Discovery Process

by deanpeters

Discovery Process is an Automation skill for Claude Code, published by deanpeters in Product-Manager-Skills.

6.5K stars780 forkson deanpeters/Product-Manager-SkillsAdded 2026/08/15+1% in starsRepository updated 2026/08/13

View source on GitHub Download repo ZIP

ai-agentsai-product-managementclaude-skillspm-frameworksproduct-management

Install in seconds

Install Discovery Process

Copy Discovery Process into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/deanpeters/Product-Manager-Skills/tree/main/skills/discovery-process ~/.claude/skills/discovery-process

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/deanpeters/Product-Manager-Skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/discovery-process/SKILL.md in deanpeters/Product-Manager-Skills
Installs to: ~/.claude/skills/discovery-process
Collection: One of 25 skills cataloged from this repository
Category: Automation — 1523 skills

What Discovery Process does

Discovery Process runs a full product discovery cycle from problem hypothesis to validated solution, orchestrating framing, interviews, synthesis, and experiments. Use it when a team needs a structured path through problem space exploration and validation before committing to development.

Discovery Process is cataloged under Automation on DirSkills. Discovery Process comes from a repository tagged ai-agents, ai-product-management, claude-skills, pm-frameworks and product-management.

Documentation

README

Excerpt

Purpose

Guide product managers through a complete discovery cycle—from initial problem hypothesis to validated solution—by orchestrating problem framing, customer interviews, synthesis, and experimentation skills into a structured process. Use this to systematically explore problem spaces, validate assumptions, and build confidence before committing to full development—avoiding "build it and they will come" syndrome and ensuring you're solving real customer problems.

This is not a one-time research project—it's a continuous discovery practice that runs in parallel with delivery, typically 1-2 discovery cycles per quarter.

Input

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Discovery Process

What else does deanpeters publish alongside Discovery Process?
Discovery Process is one of 25 skills that DirSkills catalogs from deanpeters/Product-Manager-Skills, the repository it ships in. Its siblings there include AI-Shaped Readiness Advisor, Acquisition Channel Advisor and Agent Orchestration Advisor. Each one is a separate skill with its own page in this directory, installs the same way Discovery Process does, and is maintained by deanpeters in that same repository. The rest of the collection is listed on the deanpeters/Product-Manager-Skills page.
How does Discovery Process compare to other Automation skills?
Discovery Process ranks #204 by stars among the 1523 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Discovery Process against them. Open each page to compare what they document and how they install.