pm-lean-canvaslisted

# PM - Lean Canvas ## Agent mode (`--agent`) Supports `--agent`: runs autonomously in a subagent, drafts the artifact from existing inputs, and returns a short summary + coverage note. - **No flag** → interactive (default); if inputs are heavy, offer agent mode. - **`--agent`** → obey. First check inputs are complete. Anything missing: do NOT invent it - mark `[ASSUMED - what/why]` in the output and summary. Never hallucinate to fill a gap. - **Review required:** the artifact contains commitments - after drafting, require the user's review before finalizing; do not close decisions autonomously. --- ## What this skill does Produces a one-page business model focused on problem-solution fit and early traction. Lean Canvas is optimized for the validation stage - it forces explicit problem/solution pairing, early adopter definition, and unfair advantage thinking before scaling. Unlike the Business Model Canvas (which maps an established business), Lean Canvas maps a hypothesis. Each block is a bet that needs validation. No invented market data or assumptions. Claude structures the canvas; user provides the business knowledge from Phase 2 research and Phase 3a Go/No-Go outcomes. --- ## Dependencies **Recommended before running:** - `pm-hypotheses` (Results mode) - Go/No-Go verdict must be GO before running this skill - `design-thinking` - Problem, UVP, and Solution blocks draw directly from design thinking synthesis - `pm-personas` - Customer Segments and Early Adopters