Problem Framing

Problem Framing is an AI Engineering skill for Claude Code, published by mattgierhart in PRD-driven-context-engineering.

182 stars10 forkson mattgierhart/PRD-driven-context-engineeringAdded 2026/09/07Repository updated 2026/08/31

View source on GitHub Download repo ZIP

agent-skillsagentic-codingai-agentsai-assistedclaudeclaude-codeclaude-code-skillscontext-engineeringdeveloper-toolsprdproduct-developmentproduct-managementproductivityspec-driven-developmenttemplatesworkflow

Install in seconds

Install Problem Framing

Copy Problem Framing 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/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v01-problem-framing ~/.claude/skills/prd-v01-problem-framing

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/mattgierhart/PRD-driven-context-engineering.git

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

In this catalog

Source file: .claude/skills/prd-v01-problem-framing/SKILL.md in mattgierhart/PRD-driven-context-engineering
Installs to: ~/.claude/skills/prd-v01-problem-framing
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 3475 skills

What Problem Framing does

Problem Framing transforms vague product ideas into evidence-anchored problem statements for PRD v0.1. It creates CFD entries, gap assessments, and a structured Why section when starting a new product or feature.

Problem Framing is cataloged under AI Engineering on DirSkills. Problem Framing comes from a repository tagged agent-skills, agentic-coding, ai-agents, ai-assisted and claude.

Documentation

README

Excerpt

Problem Framing Skill

Transform market signals into evidence-anchored problem statements.

Consumes

This skill assumes you have zero prior research. It is the starting point.

No prior CFD- entries needed
No prior PR D required
Assumes: Founder/PM has observed market signals but hasn't validated them

Produces

This skill creates/updates:

CFD-* entries (customer feedback) — 1-5 per problem dimension, with confidence scoring (see PRINCIPLES.md)
PRD.md Why section — Evidence-anchored problem statement table
MVP scope signal — Identifies which problem dimensions will drive MVP feature scope (handed to v0.3)

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

Frequently asked about Problem Framing

What else does mattgierhart publish alongside Problem Framing?
Problem Framing is one of 25 skills that DirSkills catalogs from mattgierhart/PRD-driven-context-engineering, the repository it ships in. Its siblings there include Architecture Design, Competitive Landscape Mapping and Environment Setup. Each one is a separate skill with its own page in this directory, installs the same way Problem Framing does, and is maintained by mattgierhart in that same repository. The rest of the collection is listed on the mattgierhart/PRD-driven-context-engineering page.
How does Problem Framing compare to other AI Engineering skills?
Problem Framing ranks #3070 by stars among the 3475 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. 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 Problem Framing against them. Open each page to compare what they document and how they install.