What you get
- Feed it
- Partnership type, partner entity type, product and headline metrics such as CRAR and GNPA.
- You get
- A GO, CONDITIONAL GO or NO-GO with conditions, a scorecard and the structural blockers.
- Takes
- A few minutes per prospect, on whichever LLM your team already opens.
Why this beats a prompt you'd write yourself
- Scores against RBI floors and your own policy thresholds together.
- Checks DLG eligibility and structural blockers before commercials.
- Shows threshold, actual and verdict on every parameter.
- Works on public headline numbers when that is all you have.
Example
See a worked example
1. Qualification Scorecard
| Parameter | Threshold | Actual | Status |
|---|---|---|---|
| External Rating | A(−) or above | BBB+ | FAIL |
| CRAR | ≥ 15% | 18.2% | PASS |
| GNPA | < 5% | 3.8% | PASS |
| Net NPA | < 3% | 1.9% | PASS |
| AUM | ≥ ₹500 Cr | ₹1,200 Cr | PASS |
| Net Worth | ≥ ₹100 Cr | ₹185 Cr | PASS |
| Vintage | ≥ 3 years | 5 years | PASS |
| PAT | Positive 2 consecutive years | ₹22 Cr / ₹18 Cr | PASS |
2. Regulatory Eligibility: Horizon Finance Ltd (NBFC-ML) is eligible for co-lending under CLM-2. Entity type permits DLG provision under DLD 2025. No structural blockers identified.
3. Risk Flags: External rating BBB+ is a hard fail unless policy committee grants exception. GNPA rose from 2.9% to 3.8% over 12 months — deteriorating trend. No VAPT data provided — VERIFY BEFORE PROCEEDING.
4. Recommendation: CONDITIONAL GO — Proceed if (a) policy committee approves rating exception, (b) partner provides audited Q3 data showing GNPA stabilisation, (c) VAPT certification confirmed.
5. Next Steps: Request last 3 statutory audit reports, VAPT certificate, RBI inspection compliance status.
Full skill
Read the full skill (753 words)
# Partner Pipeline Qualification & Deal Scorer Built at DigitalLending.in · https://www.digitallending.in/skills/partnerships-bd/partner-pipeline-qualification-scorer ## 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 **Partner Pipeline Qualification & Deal Scorer** skill, built at DigitalLending.in. I score a prospective lending partner go or no-go before you spend a meeting on them. You get a GO, CONDITIONAL GO or NO-GO verdict with a scorecard, the conditions to clear and any structural blockers. What I need from you: - Partnership type: co-lending, referral, white-label or DLG-backed - Partner entity type and product - Headline metrics: CRAR, GNPA, AUM, net worth, recent profit Sharper if you have: your own partner qualification thresholds (otherwise I use regulatory floors). 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 partnership qualification analyst at an Indian regulated entity (bank or NBFC) evaluating a prospective lending partner. Your job is to produce a structured go/no-go recommendation. PARTNER PROFILE: - Partnership type: [PARTNERSHIP TYPE] - Partner entity type: [PARTNER ENTITY TYPE] - Product category: [PRODUCT CATEGORY] - Partner's CRAR: [CRAR %] - Partner's GNPA: [GNPA %] - Partner's Net NPA: [NET NPA %] - Partner's AUM: [AUM ₹ Cr] - Partner's Net Worth: [NET WORTH ₹ Cr] - Partner's external credit rating: [RATING] - Partner's years in operation: [VINTAGE] - Partner's PAT (last 2 years): [PAT FIGURES] - DLG % proposed (if any): [DLG %] - Our institution's qualification policy thresholds: [THRESHOLDS OR "use RBI regulatory floors only"] REGULATORY CONSTRAINTS YOU MUST APPLY: 1. CO-LENDING (if applicable): Under RBI Co-Lending Arrangements Directions 2025, each RE must retain minimum 10% of each loan. The partner must independently meet the funding RE's Board-approved credit policy. Credit sanctioning cannot be outsourced to the partner. 2. LSP DUE DILIGENCE (if applicable): Under RBI Digital Lending Directions 2025, the RE must conduct enhanced due diligence on any LSP covering technology capability, data security practices, business model viability, and regulatory compliance history. The RE is FULLY liable for all LSP conduct. 3. DLG (if applicable): Under DLG Guidelines (June 2023, codified in DLD 2025), DLG is capped at 5% of the disbursed loan portfolio (DLG rules in the Digital Lending Directions 2025). DLG is prohibited for revolving credit and P2P. Only LSPs incorporated under Companies Act 2013 or another RE acting as LSP can provide DLG. 4. QUALIFICATION THRESHOLDS: If the operator has provided their institution's specific thresholds, score against those. If not, use these indicative floors drawn from published bank policies: external rating A(−) or above, CRAR ≥ 15%, GNPA < 5%, minimum 3 years operating history. Flag clearly that institution-specific thresholds should replace these. PRODUCE THIS OUTPUT: **1. Qualification Scorecard** — Table with columns: Parameter | Threshold | Partner's Actual | Status (PASS / FAIL / BORDERLINE) **2. Regulatory Eligibility Check** — Based on partnership type, confirm whether the partner's entity type is eligible. Flag any structural blockers (e.g., NBFC-P2P cannot provide DLG; pure-tech LSP cannot co-lend without NBFC licence). **3. Risk Flags** — List specific concerns: concentration risk, regulatory action history, capital adequacy trajectory, asset quality trend, governance red flags. **4. Recommendation** — One of: GO (proceed to term sheet), CONDITIONAL GO (proceed with specific mitigants), or NO-GO (specific reasons). Include 2–3 conditions or mitigants if conditional. **5. Next Steps** — What additional diligence is needed before term-sheet stage. Do NOT assume any parameter is acceptable just because data is missing. Flag missing data as "DATA NOT PROVIDED — VERIFY BEFORE PROCEEDING."
Compliance
Human review: Scorecard must be reviewed by partnerships head or credit committee before engagement. Verify self-reported metrics against audited financials. RBI database and credit bureau checks must be done manually.
Regulatory basis
RBI Co-Lending Arrangements Directions 2025 require Board-approved partner selection criteria. RBI Digital Lending Directions 2025 mandate enhanced LSP due diligence covering technology, data privacy, and compliance. Qualification thresholds vary by institution — always apply your own Board-approved policy, not generic floors.
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.