discovery

Name: discovery
Availability: InStock
Author: bernajaber

Conduct deep conversational interviews to extract product requirements and produce a brief document.

Updated Feb 26, 2026

Search Tags:#requirements #discovery #user-interview #product-brief #gate-1 #feature-id

Ready to run

npx skills add https://github.com/bernajaber/pi-product-system --skill discovery-bernajaber

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: discovery
Source: https://github.com/bernajaber/pi-product-system/tree/main/skills/discovery
Command: npx skills add https://github.com/bernajaber/pi-product-system --skill discovery-bernajaber

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill captures the operator's intent through a deep, iterative interview so the project has a single-source, assumption-free brief that defines what to build and when to proceed.

Core Features & Use Cases

Deep interviews with no round limit: Ask targeted follow-ups until every behavioral decision is the operator's, not the agent's.
Structured output and workflow updates: Produce a sub-one-page brief saved to .pi/specs/<feature>/brief.md, choose a kebab-case feature ID, and update workflow-state.json and .pi/feature-list.json.
Gate 1 presentation: Present the brief in Portuguese and collect a formal approval, correction, or restart decision to drive the next phase.

Quick Start

Ask the operator in Portuguese to describe what they want to build, probe until no assumptions remain, and then save the brief to .pi/specs/<feature>/brief.md.

Frequently Asked Questions about discovery

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

FAQPage Schema

How do I turn operator input into a concise product brief?▼

The product discovery process works by conducting deep conversational interviews with no round limit, asking targeted follow-ups until every behavioral decision belongs to the operator, and then generating a sub-one-page brief saved to .pi/specs/<feature>/brief.md.

How do I run user interviews for product discovery without making assumptions?▼

To run user interviews for product discovery without assumptions, the Skill probes open-ended operator descriptions iteratively, asking targeted follow-up questions until no assumptions remain and all feature requirements are explicitly defined.

When do I need a Gate 1 discovery process for feature requirements?▼

You need a Gate 1 discovery process for feature requirements when a product or feature requires greenfield or brownfield work, ensuring you capture a single-source, assumption-free brief before proceeding to the next phase.

Can I generate a kebab-case feature ID and update workflow-state.json automatically?▼

Yes, you can generate a kebab-case feature ID and update workflow-state.json automatically, as the Skill handles structured output by saving the brief to .pi/specs/<feature>/brief.md and updating workflow-state.json and .pi/feature-list.json accordingly.

What is the best way to conduct deep conversational interviews for product requirements?▼

The best way to conduct deep conversational interviews for product requirements is using an iterative approach that handles open-ended descriptions, probes until no assumptions remain, and optionally incorporates reference research to produce a formal brief document.

Does the Gate 1 brief presentation support approval, correction, or restart decisions?▼

Yes, the Gate 1 brief presentation supports approval, correction, or restart decisions by presenting the brief in Portuguese and collecting a formal gate confirmation to drive the next workflow phase.