$npx -y skills add wshobson/agents --skill before-you-buildPre-build product and feature risk review for founders, product managers, and AI-assisted builders. Use this skill when the user is about to build a landing page, MVP, SaaS product, internal tool, agent workflow, or major feature and needs to check demand, positioning, monetizati
| 1 | # Before You Build |
| 2 | |
| 3 | Run a compact pre-mortem before implementation. The goal is not to block building; it is to identify the highest-risk assumption, the smallest validation step, and the build scope that should be delayed until evidence improves. |
| 4 | |
| 5 | ## When To Use |
| 6 | |
| 7 | Use this skill when a user asks to build or ship: |
| 8 | |
| 9 | - A new product, MVP, prototype, landing page, SaaS app, marketplace, content site, agent workflow, or internal tool |
| 10 | - A major feature with unclear adoption, revenue, retention, trust, or distribution impact |
| 11 | - A public launch asset where weak positioning could waste development or promotion effort |
| 12 | |
| 13 | Skip this skill when the task is a narrow implementation fix, refactor, test repair, dependency update, or already-validated change with clear acceptance criteria. |
| 14 | |
| 15 | ## Risk Checklist |
| 16 | |
| 17 | Review the idea across these risks: |
| 18 | |
| 19 | - **Demand:** Is there evidence that a specific buyer or user urgently wants this? |
| 20 | - **Positioning:** Can the target user understand what it is and why it matters in one sentence? |
| 21 | - **Monetization:** Is there a credible path to payment, budget, or strategic value? |
| 22 | - **Retention:** Is there a reason users would return after the first try? |
| 23 | - **Trust:** Does the product require credibility, data access, integrations, or behavior change that users may resist? |
| 24 | - **Distribution:** Is there a repeatable way to reach the target user? |
| 25 | - **Feature adoption:** For feature work, will the feature change user behavior or just add surface area? |
| 26 | |
| 27 | If the verdict is not obvious, use `references/risk-checklist.md` for deeper questions. |
| 28 | |
| 29 | ## Output Format |
| 30 | |
| 31 | Keep the response short and decision-oriented: |
| 32 | |
| 33 | 1. **Risk verdict:** Low, medium, or high risk, with one sentence explaining why. |
| 34 | 2. **Main assumption:** The single assumption most likely to break the project. |
| 35 | 3. **Evidence to find first:** The smallest useful signal before building more. |
| 36 | 4. **Do next:** One concrete validation step or reduced build scope. |
| 37 | 5. **Delay:** What not to build yet. |
| 38 | |
| 39 | ## Guidance |
| 40 | |
| 41 | - Be direct about weak evidence, but avoid dismissing the user's idea. |
| 42 | - Prefer smaller validation steps over large research plans. |
| 43 | - Separate product risk from engineering difficulty. |
| 44 | - If the idea is already validated, say what evidence makes it lower risk and suggest the smallest implementation slice. |
| 45 | - If facts are missing, name the missing evidence instead of inventing market claims. |