Update to Credit Compass

{
  "description": "Help an Indian home buyer decide whether they can afford a home loan, what rate they will likely get, which bank and government schemes fit, and what the loan will really cost. Use when someone is planning to buy a flat or house, asks \"can I afford a ₹X home loan\", \"how much home loan can I get\", or \"which bank for my home loan\".",
  "included_files": [],
  "name": "home-loan-decision",
  "skill_md_contents": "---\nname: home-loan-decision\ndescription: Help an Indian home buyer decide whether they can afford a home loan, what rate they will likely get, which bank and government schemes fit, and what the loan will really cost. Use when someone is planning to buy a flat or house, asks \"can I afford a ₹X home loan\", \"how much home loan can I get\", or \"which bank for my home loan\".\n---\n\n# Home loan decision\n\nExplicit instructions from the user override this workflow. Skip steps they don't want.\n\n## Answer first, then refine\nStart computing as soon as you know the **loan amount** (or property price) and **monthly take-home**. Do not open with a list of questions. Fill every gap with a stated assumption:\n- Tenure 20 years · existing EMIs ₹0 · living expenses ≈ 35% of take-home\n- Rate: the median from `get_current_interest_rates`\n- Salaried private-sector employee · CIBIL 750 · ready property\n\nSay the assumptions in one line. The cards have sliders, so the user can adjust amount, rate and tenure themselves. After the result, ask at most **one** question — the one that would change the verdict most (usually existing EMIs or expenses).\n\nNever ask for PAN, Aadhaar, account numbers or documents with them.\n\n## Steps\n1. `get_current_interest_rates` (loanType `home`) — never guess a rate.\n2. `check_loan_affordability` with the user's numbers (and the assumptions above) at the median advertised rate. If the verdict is `tight` or `unaffordable`, lead with that and the recommended loan amount before anything else.\n3. `predict_my_interest_rate` — the rate this borrower will likely get, and the bank that fits best.\n4. `calculate_loan_cost` at the predicted rate — EMI, total interest, APR, tax benefit, saving habits.\n5. `find_government_schemes` (purpose Home). For state schemes, check the user's state first.\n6. `list_loan_red_flags` (Home, severity high) — pick the 3 most relevant to their situation (e.g. under-construction → pre-EMI trap).\n\n## Answer format\n1. **Verdict in one line** — affordable / stretch / not yet, with the safe loan amount.\n2. A short table: EMI, FOIR, likely rate, total interest, APR.\n3. Best-fit banks (max 3) and why.\n4. Schemes that match, with the official portal link.\n5. Three things to check before signing.\n6. One line: these are estimates, not a loan offer; link to the relevant `openOnSite` page.\n\n## Don't\n- Don't present advertised minimum rates as what the user will get.\n- Don't recommend a specific lender as \"the best\"; say \"best fit for this profile\" and show the alternatives.\n"
}