discover

Create a discovery.md with JTBD canvas, assumption map, and experiment backlog.

Updated Mar 12, 2026
One-click install
npx skills add https://github.com/Nerfherder16/BrickLayer --skill discover-nerfherder16
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: discover
Source: https://github.com/Nerfherder16/BrickLayer/tree/main/.claude/skills/discover
Command: npx skills add https://github.com/Nerfherder16/BrickLayer --skill discover-nerfherder16

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Structured discovery to validate feature ideas before building, combining JTBD analysis, assumption mapping, and experiment design.

Core Features & Use Cases

  • JTBD canvas generation for a feature idea
  • Five-assumption mapping with prioritization
  • End-to-end discovery.md output with an experiment backlog
  • Output path guidance and timestamped discovery file handling

Quick Start

Run /discover on a feature idea to generate the discovery.md with a JTBD canvas, assumption map, and an experiment backlog.

Frequently Asked Questions about discover

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

FAQPage Schema
How do I validate feature ideas before adding them to the product backlog?

To validate feature ideas before backlog creation, you can use structured JTBD discovery and assumption mapping to identify risks. This process generates a discovery file detailing user jobs, prioritized assumptions, and an experiment backlog to test viability.

What is JTBD discovery and how does it work for software feature ideation?

JTBD discovery is a product management framework analyzing what users are trying to accomplish rather than their demographics. It works for software feature ideation by generating a canvas that maps user jobs, assumptions, and experiments to validate early concepts.

How do I map and prioritize assumptions during product discovery?

To map and prioritize assumptions during product discovery, you generate an assumption map of five items within a discovery file. This identifies the riskiest assumptions surrounding a feature idea so you can design targeted experiments to validate them.

Can I generate an experiment backlog directly from early feature concepts?

Yes, you can generate an experiment backlog directly from early feature concepts by running a structured discovery process. This combines JTBD analysis and assumption mapping to output a discovery file containing a ready-to-use experiment backlog for your team.

Does this discovery process require any specific frameworks or dependencies to run?

No external frameworks or dependencies are required to run this discovery process. It operates independently to generate a timestamped discovery.md file within a designated directory containing the JTBD canvas, assumption map, and experiment backlog.