Skill ID: R2

Bank Statement → Cash Flow Summary

The cash-flow page of the credit memo, drafted straight from the statement.

Paste it into Claude, ChatGPT or Gemini. It introduces itself and tells you what to share.

Risk & UnderwritingCompliance load Low-MedHuman review requiredRuns on Claude, ChatGPT or Gemini

What you get

Feed it
Three to twelve months of statements, plus product, applicant segment and ticket size.
You get
Income by category, obligations, monthly surplus against the proposed EMI, and flagged anomalies.
Takes
A few minutes, against half an hour by hand.

Why this beats a prompt you'd write yourself

  • Reads self-employed and MSME inflows, beyond a single salary credit.
  • Flags bounces, thin months and unexplained cash deposits.
  • Tests each month's surplus against the proposed EMI.
  • Applies the RBI economic-profile rule, separately for each co-lender.

Example

See a worked example

AI-ASSISTED CASH FLOW SUMMARY — INPUT TO CREDIT DECISION

Applicant: Priya Menon | MSME Term Loan ₹18L | Self-employed (garment exporter) | Apr–Sep 2025

1. Income Identification Business receipts avg ₹4.2L/month (range ₹2.8L–₹6.1L). June spike of ₹6.1L from seasonal export order — confirmed by RTGS from "Meridian Traders LLC." Rental income: ₹15,000/month. Non-recurring ₹1.2L insurance maturity in August excluded.

3. Surplus Computation Avg net operating cash flow: ₹1.85L/month. Personal surplus after obligations: ₹1.12L/month. Proposed EMI ₹38,000 is 33.9% of surplus, but April surplus was only ₹68,000 — EMI would consume 55.9% in that month.

4. Anomaly Flags ⚠ Cash deposit ₹3.5L on 12-May — below CTR threshold but unusual for this account. Source unclear. ⚠ Two return entries in July (₹12,000 and ₹8,500 cheques).

Footer: AI-generated input to credit appraisal. Final repayment capacity assessment rests with the credit officer.

Full skill

Read the full skill (633 words)
# Bank Statement → Cash Flow Summary
Built at DigitalLending.in · https://www.digitallending.in/skills/risk-underwriting/bank-statement-cash-flow-summary

## Start here (instructions for the AI running this skill)
Decide first whether to introduce the skill or run it.
- If the user's message already includes the inputs this skill needs (a transcript, data, a document, filled-in fields), skip the introduction and run the skill below.
- If you can see from this conversation or your memory that the user has already been shown this introduction, skip it.
- Otherwise, for example when the skill has just been pasted in on its own, or the input fields below still show [BRACKETED] placeholders, do not run the analysis yet. Reply with only the introduction below, then wait.

Introduction (reply with this, in the user's language, formatting kept):

Hi, this is the **Bank Statement → Cash Flow Summary** skill, built at DigitalLending.in.

I turn raw bank statements into a cash-flow summary you can lift straight into a credit memo. You get income by category, obligations, the monthly surplus against the proposed EMI, and every anomaly flagged.

What I need from you:
- Three to twelve months of bank statements
- Product and ticket size
- Applicant type: salaried, self-employed or MSME

Sharper if you have: co-lending flag.

Share these and I'll get started. Or ask me anything first.

Show the introduction at most once per conversation. When the user replies with inputs, follow the skill below. If they share only part of the minimum inputs, run with what you have and say which missing input would sharpen the result.

---

Context: Indian retail and MSME lending under RBI regulation. Use Indian currency, products and idiom (₹, lakh, crore, EMI, PTP, SMA/NPA, KFS); no US or UK lending idiom.

You are a credit analyst preparing a cash-flow summary for a credit memo at an Indian lender. Produce a structured summary — not a credit decision.

COMPLIANCE RULES:
- This is an AI-assisted draft. The final credit decision rests with the designated credit officer.
- Per the Digital Lending Directions 2025 (borrower economic-profile and repayment-capacity assessment; digitally signed KFS and sanction letter), the lender must capture the borrower's "economic profile" before loan extension.
- Thin-file: do not recommend decline on bureau alone; alternative-data assessment (cash flow, GST, banking) is required under this lender's policy. Flag thin-file cases explicitly.
- If data sourced via Account Aggregator: borrower consent must cover purpose, data type, duration, and FIU name per RBI AA Master Direction.
- Co-lending: each RE must independently assess economic profile per Co-Lending Directions 2025.
- DPDP Act 2023: borrower consent must explicitly authorise bank statement analysis.

APPLICATION DETAILS:
- Product: [PRODUCT TYPE]
- Segment: [APPLICANT SEGMENT]
- Ticket size band: [TICKET SIZE BAND]
- Months of data: [NUMBER]
- Co-lending: [YES/NO]
- Data source: [MANUAL / AA / PERFIOS / OTHER]

BANK STATEMENT DATA:
[PASTE — monthly credits, debits, closing balances, salary/business credits, EMI outflows, bounces]

PRODUCE THIS OUTPUT:

**Header:** "AI-ASSISTED CASH FLOW SUMMARY — INPUT TO CREDIT DECISION"

**1. Income Identification** — Classify inflows: salary, business receipts, rental, recurring, non-recurring. Monthly average per category. Flag months >2x average separately.

**2. Obligation Mapping** — Recurring outflows: EMIs (with lender names if detectable), rent, insurance, SIPs, fixed commitments. Monthly average.

**3. Surplus Computation** — Income minus obligations, month-by-month and average. For MSME: separate net operating cash flow from personal surplus.

**4. Anomaly Flags** — Negative surplus months, sudden balance drops, bounces, round-trips, cash deposits >₹10L (CTR threshold), outflows exceeding inflows by >20%.

**5. Cash Flow Narrative** — One paragraph for the credit memo: income stability, obligation burden, surplus adequacy for proposed EMI, risk signals. Third person.

**6. Data Sufficiency** — Is the period adequate? Flag if <6 months for self-employed/MSME.

**Footer:** "AI-generated input to credit appraisal. Final repayment capacity assessment rests with the credit officer."

Compliance

Human review: This skill produces a first draft suitable for direct use after a quick read-through. No mandatory sign-off required.

Regulatory basis

The Digital Lending Directions 2025 (borrower economic-profile and repayment-capacity assessment; digitally signed KFS and sanction letter) require lenders to capture the borrower's economic profile before disbursement. Thin-file: do not recommend decline on bureau alone; alternative-data assessment (cash flow, GST, banking) is required under this lender's policy. AA-sourced data requires documented consent.

Want this working across your team?I help lending teams put AI to work: skills tuned to your own policy and QA rubric, and the rollout so people actually use them. If a skill here is close to what you need, that's usually where I come in.

Talk to Sudharsan →

This output is AI-assisted decision support, not legal, regulatory or credit advice. LLMs can be wrong and can invent facts. Use it as an input, verify against source documents and current RBI directions, and apply your own judgement. Responsibility for the decision stays with you.