prototype-first-workflowlisted

Build-stage skill: turns a feature idea into the smallest testable prototype plan — built around what the prototype must disprove, not what it should demonstrate. Use when the user wants to test before building — 'plan the smallest prototype', 'how do we prototype this before committing', 'design the spike', 'fastest way to test if this works' — or when /pm routes such a request here. Do NOT use to execute the build, to make the build/kill call itself (ai-feature-go-no-go), to map assumptions without a test plan (assumption-mapper — its riskiest assumption is this skill's input), or for definitions of prototyping methods.
Abhillashjadhav/PM-agent-OS · ★ 1 · AI & Automation · score 60

Install: claude install-skill Abhillashjadhav/PM-agent-OS

# Prototype-First Workflow Prototypes exist to kill bad ideas cheaply. A prototype that can only succeed is a demo — this skill plans the one that can fail. ## Verification gates (defined first; output is blocked until all pass) - **G1 — Kill hypothesis named:** the plan states what the prototype must DISPROVE — a falsifiable claim with a numeric threshold set before the run ("recruiters discard >80% of senior-candidate drafts"). Demonstrate-only plans ("show the drafts are useful") fail the gate. - **G2 — Minimum lethal build:** every component of the plan is justified by the kill test. Scope that serves the demo but not the test is cut; if a cheaper build (Wizard-of-Oz, concierge, template sidecar) can kill the hypothesis, the plan must use it or say why not. - **G3 — Consequences pre-committed:** thresholds carry their basis, measurement is defined (what's logged, window, N — from stated context only), and both branches exist: if killed → what, if survived → what. No invented user counts or benchmark thresholds. ## Steps 1. **Extract the fight.** What is the team actually arguing about? That disagreement is the kill hypothesis's home — the fixture risk ("recruiters won't trust AI drafts with senior candidates") converts directly. If nothing is contested, ask what would make the team abandon the idea; if truly nothing would, say the prototype is theater and stop. 2. **Write the kill hypothesis:** falsifiable, thresholded, time-boxed. Use the team's own claims as bars (