agentleFS
ovargasovargas/virtual-team/skills/domain-glossary/SKILL.md

domain-glossary

Skill14 starsChanged 8 months agoMITView on GitHub

Use when a consumer project has a CONTEXT.md file — defines the domain glossary convention for consistent terminology across specs, plans, and code. Pipeline commands read CONTEXT.md during context loading and use its vocabulary in generated artifacts.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Domain Glossary Convention

What It Is

CONTEXT.md is an optional file at the repository root that defines the project's domain language. It gives the pipeline a shared vocabulary so specs, plans, and code use consistent terminology.

CONTEXT.md is optional. Commands work without it. When present, commands read it during context loading and prefer its defined terms over synonyms.

When to Create One

Create CONTEXT.md when:

  • The same concept has multiple names in specs or code ("order" vs "transaction" vs "purchase")
  • New team members (or AI) use wrong terms because the domain isn't documented
  • start offers to scaffold it during repo initialization

Format

# Domain Context

## Language

| Term | Definition | Avoid |
|------|-----------|-------|
| [Term] | [What it means in this project] | [Synonyms to avoid] |

## Relationships

- A **[Term A]** contains one or more **[Term B]**
- A **[Term B]** references exactly one **[Term C]**

## Example Dialogue

> "When a customer places an **order**, the system creates **line items**..."

## Flagged Ambiguities

- "[Term]" — currently means both X and Y. Needs splitting when [condition].

Pipeline Behavior

Commands that read CONTEXT.md:

  • feature — uses vocabulary when writing the feature spec
  • plan — references terms when naming phases, steps, and components
  • implement — uses terms in variable names, function names, comments, and commit messages; avoids synonyms listed in the "Avoid" column
  • tech-review — checks that code uses defined vocabulary consistently; flags terminology drift

Graceful Degradation

  • No CONTEXT.md → commands proceed normally, no warning
  • Empty sections → skip those sections, use what's populated
  • Ambiguities listed → flag them in generated artifacts when the ambiguous term appears

Related

  • ADR-002 defines this convention: docs/decisions/2026-04-29-domain-glossary-convention.md
  • start scaffolds CONTEXT.md when the user opts in during repo initialization
  • The /virtual-team:grill command maintains CONTEXT.md inline during grilling sessions

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.