idea-validation
Phase 1: research and test a product idea before committing to an MVP or solution scope.
SKILL.md.claude/skills/idea-validation/SKILL.md
GitHub<!-- Generated by mstack from Misbah's Build Like This workflow. Regenerate instead of editing. -->
idea-validation
This skill is part of Misbah Khursheed's Build Like This workflow. Thinking, evidence, and explicit trade-offs come before generated output.
Project identity and sources of truth
The repository where this skill is installed is the host project being built. Build Like This is the method used to build it; mstack only installs and reconciles method resources. Do not assume mstack or Build Like This is the product unless project-owned sources explicitly identify this repository as mstack itself.
Use project-owned docs/, decisions, executable code, and tests as sources of truth. .mstack/templates/ are reference scaffolds to copy and adapt into project-owned documents, not product requirements and not a replacement for docs/.
Purpose
Reduce the largest uncertainty in a product idea with current, attributable evidence and a falsifiable validation step. This precedes plan-mvp: it decides whether and how the idea deserves product planning rather than defining the MVP itself.
Required inputs
- The idea, suspected user/context and problem, origin of the hypothesis, constraints, and decision deadline.
- Any existing observations, research, analytics, alternatives, attempted solutions, or known contradictions.
- Authorized research channels and limits on browsing, outreach, paid sources, personal data, and experiments.
If a missing input would materially change the result, state the gap and obtain or discover it before proceeding. Otherwise label the assumption and continue.
Process
- Have the product manager lead; delegate independent problem/context and alternative/market evidence lanes to product research and analysis specialists.
- State the falsifiable problem/value hypothesis, evidence standard, decision options, and what would disconfirm the idea.
- Gather dated, attributable sources across independent source classes; record methods, access dates, relevance, and limitations.
- Compare the current workaround, alternatives, switching costs, frequency/severity signals, feasibility constraints, and negative evidence.
- Separate facts, interpretations, assumptions, contradictions, and open questions; never label secondary evidence as direct user validation.
- Choose go/refine/stop and define the smallest authorized primary-research or experiment step with a predeclared threshold.
Output contract
- A project-owned discovery brief under docs/research/ using the discovery template, with citations and confidence labels.
- A ranked assumption/evidence ledger, alternatives map, and explicit go/refine/stop rationale.
- The next validation experiment or research plan with owner, ethics/permission boundary, threshold, and stop rule.
Guardrails
- Do not proceed directly to features or architecture merely because the idea is plausible.
- Do not fabricate users, sources, quotes, demand, market size, or validation confidence.
- Do not contact people or mutate an external system without explicit authorization.
Delegation and parallel safety
- Material lifecycle work must delegate at least one bounded specialist lane when subagents are available. Prefer two or more concurrent lanes only for independent evidence gathering, analysis, or non-overlapping file ownership.
- The active lead owns integration and acceptance. Supporting agents do not recursively delegate unless explicitly promoted to lead a named lane.
- Assign distinct outputs and ownership. Serialize shared docs, contracts, schemas, migrations, deployments, external writes, and overlapping file edits.
- When subagents are unavailable, perform the same named specialist passes sequentially and state that constraint instead of implying parallel verification.
- Delegation never grants permission for outreach, consequential external actions, destructive changes, paid resources, or production operations.
End with the evidence gathered, verification performed, and any residual risk or unresolved decision.