domain-lending
Skill1 starsChanged 8 days agoMITView on GitHub
Consumer lending domain knowledge for Business Analysts - glossary, core processes (origination, eKYC, credit assessment and decisioning, offer and e-contract, disbursement, repayment schedule, collections by days-past-due, early repayment, restructuring, closure), business rules (eligibility, interest and repayment calculation methods, repayment allocation order, schedule recalculation, DPD buckets, approval authority), data model with status sets, integrations (credit bureau CIC, eKYC, core/ledger, auto-debit, e-sign, scoring), regulatory touchpoints and a BA question checklist. Use together with any BA task whenever the context is consumer loans, personal loans, buy-now-pay-later, installment, finance company, loan origination system (LOS), loan management system (LMS) or collections - or the user mentions "cho vay", "khoản vay", "vay tiêu dùng", "trả góp", "BNPL", "thẩm định", "giải ngân", "nợ quá hạn", "thu hồi nợ", "lãi suất", "CIC".
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- api-specSkill
- ba-diagramsSkill
- bpmn-modelingSkill
- decision-tableSkill
- domain-bankingSkill
- domain-ecommerceSkill
- domain-logisticsSkill
- domain-paymentsSkill
- edge-case-finderSkill
- functional-decompositionSkill
- meeting-to-requirementsSkill
- requirements-linterSkill
- screen-specSkill
- user-story-writerSkill
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
- Distinctive: line 31
Use masked values for ID numbers, phone numbers and incomes in examples.
≈ “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.
Files
Domain Pack: Consumer Lending / Cho vay tiêu dùng
This skill adds domain knowledge on top of the BA method skills (meeting-to-requirements, requirements-linter, functional-decomposition, user-story-writer, decision-table, edge-case-finder, api-spec, screen-spec, bpmn-modeling, ba-diagrams). It makes their output lending-correct. It focuses on retail/consumer loans (personal loan, BNPL, installment); corporate lending is out of scope. For the bank around the loan (accounts, transfers) also load domain-banking.
How to use the references
| Task | Read |
| Terminology | references/glossary.md |
| Decompose functions, draw processes | references/processes.md |
| Requirements, stories, AC, decision tables (approval, allocation) | references/business-rules.md + references/checklist.md |
| ERD, API payloads, status sets | references/data-model.md |
| Context/sequence diagrams, integration specs | references/integrations.md |
| Compliance | references/regulations.md |
| Goals, reports | references/kpis.md |
How to apply domain knowledge
- Identify the product: cash loan, installment at point of sale, BNPL, credit line; secured or unsecured; own funds or partner funded. It changes the process and the rules.
- Add the scenarios a lending BA never forgets: interest method (flat vs reducing balance) and how it is disclosed, repayment allocation order, due date on a holiday, partial and early repayment recalculation, failed auto-debit retries, DPD buckets and collection actions, restructuring, loan after eKYC mismatch or fraud, cooling-off or cancellation, manual review fallback.
- Separate decision logic from workflow: eligibility, approval authority and allocation are rules (use
decision-table), not flow. - Ask, don't invent: rates, fees, limits and cut-offs are product and risk decisions ->
[value - confirm]. - Flag regulatory touchpoints (rate and fee disclosure, consumer protection, credit reporting, provisioning, data protection) with "verify the current regulation with Compliance/Legal".
Guardrails
- Generic typical practice (Vietnam focus); each lender differs. Never state an interest cap or legal threshold as fact.
references/regulations.mdhas a "last reviewed" date and lists topics to ask about, not legal conclusions.- Use masked values for ID numbers, phone numbers and incomes in examples.
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.