Skip to content
Get packs

Domain Modeling

Helps an agent build and sharpen a project's shared glossary and architecture decision records

Source Download skill
Repository
mattpocock/skills
Stars
309,658
Licence
MIT
Files
4 files

What it does

When installed, the agent actively helps you define the core terms of your software project. It challenges vague or conflicting words, tests ideas against concrete edge-case scenarios, and checks whether the code matches what you say. It writes resolved terms into a GLOSSARY.md file as they come up, and offers to record important, hard-to-reverse design decisions as Architecture Decision Records (ADRs) only when they meet strict criteria.

Great for

  • Developers starting or untangling a codebase whose terminology has become inconsistent
  • Teams using domain-driven design who want a maintained glossary and decision log
  • People planning a design session who want an agent to push for precise language

Skip it if

  • Simply reading an existing glossary for vocabulary: the skill says this is a basic habit and not its purpose, so it adds little there
  • Small throwaway scripts or prototypes where a formal glossary and decision records would be overhead
  • Projects that expect the agent to record every decision automatically: the skill deliberately limits ADR offers to a few cases

Try asking

  • “Let's design the order cancellation flow. Challenge any terms that conflict with our GLOSSARY.md.”
  • “Help me decide whether 'account' means Customer or User and update the glossary.”
  • “Should we record this database choice as an ADR? Check it against the criteria first.”
  • “Stress-test our billing concepts with edge-case scenarios and tell me where the code disagrees.”
Step-by-step guide: how to use Domain ModelingInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the MIT licence and an attribution note.

    domain-modeling.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip domain-modeling.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip domain-modeling.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Keep GLOSSARY.md free of implementation details, as the skill instructs, so it stays a true glossary.
  • Give the agent access to your code so it can cross-reference how things actually work.
  • Expect it to offer an ADR only for decisions that are hard to reverse, surprising, and the result of a real trade-off.

What's inside

  • ADR-FORMAT.md
  • agents/openai.yaml
  • GLOSSARY-FORMAT.md
  • SKILL.md

Redistributed unmodified from mattpocock/skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.