Skip to main content
skill CX Codex

before-you-build · onewave-ai — Claude Code skill for idea validation

The before-you-build skill identifies the main risk in an idea and suggests a small test before implementation starts. Use it to assess a product, feature, MVP, agent, or automation.

MIT 130 installs ★ 440 updated 2026-10-20

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add OneWave-AI/claude-skills --skill before-you-build -a claude-code
Open on GitHub

What before-you-build does

Before development, the skill restates the idea, picks the one or two risks that matter most, and proposes a step to reduce uncertainty. It checks factors such as demand, willingness to pay, access to users, fit with existing workflows, trust, timing, and scope. The response gives a risk verdict and a direction: build, narrow the build, validate first, or hold off.

Suggested tests can include asking users about past attempts, seeking a commitment before writing software, or delivering the outcome manually once. If the idea lacks enough detail, the skill asks a clarifying question. For learning or portfolio work, it focuses on scope and the learning goal rather than startup criteria. It deliberately avoids stack, architecture, tool, and code advice, so it is not meant for requests that already concern implementation alone.

What it helps with

  • identify the biggest product risk before coding
  • test demand before committing to an MVP
  • check whether a feature blocks payment or retention
  • shrink a project to the proof needed now
  • set a clear learning goal for a portfolio project

Example prompts for the agent

  • Assess this appointment-booking product idea before I build it. Which risk should I test first?
  • For this feature in an existing product, check whether it blocks payment and suggest a small validation step.
  • This is a portfolio project. Help me narrow the scope and define what I should learn.

How to install before-you-build

1Skills CLI (Vercel)

npx skills add OneWave-AI/claude-skills --skill before-you-build -a claude-code

2Manually: put the files in place

~/.claude/skills/before-you-build/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/before-you-build/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about before-you-build

How do I install before-you-build in Claude Code?

Run npx skills add OneWave-AI/claude-skills --skill before-you-build -a claude-code. The skill file is at ~/.claude/skills/before-you-build/SKILL.md.

What does before-you-build do?

It reviews an idea before implementation, identifies its main risk, and recommends a small way to test it. The response also gives a risk verdict and a suggested next move.

Can before-you-build recommend a tech stack?

No. It focuses on product assumptions before implementation and avoids recommending stacks, architectures, tools, or code.

Source text

SKILL.md · MIT
---
name: before-you-build
description: Use before starting a product, feature, MVP, agent, automation, or integration build to identify the main pre-build risk and choose the smallest validation step. Trigger when the user asks whether to build, scope, validate, prioritize, or sanity-check an idea before implementation.
---

# Before You Build

Use this skill as a short pre-build risk gate.

The goal is to stop implementation from starting before the riskiest product assumption is clear. Stay implementation-agnostic: do not recommend stacks, architectures, tools, or code.

## Core Behavior

When invoked:

1. Restate the idea in one sentence.
2. Identify the dominant pre-build risk.
3. Give a short risk verdict.
4. Recommend the smallest validation step that can reduce uncertainty before building.

Keep the response short unless the user explicitly asks for a deeper review.

## Seven Risk Dimensions

Check the idea through these dimensions:

- Demand risk: Do enough people already feel this problem strongly?
- Buyer risk: Is there a clear person or team with reason to pay or commit?
- Distribution risk: Is there a believable path to reaching those people?
- Workflow risk: Does the idea fit how users already behave, decide, or work?
- Timing risk: Is this urgent now, or only interesting in theory?
- Trust risk: Does the product require data, access, behavior change, or credibility users may not grant?
- Scope risk: Is the proposed build larger than the proof needed right now?

Pick the one or two risks that matter most. Do not turn every review into a long checklist.

## Output Format

Use this format:

```markdown
## Before You Build

Idea:
- [One-sentence restatement.]

Risk verdict:
- [Low / Medium / High risk] because [one concrete reason].

Main risk:
- [The dominant risk dimension and why it matters.]

Smallest validation step:
- [One specific action the user can take before building.]

Build guidance:
- [Build now / Build smaller / Validate first / Do not build yet.]
```

## Validation Step Rules

The smallest validation step should be specific and low-cost.

Prefer steps like:

- Talk to five target users who already tried to solve the problem.
- Ask for payment, pre-order, letter of intent, or manual commitment before building software.
- Run a landing page, waitlist, outbound message, or concierge test around one narrow promise.
- Manually deliver the outcome once before automating it.
- Test whether the missing feature blocks payment, retention, activation, or only completeness.
- Find one repeated channel that can reach the target users before expanding scope.

Avoid steps like:

- Build the MVP first.
- Add more features to see what happens.
- Choose a tech stack.
- Design the architecture.
- Write code.
- Create a broad product roadmap.

## Special Cases

If the idea is too vague, ask one clarification question:

```text
Who is this for, what painful situation are they in, and how do they solve it today?
```

If the user is asking about a feature for an existing product, focus on whether the feature is a real blocker for payment, retention, activation, trust, or delivery.

If the user says the project is for learning, portfolio, or fun, do not judge it by startup standards. Focus on keeping scope small and making the learning outcome clear.

If the decision to build is already made and the user only wants implementation help, do not use this skill.

## Style

Be direct, skeptical, and useful.

Do not be dismissive. The point is not to kill ideas; the point is to make the next build decision harder to fool yourself about.

© OneWave-AI · MIT · OneWave-AI/claude-skills

Similar skills

All skills for Notes, tasks and projects →

before-you-build by other authors comes first.

before-you-build bin1874 The before-you-build skill reviews product and feature risk before implementation. Use it to find the key assumption and the smallest useful validation step. CX Codex +1 3,100installs idea-refine addyosmani idea-refine is a Claude Code skill that turns an early idea into a clearer direction and tests its assumptions. It activates when asked to brainstorm, refine an idea, or challenge a plan. CX Codex +1 75,100installs principle-subtract-before-you-add backnotprop principle-subtract-before-you-add — a development skill that enforces removing dead code, stubs, and unused validators before writing new features or refactoring. CX Codex +1 10,200installs mvp-scope emotixco The mvp-scope Claude Code skill turns a feature wishlist into a focused MVP plan. It kicks in when a founder needs to choose what to build first. CX Codex +1 ★ 900repo stars build-mvp BuilderOS build-mvp walks every roadmap task in order, implementing, testing and checking each one off, then makes the initial commit. CX Codex +1 1,700installs alalanet guard — check before you install alalanet alalanet guard — check before you install is a Claude Code MCP server checking packages, repositories, skills, and MCP servers before agent installation or connection. It checks remotely without a local install. CX Codex +1 bmad-forge-idea bmad-code-org bmad-forge-idea is a Claude Code skill that probes an early idea through questions and competing perspectives. Invoke it to challenge assumptions, find weak spots, or clarify a plan. CX Codex +1 17,000installs

From the same set185

The whole set →
icp-deep-scanner The icp-deep-scanner skill turns data from connected tools into an Ideal Customer Profile and a persona library. Use it when you need to refresh your ICP or build buyer personas from actual data, not guesses. CX Codex +1 161installs product-launch-war-room product-launch-war-room is a Claude Code skill that tests a launch plan against expert and customer viewpoints, then returns a decision and rollout steps. Run it for a product launch, repricing, or repositioning. CX Codex +1 159installs pricing-change-strategist pricing-change-strategist plans a price increase or tier restructure with churn modeling. CX Codex +1 158installs hyperframes-sales-demo-builder hyperframes-sales-demo-builder — a skill for Claude Code, Codex, Cursor and other platforms that builds a prospect-specific demo video in HyperFrames. CX Codex +1 157installs typography-scale-builder typography-scale-builder — a Claude Code skill that designs typographic systems with modular or fluid type scales. It audits existing font values across the codebase and outputs design tokens, CSS, and Tailwind configs. CX Codex +1 116installs local-seo-optimizer local-seo-optimizer — a Claude Code skill for local SEO audits and Google Business Profile optimization. Identifies listing gaps and benchmarks performance against map pack competitors. CX Codex +1 114installs cowork-rfp-response cowork-rfp-response — a skill for Claude Code that shreds RFP documents and maps requirements against company archives. It flags unanswerable criteria and disqualifiers before drafting starts. CX Codex +1 112installs review-response-writer The review-response-writer Claude Code skill drafts review replies in the owner’s voice and sorts reviews by situation. It flags mentions of injury, illness, discrimination, or legal threats for the owner. CX Codex +1 110installs

Project sponsors

Companies that keep this analytics open