agentleFS
dikamilodikamilo/dx-workflow/skills/dx-domain-discover/SKILL.md

dx-domain-discover

Skill8 starsChanged 4 months agoMITView on GitHub

Mine a brownfield codebase for its domain vocabulary and seed the project glossary.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Keep only terms specific to this domain.

    line 23
  2. Distinctive:

    Stop. Do not chain into another skill.

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

dx-domain-discover

Bootstrap foundation/glossary.md from an existing codebase. Mine the code for the ubiquitous language already living in it — the terms the domain uses — and write them down so every later skill names things consistently. This is the one-time (per-module) extraction pass; /dx-domain keeps the glossary sharp during ongoing work. Re-runnable: pass [module or path] to scope the sweep to one area and grow the glossary incrementally.

Guard. foundation/glossary.md must exist (seeded by /dx-init) — if it is missing, tell the user to run /dx-init first, then stop. Read the current glossary before mining so you extend it, never clobber it.

Invoke dx-references with knowledge-layer for the glossary entry shape and the standards/lessons/glossary distinction — this skill writes the glossary and nothing else.

1 — Mine the vocabulary

Spawn built-in Explore subagents (fan-out, read-only), scoped to [module or path] when given, else the whole repo. Harvest candidate domain terms from:

  • Identifiers — type/class/entity names, enums, key function and method names.
  • Module and package names — the boundaries the code already draws.
  • Comments and existing docs — READMEs, ADRs, doc-comments where terms get defined in prose.

Keep only terms specific to this domain. Drop general programming concepts (cache, retry, handler, DTO) — they are not ubiquitous language.

2 — Resolve and write

For each surviving term, write a glossary entry in the shape from knowledge-layer (**Term**: definition — domain-only, no implementation. _Avoid_: confusable term). Be opinionated: when several names map to one concept, pick one and list the rest under _Avoid_.

Surface, don't average. When you find a term clash (two definitions for one word) or a fuzzy/overloaded term, do not guess — list it and ask the user to resolve it, then record their decision. Keep the file glossary-ONLY: no implementation detail, no rationale, no decisions (those are lessons).

Done when

New and sharpened terms are in foundation/glossary.md and every clash was resolved by the user. Print a short summary — terms added, terms already present, clashes resolved — then:

Glossary seeded: foundation/glossary.md
Next: /dx-domain-discover <another-module>   — extend the sweep to another area
  or: /dx-domain                             — keep the glossary sharp as you work

Stop. Do not chain into another skill.

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.