tpo-product-owner-agent-operating-manual

Guides product discovery, task decomposition, developer supervision, and release readiness decisions.

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/TECH-HY/SKILLS --skill tpo-product-owner-agent-operating-manual-tech-hy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tpo-product-owner-agent-operating-manual
Source: https://github.com/TECH-HY/SKILLS/tree/main/skills/tpo-product-owner-agent-operating-manual
Command: npx skills add https://github.com/TECH-HY/SKILLS --skill tpo-product-owner-agent-operating-manual-tech-hy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It turns vague ideas and business requests into structured product goals, requirements, architecture plans, and developer tasks while enforcing quality gates before approval or release. ## Core Features & Use Cases - Six Operating Modes: Product Discovery, Requirements Definition, Architecture Planning, Task Creation, Implementation Review, and Release Readiness, each with a defined output structure. - Quality Gates and Scoring: Product, architecture, code, UX/UI, security, and release gates plus a weighted review rubric that maps scores to decisions (Approved, Approved with fixes, Needs revision, Blocked, Rejected). - AI Developer Supervision: Defines required task inputs, expected developer output format, and review steps so implementation stays aligned with product scope. - Use Case: A user pastes a rough feature idea; the agent produces an MVP scope, user stories, acceptance criteria, a task brief for the developer agent, and later reviews the delivered code against the rubric before approving release. ## Quick Start Ask the agent to act as a Technical Product Owner and turn your feature idea into a scoped plan with acceptance criteria and developer tasks.

Frequently Asked Questions about tpo-product-owner-agent-operating-manual

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

FAQPage Schema
How do I turn a vague product idea into structured requirements?

Use the Product Discovery and Requirements Definition modes. The agent produces a product goal, target users, MVP scope, user stories, functional and non-functional requirements, acceptance criteria, and open questions before any development starts.

How do I write tasks for an AI developer agent?

Use Mode 4, Task Creation. Each task includes an ID, goal, context, scope, out-of-scope boundaries, requirements, affected files, testable acceptance criteria, expected developer output, and a review checklist so the developer cannot reasonably misunderstand it.

What quality gates should code pass before release?

The manual defines seven gates: product, architecture, developer task, code, UX/UI, security, and release. The release gate requires met acceptance criteria, passing tests, closed blockers, a rollback plan, monitoring, and documentation.

How is an implementation review scored?

Reviews use a weighted rubric: requirement fit 25%, architecture 20%, code 15%, security 15%, UX/UI 10%, testing 10%, documentation 5%. Scores of 90-100 approve, 75-89 approve with fixes, 50-74 need revision, below 50 reject or block.

When should work be sent back for revision instead of approved?

Return work as Needs revision when it is incomplete, risky, misses acceptance criteria, or the developer changed scope without permission. List required fixes, send a revised task, and track unresolved risks until the Definition of Done is met.