agentleFS
lechithinhlechithinh/ba-claude-skills/skills/domain-banking/SKILL.md

domain-banking

Skill1 starsChanged 8 days agoMITView on GitHub

Retail banking domain knowledge for Business Analysts — glossary, core processes (eKYC onboarding, accounts, fund transfers, cards, lending, deposits, disputes), common business rules (limits, cut-off, threshold-based authentication, maker-checker, reconciliation), data model, integrations (core banking, NAPAS, CITAD, AML, CIC), Vietnamese regulations and a BA question checklist. Use together with any BA task (requirements, user stories, linting, decomposition, diagrams, API/test design) whenever the context is a bank, digital banking, mobile banking, internet banking, core banking, payments inside a bank, cards or loans — or the user mentions "ngân hàng", "chuyển tiền", "mở tài khoản", "eKYC", "thẻ tín dụng", "khoản vay", "tiền gửi", "tra soát", "NAPAS", "CIF".

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read only the file(s) you need for the current task:

    line 11
  2. Very specific:

    Ask domain questions, don't invent answers: Every bank configures limits, fees and products differently.

    line 25
  3. Very specific:

    Never include real customer data, account numbers or card numbers in examples.

    line 33

≈ “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 Pack: Retail Banking / Ngân hàng bán lẻ

This skill adds domain knowledge on top of the BA method skills (meeting-to-requirements, requirements-linter, functional-decomposition, user-story-writer, ba-diagrams). It does not replace them — it makes their output banking-correct.

How to use the references

Read only the file(s) you need for the current task:

TaskRead
Understand or explain terms; write in proper bank terminologyreferences/glossary.md
Decompose functions, draw processes, find missing stepsreferences/processes.md
Write/lint requirements, user stories, acceptance criteriareferences/business-rules.md + references/checklist.md
ERD, data dictionary, API payloadsreferences/data-model.md
Context diagrams, sequence diagrams, integration/API specsreferences/integrations.md
Compliance, NFRs, security, auditreferences/regulations.md
Business goals, reports, success metricsreferences/kpis.md

How to apply domain knowledge

  1. Add the scenarios a banking BA would never forget: limits, threshold-based authentication, cut-off/holidays, timeout & pending status, reversal, reconciliation, duplicate prevention, maker-checker, audit trail, AML screening.
  2. Ask domain questions, don't invent answers. Every bank configures limits, fees and products differently. Put unknown values as [value — confirm with bank policy] and add the question to the open-questions list.
  3. Use the bank's vocabulary: CIF, CASA, value date, cut-off, beneficiary, maker/checker, posting, reversal, reconciliation. Provide Vietnamese equivalents when replying in Vietnamese.
  4. Flag regulatory touchpoints (identity verification, biometric authentication thresholds, data protection, AML) but never state a regulation as final — always add: "verify against the current version of the regulation and the bank's compliance team".
  5. Separate business rules from requirements: limits, fees, cut-off times and thresholds are configurable parameters, not hard-coded requirements. Recommend a parameter/config requirement.

Guardrails

  • Knowledge here is generic to retail banking (with a Vietnam focus). Individual banks differ — present it as typical practice, not the bank's truth.
  • Regulations change. references/regulations.md has a "last reviewed" date; mention it when citing.
  • Never include real customer data, account numbers or card numbers in examples; use masked values (9704 **** **** 1234).

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.