domain-modeling

An agent skill by mattpocock, from mattpocock/skills. Tags: analysis, architecture, database, design, documentation.

What it does

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add mattpocock/skills --skill domain-modeling

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/mattpocock/skills
cp -r skills/skills/engineering/domain-modeling ~/.claude/skills/domain-modeling

Safety box score

Grade A, minimal risk: 9 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a documentation-only domain-modeling aid: it reads existing glossary/ADR files and may create or edit `GLOSSARY.md` and `docs/adr/` entries in the repository. It does not contain code execution, network access, or secret-handling behavior; the main thing you grant is in-repo documentation churn and opinionated language policing.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell commands, code evaluation, or shipped scripts are present; the files are plain markdown and a small YAML descriptor.
Network access	0 (none)	There are no download, upload, API-call, or remote-host instructions anywhere in the skill files.
Filesystem reach	1 (low)	It is explicitly designed to create and edit repo-local files like `GLOSSARY.md` and `docs/adr/` ('Create files lazily' and 'update `GLOSSARY.md` inline'), but it does not target paths outside the project.
Secrets & credentials	0 (none)	The skill never asks for tokens, keys, passwords, `.env` files, browser sessions, or CLI logins.
Privilege & persistence	0 (none)	No sudo, global install, service registration, shell startup edits, or other privilege-changing actions are described.
Instruction hijack surface	1 (low)	It strongly directs the agent's behavior ('call it out immediately', 'challenge terms', 'ask if unclear'), but it does not tell the agent to ignore higher-priority instructions or follow remote content.
Irreversible actions	0 (none)	The skill does not post, deploy, pay, book, or delete anything outside documentation edits in the repo.
Transparency	0 (none)	All shipped files are readable text; there are no binaries, encoded blobs, minified code, or unpinned installers.

Before installing

Confirm the team wants the agent to rewrite terminology in `GLOSSARY.md` as it works, not just comment on it.
If this repo may have multiple contexts, read or create `GLOSSARY-MAP.md` first so the agent edits the right glossary.
Check whether your workflow tolerates in-place doc churn under `docs/adr/` when a decision is deemed hard to reverse.

Rated 2026-10-16 by an automated review of 4 files from the skill's repository.

Source

Repository: mattpocock/skills (all skills from this repository)
Path: skills/engineering/domain-modeling/SKILL.md
Branch: main
Updated: 2026-10-05

aws-database — Routes any task involving AWS databases — choosing, comparing, recommending, getting started with.
design-md — Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files
diagramming-code — Generates Mermaid diagrams from Trailmark code graphs.
how — Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live".
principle-exhaust-the-design-space — Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase.
principle-foundational-thinking — Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share.