woos-problem-validation

Étoiles7

Forks1

Mis à jour16 juin 2026 à 10:16

Validate whether the captured problem is real, painful, frequent, and worth pursuing before broader discovery work begins.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Source

zero-click

zero-click/zero-ratchet

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Métiers associésSOC

Basé sur la classification professionnelle SOC

Analystes en études de marché et spécialistes en marketingProfessions des affaires et des opérations financières·SOC 13-1161

Explorateur de fichiers

2 fichiers

SKILL.md

readonly

name	woos-problem-validation
description	Validate whether the captured problem is real, painful, frequent, and worth pursuing before broader discovery work begins.
version	1.0.0
author	Hermes Profile
license	MIT
metadata	{"hermes":{"tags":["product","discovery","validation","research"],"related_skills":["woos-product-discovery"]}}

Problem Validation

Output Language

Author all user-facing prose (narratives, findings, summaries) in the user's most recent input language (e.g. if the user is writing in Chinese, write the PRD body, review findings, and summaries in Chinese).
Keep these tokens verbatim in English regardless of the user's language, because they are contract identifiers consumed by other skills and gates:
- Verdict tokens: PASS, REQUEST_CHANGES, BLOCKED, NOT_RUN
- Severity tokens: critical, high, medium, low, warning
- Tag tokens: [ASSUMPTION: ...], [NEEDS CLARIFICATION: ...], [NEEDS INPUT: ...]
- Phase / dimension IDs: P0 … P11, P2a, Phase A, Phase B
- Shape values: internal-tool, single-operator, consumer-product, multi-stakeholder, CLI
- P0 rating values: strong, adequate, thin, broken
- Section headings declared in templates (e.g. ## Background, ## Functional Requirements, ## Assumptions Index) — translations break downstream structural checks
- Field labels inside templates (e.g. **Consequences (testable):**, **Out of Scope:**, **User value:**, Given … When … Then …)
Code, file paths, IDs, and quoted PRD excerpts stay in their original form.

Purpose

Decide whether the captured problem should proceed, pivot, or park.

Required Load Set (mandatory)

references/framework-customer-pain-points.md
ideas/<slug>/00-idea-capture.md

If any required file is not loaded, return BLOCKED.

Output

ideas/<slug>/00-idea-capture.md → append ## Problem Validation

Required Decision

The output must conclude with one of:

PROCEED
PIVOT
PARK

Must Answer

Is this a real problem?
How frequently does it occur?
How painful is it?
How many people have it?
Are people already paying time or money to solve it?

Plus depuis ce dépôt

même dépôt

woos-architecture-overview

zero-click/zero-ratchet

Produce the high-level architecture overview used by downstream product design and engineering.

2026-06-167

woos-architecture-review-gate

zero-click/zero-ratchet

Independent high-level architecture review gate for discovery.

2026-06-167

woos-idea-capture

zero-click/zero-ratchet

Capture and structure raw ideas through guided interview or quick note. Produces a structured idea document ready for research or PRD pass. Focuses purely on product intent — no technical decisions.

2026-06-167

woos-idea-to-design

zero-click/zero-ratchet

Entry-point product workflow from raw idea to validated product design artifacts. Stops at reviewed PRD readiness and does not include engineering implementation.

2026-06-167

woos-prd-authoring

zero-click/zero-ratchet

Write the per-feature PRD from the ranked requirements contract using the mandatory PRD template.

2026-06-167

woos-prd-consistency-audit

zero-click/zero-ratchet

Dedicated analyze gate for PRD and UI brief consistency. Runs script extraction first, then semantic review with evidence-backed findings.

2026-06-167

Problem Validation

Output Language

Author all user-facing prose (narratives, findings, summaries) in the user's most recent input language (e.g. if the user is writing in Chinese, write the PRD body, review findings, and summaries in Chinese).

Keep these tokens verbatim in English regardless of the user's language, because they are contract identifiers consumed by other skills and gates:

Verdict tokens: PASS, REQUEST_CHANGES, BLOCKED, NOT_RUN
Severity tokens: critical, high, medium, low, warning
Tag tokens: [ASSUMPTION: ...], [NEEDS CLARIFICATION: ...], [NEEDS INPUT: ...]
Phase / dimension IDs: P0 … P11, P2a, Phase A, Phase B
Shape values: internal-tool, single-operator, consumer-product, multi-stakeholder, CLI
P0 rating values: strong, adequate, thin, broken
Section headings declared in templates (e.g. ## Background, ## Functional Requirements, ## Assumptions Index) — translations break downstream structural checks
Field labels inside templates (e.g. **Consequences (testable):**, **Out of Scope:**, **User value:**, Given … When … Then …)

Code, file paths, IDs, and quoted PRD excerpts stay in their original form.

Purpose

Decide whether the captured problem should proceed, pivot, or park.

Required Load Set (mandatory)

references/framework-customer-pain-points.md

ideas/<slug>/00-idea-capture.md

If any required file is not loaded, return BLOCKED.

Output

ideas/<slug>/00-idea-capture.md → append ## Problem Validation

Required Decision

The output must conclude with one of:

PROCEED

PIVOT

PARK

Must Answer

Is this a real problem?

How frequently does it occur?

How painful is it?

How many people have it?

Are people already paying time or money to solve it?