before-you-build
SolidUse 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.
Install
Quality Score: 86/100
Skill Content
Details
- Author
- OneWave-AI
- Repository
- OneWave-AI/claude-skills
- Created
- 9 months ago
- Last Updated
- 1 weeks ago
- Language
- N/A
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
idea-validator
Pressure-test whether an idea, product, or feature is worth building — BEFORE sinking days into it. Use whenever someone weighs building something and the real risk is the premise rather than the code. Triggers include "should I build X", "is this idea worth it", "validate this idea", "does this beat what already exists", "should this exist", "I'm about to build X", or mid-build "should I keep going or kill it". The method names the incumbent you must beat, ranks assumptions by risk × cost-to-test, attacks the cheapest riskiest one first, pre-registers kill criteria before any test, separates whether it's real from whether it's differentiated (real-but-commodity is a NO), and ends with a GO / NO-GO / CONDITIONAL-GO verdict plus scorecard. Trigger even on enthusiasm ("I have a great idea for…"), not just doubt. Distinct from reality-check (verifies an existing plan for hallucinations); this decides whether a thing should be built at all.
idea-stress-test
Stress-test a business idea, product hypothesis, or new feature BEFORE building it, to decide whether it is worth your time. Use this skill whenever the user is weighing whether to build, launch, or invest time in an idea — phrases like "should I build", "is this worth it", "I have an idea for", "thinking about a startup/product/feature", "validate my idea", "проверь гипотезу", "стоит ли делать". The skill forces the idea through a fixed gauntlet — who pays, what already solves this pain for free, the cheapest 7-day test, and a pre-committed kill criterion — and ends with a GO / NO-GO / TEST-FIRST verdict. Pushes back on the framing instead of cheerleading. Lean toward triggering this even when the user only hints at evaluating an idea, because the most expensive mistake is skipping validation and building the wrong thing.
derisk-sequencer
Turn a validated idea into a risk-ordered sequence of experiments and build steps, with one hard rule — no product code is scheduled before the test that de-risks it. Use whenever someone has an idea worth building and asks what to do in what order — "what should I build first", "what order do I tackle this", "sequence this plan", "de-risk this roadmap", or presents a build plan that front-loads construction ahead of validation. The method lists the load-bearing assumptions, scores each by risk divided by cost-to-test, orders experiments cheapest-decisive first with kill-gates between them, places every build step after its unlocking test, and defers governance, breadth, and optimization until their gates clear — then emits an ordered sequence and a linter that flags build-before-its-test. Distinct from task-decomposition and overwhelm-breakdown (which collapse a big task to one next step for momentum) and agent-orchestration (which sequences build phases); this sequences de-risking ahead of building.