skills.rest
wuji-technology
wuji-technologyOFFICIAL
Explore all skills by this author →
Website𝕏@wuji_globalGitHub

value-validation

Validate released product versions against PRD assumptions using MOQL data.

Updated Aug 27, 2026
Search Tags:#retrospective#post-release#prd#feishu#hypothesis-testing#moql#value-validation
One-click install
npx skills add https://github.com/wuji-technology/pm-workflow-plugin --skill value-validation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: value-validation
Source: https://github.com/wuji-technology/pm-workflow-plugin/tree/main/skills/value-validation
Command: npx skills add https://github.com/wuji-technology/pm-workflow-plugin --skill value-validation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Validate whether a released product version or feature achieved the outcomes and assumptions defined in PRD and Design by comparing delivery artifacts and observed data, and produce clear improvement actions and knowledge artifacts for learning loops.

Core Features & Use Cases

  • Quick mode (version-level): automated MOQL data collection, PRD-to-metrics comparison, a concise validation report and suggested improvement stories for rapid post-release checks.
  • Full mode (feature-level): multi-dimensional evaluation (user/business/technical/process/learning), hypothesis-by-hypothesis verdicts, multi-agent inquiry sessions, and structured experience persistence into the knowledge base.
  • Data & integration: built-in MOQL query templates, downgraded workflows for manual data input, report and asset templates, and optional automatic creation of improvement workitems when authorized.
  • Use case: run a version-level check one week after release to confirm delivery quality and generate prioritized remediation stories, or run a full feature evaluation to close the learning loop and capture product learnings.

Quick Start

Run value-validation for product studio version v0.7.0 to generate a quick validation report, key findings, and improvement suggestions.

Frequently Asked Questions about value-validation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I validate post-release product assumptions against actual delivery data?▼

Post-release product validation compares your PRD and design assumptions against observed behavioral data. By querying Feishu MOQL project metrics, it generates concise validation reports, hypothesis verdicts, and prioritized improvement stories for retrospectives.

What is the difference between quick version-level and full feature-level evaluation?▼

Quick version-level evaluation provides automated MOQL data collection and concise reports for rapid post-release checks. Full feature-level evaluation offers multi-dimensional inquiry across user, business, and technical axes, persisting structured learnings into the knowledge base.

Can I run a post-release evaluation without automated Feishu MOQL data access?▼

Yes, you can run a post-release evaluation without automated Feishu MOQL access. The workflow supports a downgraded mode where you manually input user-provided metrics, still allowing you to compare delivery artifacts against PRD assumptions and generate improvement actions.

How do I generate improvement stories after a product release retrospective?▼

To generate improvement stories after a retrospective, input your version metrics and PRD artifacts. The evaluation process identifies gaps between expected and actual outcomes, automatically suggesting prioritized remediation workitems when authorized.

Does post-release validation require a specific PRD or design document structure?▼

Post-release validation requires access to your portfolio PRD and design document structure to map expected outcomes against actual delivery. It uses these artifacts to perform hypothesis-by-hypothesis testing and generate clear improvement actions for learning loops.

What is the best way to close the learning loop after a feature rollout?▼

The best way to close the learning loop after a feature rollout is running a full feature-level evaluation. It captures product learnings through multi-dimensional inquiry, validates hypotheses against behavioral data, and persists structured experiences into your knowledge base.

Related Skills

Explore More Product & Management Skills→
jasonmeansjasonmeans
2

todo-validate-hypothesis

Create and validate structured hypotheses with measurable outcomes.

Community
Intermediate
The13thNodeThe13thNode
3

learn

Capture and organize session learnings into a structured markdown file.

Community
Intermediate
product-on-purposeproduct-on-purpose
527

deliver-launch-checklist

Generate a cross-functional launch readiness checklist with owners, due dates, and go/no-go criteria.

Official
Advanced
rezosndrezosnd

excel-generator

Generate styled Excel workbooks with formulas, charts, and data validation.

Community
Intermediate