business-data-context
Skill26 starsChanged 10 days agoMITView on GitHub
What the system under test IS at the data level: business entities and why they exist, their relationships, state machines, automatic processes (DB triggers, cron jobs, webhooks), external integrations and the business flows that move data between them. Load it whenever a task touches the database, data validation, a SQL query, test data setup, an entity's lifecycle or status transitions, a trigger or a background job, or asks how the product works under the hood, even when nobody says 'data map'. Reads its map through `bun run context:map business-data-context`. Pure knowledge plus a self-update proposal path: NOT for running a QA stage, NOT for endpoint contracts (business-api-context) or user journeys (business-e2e-context).
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- acliSkill
- agentic-qa-coreSkill
- agentic-qa-onboardSkill
- bug-screenshot-annotationSkill
- business-api-contextSkill
- business-domain-contextSkill
- business-e2e-contextSkill
- evidence-artifactSkill
- exploratory-testingSkill
- framework-developmentSkill
- git-flow-masterSkill
- infra-contextSkill
- iql-contextSkill
- jira-administrationSkill
- judgment-daySkill
- orca-orchestrationSkill
- project-contextSkill
- project-discoverySkill
- pr-review-leadSkill
- regression-testingSkill
- session-handoffSkill
- shift-left-testingSkill
- sprint-conductorSkill
- sprint-testingSkill
- test-automationSkill
- test-documentationSkill
- test-framework-adaptationSkill
- xray-cliSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 0 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
DO: read the map through bun run context:map business-data-context (or --section <id> for one entity or flow).
- Very specific: line 19
DO: treat a placeholder map as "no map".
- Very specific: line 20
DO: cite a fact with its section id and data-updated date.
- Very specific: line 21
WHEN a session observes something that contradicts a section: PROPOSE the one-section edit with its evidence to the user (or to the …
- Very specific: line 22
DO NOT: write anywhere but this skill's own references/.
- Very specific: line 23
DO NOT: copy map content into this SKILL.md.
- Very specific: line 24
Before a step that uses db (verifying a section) or diagrams (redrawing a figure), run the point-of-use check in …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
business-data-context
Kind
contextwith 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-data-context(or--section <id>for one entity or flow). NEVER readreferences/business-data-map.htmlraw: its SVG is most of the bytes and none of the facts. - DO: treat a placeholder map as "no map". Say so and hand the user
project-contextmodedata; never answer data questions as if the system were empty. - DO: cite a fact with its section id and
data-updateddate. A section older than the code it describes is a hypothesis to check with[DB_TOOL], not an answer. - WHEN a session observes something 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 product code. - DO NOT: copy map content into this SKILL.md. Judgment (a rule for READING the data) goes in
## Rulesorreferences/gotchas.md, dated and measured. - Before a step that uses
db(verifying a section) ordiagrams(redrawing a figure), run the point-of-use check inagentic-qa-core/references/preflight-gate.md§8.
Read full SKILL.md when: building a briefing for a DB-level dispatch, deciding whether a section is stale, or proposing an edit to the map.
What this skill knows
One aspect of the system under test: its data. Which business entities exist and why, how they relate, which states each one moves through and what fires the transitions, what runs automatically, which external services read or write it, and the end-to-end flows (User -> API -> Logic -> DB -> Response) that move 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)
| Source | What lives there | Role |
references/business-data-map.html | the synthesis, one <section> per entity, flow, state machine, process and integration, plus discovery-gaps | this skill's map (read via bun run context:map) |
the live database of the active environment ([DB_TOOL]) | schema, constraints, enums, real rows | wins over the map on any conflict |
the backend repo ({{BACKEND_REPO}}) | services, models, validation, triggers, jobs | wins over the map on any conflict |
project-context mode data | the generator that CREATEs the map and UPDATEs its stale sections | owns regeneration |
Rules (judgment, dated)
(none yet: each rule carries YYYY-MM-DD · rule · measured: how)
Not here
- Column lists and raw DDL → the database itself, on demand through
[DB_TOOL]. - Endpoint contracts, auth levels, payloads →
business-api-context. - User journeys and the feature catalog →
business-e2e-context. - Jira stories and their ACs →
.context/PBI/(synced cache).
References
references/business-data-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 data.
Refinements
Lessons land as proposals per agentic-qa-core/references/skill-refinement-protocol.md, never as direct edits.
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
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.

