternatives, no Key Metrics, vague Unfair Advantage.

bash
python3 project-management/strategy-frameworks/lean-canvas/scripts/lean_canvas_validator.py \
  --input canvas.json --format markdown

Decision frameworks

Lean Canvas vs BMC — when to use which
Use Lean CanvasUse BMC
< $1M ARR or pre-revenueMature company / division
Single segment, single productMulti-product or multi-segment
Problem-solution fit huntingOperating + scaling
Pivot conversationsStrategic planning
20-minute sketchHalf-day planning workshop
Show full SKILL.md (337 more words)Show less
Early adopter heuristic

Early adopters are not "future mainstream users." They are:

  • Aware they have the problem
  • Actively looking for a solution
  • Have cobbled together a workaround (existing alternative)
  • Have budget / authority to try yours

If you can't name 5 specific early adopters by name + workaround, you're not at problem-solution fit yet.

Unfair Advantage — what counts

Counts:

  • Insider information (proprietary data, deep customer relationships)
  • Personal authority (industry-recognized expertise)
  • Existing community / audience
  • Network effects already started
  • Capital + brand recognition

Doesn't count:

  • "We work harder"
  • "Our team is great"
  • "First mover" (in most cases; usually replicable)
  • "Better UX" (replicable)
  • "AI" (everyone has AI now)
  • "Cheaper" (price competition is a race to zero)

If your only unfair advantage is "speed" or "execution," that's a weakness as a moat.

Common engagements

"Help me sketch a canvas for my new idea"
  1. Problem + Segment first.
  2. Force list the existing alternatives (and what they cost).
  3. Write the UVP (one sentence).
  4. List Solution as 3 features max.
  5. Identify Channels you can realistically test in 4 weeks.
  6. Stub Revenue + Cost + Metrics.
  7. Honest Unfair Advantage assessment.
  8. Identify top 3 riskiest assumptions; design test for each.
"Should we pivot?"
  1. Build current state Lean Canvas.
  2. Build proposed state Lean Canvas.
  3. Compare: what's different? what's the unfair advantage now?
  4. What evidence do we have that the new model works?
  5. Run the assumption-test for the riskiest new assumption.

Anti-patterns to avoid

  • Solution before Problem. Solution-in-search-of-problem.
  • "Everyone" as segment. Force a specific early adopter description.
  • No existing alternative listed. Customers always do something today.
  • UVP that says everything. Says nothing.
  • 5+ solution features listed. Pick 3 max.
  • Vague Key Metrics. Pirate metrics (AAARRR) or HEART or similar.
  • Unfair Advantage = "execution". Not an advantage.
  • No assumption register. Canvas isn't a plan, it's a hypothesis.

References

  • references/lean-canvas-framework.md — the 9 blocks deep, comparison to BMC
  • references/lean-startup-anti-patterns.md — common mistakes + worked fixes
  • project-management/strategy-frameworks/business-model-canvas — operating-scale variant
  • project-management/discovery/value-proposition-canvas — deeper on UVP
  • project-management/discovery/identify-assumptions — assumption register
  • project-management/discovery/pre-mortem — risk discovery
  • project-management/execution/north-star-metric — Key Metric definition
  • c-level-advisor/ceo-advisor — strategic context

© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references, assets) in project-management/strategy-frameworks/lean-canvas of borghei/Claude-Skills.

  • SKILL.md
  • assets/lean_canvas_template.md
  • references/lean-canvas-framework.md
  • references/lean-startup-anti-patterns.md
  • scripts/lean_canvas_validator.py

Open the folder on GitHubat commit 4a698e8

Compare with similar skills

Lean Canvas next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Lean Canvas compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Lean Canvas this skillborghei/Claude-Skills881—~1.8kAutomated safety check: PassMIT
Good Strategy Bad Strategy Kernelamplitude/builder-skills159—~2.2kAutomated safety check: PassNone
YC Office Hoursgarrytan/gstack136k—~4.2kAutomated safety check: PassMIT
Playing to Win Strategyamplitude/builder-skills159—~1.7kAutomated safety check: PassNone
Startup Canvasphuryn/pm-skills27k—~1.6kAutomated safety check: PassMIT
Idea ValidatorMathews-Tom/armory328—~2.9kAutomated safety check: PassMIT

Similar skills

  • Good Strategy Bad Strategy Kernel

    amplitude/builder-skills

    Evaluates or drafts a strategy using Rumelt's kernel of diagnosis, guiding policy and coherent actions, to expose goal lists posing as strategy.

    159 GitHub stars~2.2k tokensUpdated 2 mo ago
    Product & Project ManagementAuto-check passed

  • YC Office Hours

    garrytan/gstack

    Runs a YC-style office hours session that pressure-tests a product idea before any code and ends in a design document instead of an implementation.

    136k GitHub stars~4.2k tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Playing to Win Strategy

    amplitude/builder-skills

    Walks a team through Lafley and Martin's five-choice cascade to pin down where to compete and how to win there.

    159 GitHub stars~1.7k tokensUpdated 2 mo ago
    Product & Project ManagementAuto-check passed

  • Startup Canvas

    phuryn/pm-skills

    Generate a Startup Canvas combining Product Strategy (9 sections) and Business Model (costs + revenue) for a new product.

    27k GitHub stars~1.6k tokensUpdated 23 days ago
    Product & Project ManagementAuto-check passed

  • Idea Validator

    Mathews-Tom/armory

    Orchestrates business idea validation via parallel sub-agents: Lean Canvas, JTBD, market/competitive/feasibility research, SWOT/PESTLE, and a weighted scorecard with verdict.

    328 GitHub stars~2.9k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check passed

  • Biz Blue Ocean

    asgard-ai-platform/skills

    Apply Blue Ocean Strategy to create uncontested market space through value innovation.

    241 GitHub stars~2k tokensUpdated 4 mo ago
    Product & Project ManagementAuto-check passed

More from borghei/Claude-Skills

All 349 skills in this repo

  • Agents In The Team

    borghei/Claude-Skills

    Run delivery when AI coding and ops agents take tickets. An agent skill from borghei/Claude-Skills.

    881 GitHub stars~4.2k tokensUpdated today
    Auto-check passed

  • AI Content Disclosure

    borghei/Claude-Skills

    Check AI-generated marketing content and reviews for required disclosures under the EU AI Act, FTC rules and platform AI-label policies.

    881 GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • AI Prototyping

    borghei/Claude-Skills

    Idea to AI-generated prototype to customer validation to engineering handoff.

    881 GitHub stars~3.6k tokensUpdated today
    Auto-check passed

  • Analytics Engineer

    borghei/Claude-Skills

    Analytics engineering across data modeling, dbt, transformation, and semantic layers.

    881 GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • Ansoff Matrix

    borghei/Claude-Skills

    Ansoff Matrix — 4-quadrant framework for growth options: market penetration, market/product development, and diversification.

    881 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Brainstorm Okrs

    borghei/Claude-Skills

    OKR brainstorming and validation using the Radical Focus framework — outcome objectives, measurable key results, counter-metrics.

    881 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Categories

Questions about Lean Canvas

What does Lean Canvas do?

Lean Canvas (Ash Maurya) — startup adaptation of the Business Model Canvas for capturing assumptions and unfair advantages in early-stage products. Lean Canvas is an agent skill from borghei/Claude-Skills. Lean Canvas (Ash Maurya) — startup adaptation of the Business Model Canvas for capturing assumptions and unfair advantages in early-stage products.

When should I use Lean Canvas?

Lean Canvas fits situations like: tasks that involve Product strategy; tasks that involve Startup and business strategy.

How do I install Lean Canvas in Claude Code?

Run `npx skills add borghei/Claude-Skills --skill lean-canvas -a claude-code`. Or copy the skill folder (project-management/strategy-frameworks/lean-canvas in borghei/Claude-Skills) into .claude/skills/lean-canvas in your project. Claude Code loads it when a task matches its description.

How do I install Lean Canvas in Codex?

Run `npx skills add borghei/Claude-Skills --skill lean-canvas -a codex`. Or copy the skill folder (project-management/strategy-frameworks/lean-canvas in borghei/Claude-Skills) into .agents/skills/lean-canvas in your project. Codex loads it when a task matches its description.

Can I use Lean Canvas in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add borghei/Claude-Skills --skill lean-canvas -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lean-canvas, .gemini/skills/lean-canvas, .github/skills/lean-canvas and .opencode/skills/lean-canvas in your project.

What does Lean Canvas need to run?

Going by SKILL.md and its folder, Lean Canvas needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Lean Canvas access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Lean Canvas safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Lean Canvas use?

Lean Canvas is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Lean Canvas use?

About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.

What are the alternatives to Lean Canvas?

Skills that share tags, products or a category with Lean Canvas: Good Strategy Bad Strategy Kernel (amplitude/builder-skills, 159 stars), YC Office Hours (garrytan/gstack, 136k stars), Playing to Win Strategy (amplitude/builder-skills, 159 stars) and Startup Canvas (phuryn/pm-skills, 27k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lean Canvas?

borghei (a GitHub user) maintains it in borghei/Claude-Skills, which has 881 GitHub stars. The repository holds 349 skills in this directory. The repository was last updated on October 7, 2026.

Source: borghei/Claude-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.