agentleFS
jscott3201jscott3201/yet-more-skills/skills/domain-language/SKILL.md

domain-language

Skill4 starsChanged 2 months agoApache-2.0View on GitHub

Clarify ambiguous domain terms using code, examples, and boundary cases. Propose consistent vocabulary when terminology is the task; not an automatic glossary, ADR, or schema migration.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look for one word used for different concepts, different words used for one concept, or an implementation term that obscures a user-visible …

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Domain Language

Make the language match both the domain expert's intent and the system's behavior. Reading an existing glossary is ordinary context gathering; use this skill when the meaning itself is unclear or being revised.

Find the conflicting meanings

Inspect existing terminology in schemas, APIs, source, user-facing text, and project documentation. Use available code-search or index tools, and verify meaningful usages in source. Do not assume a project has a particular glossary filename or documentation layout.

Look for one word used for different concepts, different words used for one concept, or an implementation term that obscures a user-visible distinction. Keep documented meaning, observed behavior, owner intent, and recommendation separate.

Stress-test a definition

Propose a short definition with important near-misses. Try ordinary examples, lifecycle transitions, failure cases, and ambiguous boundaries. In building software, concepts such as observation, command acceptance, physical readback, fault acknowledgement, and verified recovery should not collapse merely because they share a status field.

A name is useful only if it preserves the important distinction. Do not rename public interfaces for aesthetic consistency while hiding a semantic difference. When terminology changes a wire contract, stored data, or compatibility promise, surface that implementation impact before proceeding.

Record only what earns a place

For a discussion, return proposed wording and the evidence or contradiction it resolves. Edit a glossary, API description, or decision note only when documentation changes are in scope. Use the existing project format rather than creating new directories and numbering schemes.

Preserve rationale for a surprising, costly-to-reverse decision when it will help future work. A routine naming clarification rarely needs an architecture record. Ask for owner guidance when the intended domain meaning is genuinely undecidable from available evidence; do not silently substitute a convenient technical interpretation.

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.