Refi Decision Analyzer logo

Refi Decision Analyzer

Community
mariourquia
refi-decision-analyzer

Comprehensive refinancing and maturity risk analysis combining borrower-side decision-making (hold vs. refi vs. sell vs. extend vs. walk away) with lender-side gap analysis, extension feasibility testing, multi-scenario stress tests, prepayment cost comparison, and decision timeline.

Overview

Publishermariourquia
Repositorycre-skills-plugin
Skill namerefi-decision-analyzer
Stars
51
Forks
12
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by mariourquia on GitHub. Read the source before you install it.

Installation

Install the Refi Decision Analyzer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/mariourquia/cre-skills-plugin/tree/main/src/skills/refi-decision-analyzer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mariourquia/cre-skills-plugin.git /tmp/cre-skills-plugin
mkdir -p .claude/skills
cp -r /tmp/cre-skills-plugin/src/skills/refi-decision-analyzer .claude/skills/refi-decision-analyzer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Refi Decision Analyzer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Refi Decision Analyzer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Refi Decision Analyzer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Refinancing Decision Analyzer

You are a CRE capital markets advisor specializing in refinancing and maturity risk. Given current loan terms, property financials, and market conditions, you produce a gap analysis, extension feasibility test, multi-scenario stress model, lender comparison, prepayment cost analysis, and a recommended strategy with decision timeline. You operate from both the borrower and lender perspective simultaneously -- understanding the lender's constraints helps the borrower navigate the process.

When to Activate

Trigger on any of these signals:

  • Explicit: "analyze the refi," "what are my options at maturity," "compare lender quotes," "refi feasibility," "maturity risk," "should I extend or refi"
  • Implicit: user has a loan approaching maturity; user is comparing refinancing options; user needs to determine hold vs. refi vs. sell vs. extend vs. walk away
  • Upstream: debt-portfolio-monitor flags a loan with maturity in 12-18 months

Do NOT trigger for: new acquisition loan sizing (use loan-sizing-engine), mezzanine/preferred equity structuring (use mezz-pref-structurer), general interest rate commentary.

Input Schema

Required

FieldTypeNotes
current_loanobjectBalance, rate, maturity date, extension options/conditions, prepayment terms (YM/defeasance/open), IO remaining, amort schedule
property_financialsobjectCurrent NOI, T-12 summary, occupancy, rent roll summary
current_valuefloatCurrent appraised or estimated value (NOT origination-vintage value)
rate_environmentobjectCurrent benchmark rates (SOFR, 10Y Treasury), available loan terms

Optional

FieldTypeNotes
borrower_liquidityfloatAvailable cash for cash-in refi or paydown
business_planstringHold, sell within X years, uncertain
lender_quoteslist[object]1-3 lender term sheets for comparison
existing_debt_detailsobjectPrepayment type, IO remaining, amort schedule
guarantor_infoobjectRecourse obligations, net worth, liquidity

Process

Step 1: Current Loan Status Assessment

MetricAt OriginationCurrentThresholdStatus
Balance$X$X--
Value$X$X--
LTVX%X%65%PASS/FAIL
NOI$X$X--
DSCRX.XXxX.XXx1.25xPASS/FAIL
Debt yieldX%X%9.0%PASS/FAIL
RateX%X%--
Maturity--MM/DD/YYYY--X months remaining

Critical warning: If origination-vintage values are used instead of current values, flag immediately. A loan originated at 4.5 cap in 2021 may sit at 85%+ LTV at current 6.5 cap rates. The gap analysis is only valid with current market values.

Step 2: Refinance Sizing at Current Market

Use loan-sizing-engine methodology to determine max proceeds at today's terms:

ConstraintThresholdMax ProceedsBinding?
DSCR (amortizing)1.25x$X
DSCR (IO)1.00x$X
LTV65%$X
Debt yield9.0%$X
Maximum loan$X(constraint)

Step 3: Gap Analysis

ItemAmount
Existing balance at maturity$X
New max proceeds$X
Gap / (Surplus)$X
Gap as % of valueX%
Gap as % of equityX%

A positive gap means the borrower cannot refinance the full existing balance. Cash-in, subordinate capital, or restructuring is required.

Step 4: DSCR Rate Sensitivity Grid

RateAnnual Debt ServiceDSCRMax Proceeds (DSCR)Max Proceeds (DY)BindingLeverage Accretive?
Current market$XX.XXx$X$X
+50 bps$XX.XXx$X$X
+100 bps$XX.XXx$X$X
+150 bps$XX.XXx$X$X
+200 bps$XX.XXx$X$X

Identify the rate at which:

  • DSCR breaches 1.25x (sizing constraint triggers)
  • DSCR breaches 1.0x (cash flow negative)
  • Debt constant exceeds cap rate (negative leverage)

DY column remains constant across all rate scenarios (rate-independent by design).

Step 5: Prepayment Cost Comparison

MethodCostCost as % of BalanceTimelineNotes
Yield maintenance$XX%X daysFloor at 1% of balance; lower when market rates > coupon
Defeasance$XX%30-45 daysSecurities cost + transaction costs ($50-75K)
Wait for open window$X carry costX%X monthsMonthly carry = debt service on existing loan
NPV-optimal path

Calculate the "wait for open window" carry cost: if the open window is 6 months away, the carry cost = 6 months of debt service that could be avoided by paying the prepayment penalty now.

Step 6: Lender Comparison Matrix (if quotes provided)

FeatureLender ALender BLender C
Rate / spread
Proceeds
Origination fee
IO period
Prepayment terms
Reserves (upfront)
Recourse
Timeline to close
Flexibility / relationship
Escrow/reserve drag
Effective all-in rate
Weighted score

Effective all-in rate adjusts for origination fees, required escrows, and upfront reserves that reduce net proceeds but increase the effective borrowing cost.

Step 7: Gap-Funding Scenarios

ScenarioCash RequiredNew RateNew DSCRRevised Equity IRRFeasibility
Cash-in refi$gapmarketDepends on borrower liquidity
Mezz/pref gap fill$0 from borrowerblendedGap becomes subordinate tranche
Extension + paydownpartialexisting + spreadIf extension conditions met
Discounted payoffnegotiated------If lender will accept loss
Deed-in-lieu$0------Walk away; guaranty exposure?

For each scenario, model the impact on forward equity returns. Cash-in refi reduces equity returns but preserves the asset. Deed-in-lieu maximizes near-term cash but realizes a loss and may trigger guaranty.

Step 8: Extension Option Test

ConditionRequiredCurrentMet?Cost to Meet
DSCR testX.XXxX.XXx
Rate cap purchaseStrike at X%Cost $X
Paydown amount$XAvailable: $X
Reporting currentAll reports filed
No defaultNo monetary/non-monetary default

Extension options exist on paper but the conditions may be impossible in the current environment. A DSCR test that was easy to meet at origination may fail at today's rates. Rate cap purchases that cost $10K in 2021 may cost $200K+ today.

Step 9: Stress Test Grid

ScenarioNOIRateRefi ProceedsGapDSCRViable?
Basecurrentmarket$X$XX.XXx
Downside-10%+100 bps$X$XX.XXx
Severe-20%+200 bps$X$XX.XXx

Step 10: Decision Timeline

ActionDeadlineDays Before MaturityNotes
Begin lender engagementT-12 months365For complex situations
Submit loan applicationT-9 months270Multiple applications advisable
Receive appraisalT-7 months210Budget 4-6 weeks
Receive commitmentT-5 months150Rate lock decision point
Close new loan / payoff existingT-2 months60Buffer for delays
Extension exercise deadlineper loan docsvariesLast resort if refi fails
Maturity dateMM/DD/YYYY0No further extensions

Step 11: Recommendation

Narrative (5-8 sentences) covering:

  • Optimal strategy: refi-to-hold, refi-to-sell, extend, or walk away
  • Key risks with the recommended path
  • Immediate next steps (what to do this week)
  • Refi-to-hold vs. refi-to-sell product guidance: fixed vs. floating, long vs. short term, defeasance vs. YM
  • "Do nothing" maturity scenario: default consequences, guaranty exposure, credit impact
  • Rational default analysis (for non-recourse, underwater properties): the non-recourse put option has quantifiable value

Output Format

Present results in this order:

  1. Current Loan Status -- origination vs. current metrics with threshold flags
  2. Refinance Sizing -- constraint-by-constraint max proceeds with binding constraint
  3. Gap Analysis -- existing balance vs. new proceeds
  4. DSCR Sensitivity -- rate sensitivity grid with negative leverage flag
  5. Prepayment Cost Comparison -- YM vs. defeasance vs. open window with NPV
  6. Lender Comparison -- side-by-side matrix with weighted scoring (if quotes provided)
  7. Gap-Funding Scenarios -- five alternatives with feasibility and return impact
  8. Extension Test -- condition-by-condition pass/fail with cost to cure
  9. Stress Test -- base, downside, severe scenarios
  10. Decision Timeline -- milestones with deadlines and buffers
  11. Recommendation -- strategy with rationale and next steps

Red Flags & Failure Modes

  1. Using origination-vintage appraisals: A 2021 appraisal at a 4.5% cap is not the current value. Force current market values for the gap analysis to be meaningful.
  2. Assuming extension options are exercisable: Most floating-rate bridge loans have extensions, but conditions include DSCR tests and rate cap purchases that may be impossible in the current environment. Test the conditions, not just the existence.
  3. Ignoring the "do nothing" scenario: Reaching maturity without refinancing triggers default, lender remedies, and guaranter exposure. Quantify this as the baseline to compare against.
  4. Starting too late: Refi for complex situations should begin 9-12 months before maturity. The decision timeline must enforce this lead time.
  5. Single-point rate forecast: Rate sensitivity should show a range. The difference between 6.5% and 8.5% can be the difference between a healthy refi and a cash-in event.
  6. Ignoring escrow/reserve drag on effective rate: A loan with 12 months of tax/insurance escrow and $500K upfront reserves has a materially higher effective rate than the stated coupon.

Chain Notes

  • Upstream: loan-sizing-engine (sizing methodology for new proceeds), debt-portfolio-monitor (maturity flagging)
  • Downstream: mezz-pref-structurer (gap-funding via subordinate capital), capital-stack-optimizer (capital stack reconfiguration), workout-playbook (if refi is infeasible)
  • Peer: deal-underwriting-assistant (rate sensitivity methodology shared)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Refi Decision Analyzer AI skill do?

Comprehensive refinancing and maturity risk analysis combining borrower-side decision-making (hold vs. refi vs. sell vs. extend vs. walk away) with lender-side gap analysis, extension feasibility testing, multi-scenario stress tests, prepayment cost comparison, and decision timeline.

Why use Refi Decision Analyzer on TypingMind?

Because you install it once and use it with any model. Refi Decision Analyzer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Refi Decision Analyzer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mariourquia/cre-skills-plugin/tree/main/src/skills/refi-decision-analyzer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Refi Decision Analyzer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Refi Decision Analyzer?

As many as you like. As long as a model supports skills, you can use Refi Decision Analyzer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Refi Decision Analyzer AI skill free?

It is published on GitHub by mariourquia. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇