Domain Modeling
Create and maintain a shared domain vocabulary and model that all code and tests reference.
Process
- Extract terms — What domain concepts appear in the conversation?
- Define precisely — Each term gets a clear, unambiguous definition.
- Map relationships — How do concepts relate to each other?
- Update CONTEXT.md — Write the glossary where the agent can reference it.
- Align code — Ensure code structure reflects the domain model.
Rules
- Every domain concept gets exactly one name.
- Definitions are precise and unambiguous.
- The glossary is the source of truth for vocabulary.
- Code should use domain terms, not technical jargon.
Credit
This skill is based on the work of Matt Pocock (@mattpocock). Original source: mattpocock/skills. Licensed under MIT.
How to use?
1. Download
Go to the AGENT KD SKILL gallery and find this skill card. Click Download to save the SKILL.md file to your computer.
2. Install
Copy the downloaded SKILL.md into your agent's skills directory:
| Agent | Path |
|---|---|
| opencode | ~/.config/opencode/skills//SKILL.md |
| Claude Code | ~/.claude/skills//SKILL.md |
| Codex CLI | ~/.codex/skills//SKILL.md |
| Cursor | ~/.cursor/skills//SKILL.md |
| Gemini CLI | ~/.gemini/skills//SKILL.md |
Example for opencode:
ash mkdir -p ~/.config/opencode/skills/<skill-name> cp SKILL.md ~/.config/opencode/skills/<skill-name>/SKILL.md
3. Use
Restart your agent session. The skill will auto-load based on its description. You can also invoke it explicitly by typing @ in your agent.
4. Verify
Ask your agent something related to the skill's purpose. If it responds using the skill's instructions, you're all set.