agentleFS
upex-galaxyupex-galaxy/agentic-qa-boilerplate/.agents/skills/business-domain-context/SKILL.md

business-domain-context

Skill26 starsChanged 10 days agoMITView on GitHub

The vocabulary and the business of the system under test: what the product is for, who pays and why, and what every domain term means (the business meaning, the label the UI shows, the identifier the code uses, how it relates to other terms). Load it whenever a task names, labels or explains a domain concept: writing or refining acceptance criteria, authoring an ATP, naming a test case or a test file, filing a bug in business language, or asking what a term means or why a feature exists, even when nobody says 'glossary' or 'business model'. Reads its map through `bun run context:map business-domain-context`. Pure knowledge plus a self-update proposal path: NOT for running a QA stage, NOT for data structure and lifecycles (business-data-context), endpoints (business-api-context) or journeys (business-e2e-context).

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    DO: read the map through bun run context:map business-domain-context (or --section term-<slug> for one term).

    line 18
  2. Very specific:

    DO: treat a placeholder map as "no glossary".

    line 19
  3. Distinctive:

    DO: use the business term the map gives, and quote the UI label when a step talks about the screen.

    line 20
  4. Distinctive:

    WHEN a session observes a term the map lacks, or a label or meaning that contradicts a section: PROPOSE the one-section edit with its …

    line 21
  5. Very specific:

    DO NOT: write anywhere but this skill's own references/.

    line 22
  6. Very specific:

    DO NOT: copy map content into this SKILL.md.

    line 23

≈ “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

business-domain-context

Kind context with a declared write scope (agentic-qa-core/references/skill-composition-strategy.md §2b). Delivered once by upstream as a placeholder, then owned by the project: the map inside is this project's synthesis. Procedure: agentic-qa-core/references/business-context-maps.md.

Compact Rules

  • DO: read the map through bun run context:map business-domain-context (or --section term-<slug> for one term). NEVER read references/business-domain-map.html raw.
  • DO: treat a placeholder map as "no glossary". Say so and hand the user project-discovery Phase 1; never name test cases or rewrite ACs in invented vocabulary.
  • DO: use the business term the map gives, and quote the UI label when a step talks about the screen. The code identifier belongs in code and selectors, never in a TC title or a bug summary.
  • WHEN a session observes a term the map lacks, or a label or meaning that contradicts a section: PROPOSE the one-section edit with its evidence to the user (or to the conductor when you are a supervised worker), apply it only on approval. Procedure: references/refresh.md.
  • DO NOT: write anywhere but this skill's own references/. No Jira, no .context/, no other skill, no test code, no product code.
  • DO NOT: copy map content into this SKILL.md. Judgment goes in ## Rules or references/gotchas.md, dated and measured.
  • Figures are optional here: the glossary is tables. Before a step that draws one, run the point-of-use check in agentic-qa-core/references/preflight-gate.md §8.

Read full SKILL.md when: building a briefing for an ATP, TC naming or AC refinement dispatch, deciding whether a term is stale, or proposing an edit to the map.

What this skill knows

One aspect of the system under test: its business and its words. What problem the product solves, for whom, how it earns, and what each domain term means to the people who use it. Loading it changes what the agent KNOWS; the only thing it ever does is propose an edit to its own map.

Sources of truth (cited, never copied)

SourceWhat lives thereRole
references/business-domain-map.htmlthe synthesis: overview, business-model, a term-<slug> section per core term, enumerations, discovery-gapsthis skill's map (read via bun run context:map)
the product repos ({{FRONTEND_REPO}}, {{BACKEND_REPO}})UI copy, i18n files, model and enum nameswins over the map on any conflict
the backlog (.context/PBI/, synced from Jira)the words the team writes in stories and ACsevidence for a term, never a copy
business-data-contextthe structure and lifecycle behind each termcited per term, never restated
project-discovery Phase 1the generator that CREATEs the map and UPDATEs its stale sectionsowns regeneration

Rules (judgment, dated)

(none yet: each rule carries YYYY-MM-DD · rule · measured: how)

Not here

  • Entities' structure, triggers and state machines → business-data-context.
  • Endpoint groups, auth and error semantics → business-api-context.
  • Personas, journeys and the feature catalog → business-e2e-context.
  • Stack, environments and deploy → infra-context.
  • Jira stories and their ACs → .context/PBI/ (synced cache).

References

  • references/business-domain-map.html — the map (generated; read through the reader).
  • references/refresh.md — the self-update procedure and this aspect's staleness signals.
  • references/gotchas.md — measured traps in reading this project's vocabulary.

Refinements

Lessons land as proposals per agentic-qa-core/references/skill-refinement-protocol.md, never as direct edits.

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.