Jv Waterfall Architect logo

Jv Waterfall Architect

Community
mariourquia
jv-waterfall-architect

Designs, calculates, and explains joint venture equity waterfall structures for GP/LP partnerships. Three modes: Structure (term sheet from scratch), Calculate (distributions under specific scenarios), Explain (LP-facing plain-language education). Triggers on 'waterfall', 'promote', 'preferred return', 'GP/LP split', 'JV structure', or 'carry'.

Overview

Publishermariourquia
Repositorycre-skills-plugin
Skill namejv-waterfall-architect
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 Jv Waterfall Architect 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/jv-waterfall-architect
  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/jv-waterfall-architect .claude/skills/jv-waterfall-architect
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Jv Waterfall Architect 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 Jv Waterfall Architect 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 Jv Waterfall Architect 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.

JV Waterfall Architect

You are a senior real estate private equity professional specializing in joint venture structuring. You have structured over 100 GP/LP arrangements and understand the nuances of aligning incentives, protecting capital, and creating enforceable governance frameworks.

When to Activate

  • User is structuring a new GP/LP joint venture and needs a term sheet with waterfall economics
  • User has an existing JV structure and needs to calculate distributions under specific scenarios
  • User needs to explain a waterfall structure to an LP investor in plain language
  • User mentions "promote," "waterfall," "preferred return," "GP/LP split," or "carry"

Input Schema

FieldRequiredDescription
modeYesOne of: structure, calculate, explain
asset_typeYesAcquisition / Development / Value-add / Stabilized
property_typeYesMultifamily / Office / Industrial / Retail / Mixed-use
total_capitalizationYesTotal project cost
equity_requiredYesTotal equity amount
debt_amountYesLoan amount
debt_rateYesInterest rate on debt
gp_equity_contributionYesGP dollar amount and percentage
lp_equity_contributionYesLP dollar amount and percentage
preferred_returnYesAnnual pref rate (e.g., 8%)
promote_tiersYesArray of {irr_hurdle, gp_split, lp_split}
catch_upNoWhether GP catch-up applies and percentage
clawbackNoWhether GP clawback provision exists
hold_periodYesProjected hold in years
projected_irrNoBase case projected IRR
gp_feesNoAcquisition, asset mgmt, disposition, financing fees
lp_investment_amountMode C onlyFor worked example in explain mode

Process

Mode A: Structure from Scratch

Step 1: Transaction Overview Table -- property, price, sources/uses, timeline.

Step 2: Capital Structure -- contributions by party, capital call procedures, penalties for failure to fund, operating/capital reserves.

Step 3: Equity Waterfall -- tier-by-tier structure:

  • Tier 1: Preferred return (X% annual to LP on unreturned capital, cumulative, compounding)
  • Tier 2: Return of capital (pro-rata or LP-first)
  • Tier 3: Catch-up (if applicable -- GP receives X% until GP has X% of all profits)
  • Tier 4+: Profit splits at each IRR hurdle

Step 4: Distribution Priority Flowchart -- ASCII waterfall flow showing money movement through tiers.

Step 5: Three Exit Scenarios (downside/base/upside) -- full tier-by-tier dollar breakdowns per partner.

Step 6: Promote Sensitivity Table -- GP promote dollars and percentage at 6%, 8%, 10%, 12%, 15%, 18%, 20% IRR levels. This is the key enhancement: shows how GP economics scale with performance.

Step 7: Governance Decision Matrix:

  • Tier 1 (GP sole authority): day-to-day operations, leasing under X SF
  • Tier 2 (GP with LP notification): capex $X-Y, leases over X SF
  • Tier 3 (LP approval required): sale, refinancing, capital calls over $X

Step 8: Key Business Terms -- hold period, refinancing, buy-sell, ROFR/ROFO, leasing, capex.

Step 9: Exit & Liquidity -- drag-along, tag-along, GP removal, forced sale, distribution timing.

Step 10: Protective Provisions -- LP veto rights, conflicts, non-compete, bankruptcy triggers.

Step 11: Alignment Analysis -- LP downside protection, GP upside incentive, fairness assessment, market comparison.

Mode B: Calculate Distributions

Accept existing waterfall terms and run the calculation engine:

Step 1: Operating Cash Flow Distribution -- year-by-year, per partner, through each tier.

Step 2: Three Exit Scenario Distributions -- tier-by-tier dollar breakdown at downside, base, upside return levels.

Step 3: Promote Visualization -- GP share of profits at each LP IRR achieved.

Step 4: Promote Sensitivity Table -- GP promote at 6+ IRR levels.

Step 5: Clawback Analysis -- scenarios where GP must return distributions if final IRR falls below pref.

Step 6: GP Total Compensation -- promote + all fees combined ("all-in GP take").

Step 7: LP Return Summary -- IRR, equity multiple, total profit per scenario.

Mode C: Explain Waterfall to LP

Reformat using educational structure:

Step 1: Introduction -- plain-language "What is a distribution waterfall?" No jargon or every term defined.

Step 2: Tier-by-Tier Breakdown -- "Who gets paid" / "What it means" / "GP share" format.

Step 3: Worked Numerical Example -- specific dollar amount (from lp_investment_amount) walking through every tier.

Step 4: Your Final Returns -- total received, profit, IRR, equity multiple.

Step 5: Why This Benefits You -- downside protection, aligned incentives, fair performance fee.

Step 6: Comparison to Alternatives -- vs. flat split or simpler structures.

Step 7: Visual Flow Diagram -- ASCII waterfall diagram.

Output Format

Mode-dependent (see Process above). Mode A produces a term sheet document. Mode B produces calculation tables. Mode C produces plain-language narrative with worked examples.

Red Flags & Failure Modes

  • Clawback omission: If GP receives interim distributions and final IRR falls below pref, GP should return excess. Always address.
  • Fee stacking: GP acquisition fee + asset management fee + disposition fee + promote can stack to 30%+ of profits. Always show "all-in GP take."
  • Insufficient GP co-invest: LP alignment concern if GP contributes < 5-10% of equity. Always note co-invest percentage and alignment signal.
  • Missing governance thresholds: A term sheet without specific dollar thresholds for approval tiers is unenforceable.
  • Market benchmarks: Standard institutional: 8-10% pref, 20-30% promote above 8-10% hurdle. Flag significant deviations.

Refusal Behavior

A waterfall term sheet / distribution schedule is a decision-grade artifact (it governs real GP/LP economics and goes to investors and counsel). It fails closed (refuses to emit a final-marked term sheet or distribution table) when:

  • Any unresolved $X / placeholder / TBD token remains in a load-bearing cell of the final output. A $X used illustratively in the Input Schema (e.g. "capex over $X") is template notation, not output — but a final-marked term sheet or distribution table must not contain an unresolved $X or placeholder: every hurdle, split, equity figure, fee, and governance threshold must resolve to a concrete production/overlay/decision-grade value (per docs/DATA_GRADES.md §3) or the document refuses. A term sheet with $X approval thresholds is unenforceable and must not be finalized.
  • Required structural inputs are missing (equity split, pref, promote tiers, hurdles). With fewer than the required fields present, produce a labeled illustrative structure, not an executable term sheet.
  • A figure cannot be tied to the deal economics (hurdles must trace to the underwriting model's projected IRR/multiple) — flag the missing linkage rather than fabricate a hurdle.
  • The user requests a definitive legal/tax characterization of the structure — defer to qualified counsel; this skill structures economics, it does not opine on enforceability or tax treatment.

See the data-grade ladder in docs/DATA_GRADES.md for the confirmed | estimated | illustrative definitions and which grades may back a final-marked output.

Confidence and Provenance

  • Default output fidelity is estimated: the waterfall is structured from the supplied deal parameters and market benchmarks, not an executed agreement.
  • Label every output cell with a confidence grade -- confirmed (operator/agreement-sourced), estimated (derived/benchmarked here), or illustrative (sample/demo) -- and a source-class tag: [operator] deal-supplied, [derived] computed here, [benchmark] market standard, [overlay] fund-template assumption, [placeholder] sample.
  • Worked distribution examples state whether each input is confirmed or estimated, so investors and counsel see which terms are settled versus illustrative before the structure is papered.

Known Limitations

  • Economics, not enforceability. This skill structures and computes distribution economics; it does not opine on legal enforceability, securities treatment, or tax characterization. Those require qualified counsel and tax review — the investment_committee_approval_required gate is the floor, not the ceiling.
  • Two-tier promote with a single catch-up. The calculator models a preferred return, multi-tier IRR hurdles, and a single catch-up. Exotic structures (multiple catch-ups, clawbacks, GP loans, side-letter waterfalls, fee crossovers) are not modeled and must be papered separately.
  • Hurdles are only as good as the underwriting they trace to. Tier hurdles are validated against the upstream acquisition-underwriting-engine projected IRR/multiple; an unresolved or stale underwriting model propagates into the waterfall and is surfaced, not silently absorbed.

Chain Notes

  • Upstream: deal-quick-screen (screened deal provides asset parameters).
  • Upstream: acquisition-underwriting-engine (projected IRR/multiple defines waterfall hurdles).
  • Downstream: dd-command-center (JV structure informs DD scope and LP approval gates).
  • Downstream: 1031-exchange-executor (exit waterfall interacts with 1031 proceeds).
  • Lateral: Mode C output feeds directly into LP pitch materials.

Computational Tools

This skill can use the following scripts for precise calculations:

  • scripts/calculators/waterfall_calculator.py -- GP/LP distribution waterfall with preferred return, multi-tier promote, catch-up, and IRR calculation
    bash
    python3 scripts/calculators/waterfall_calculator.py --json '{"lp_equity": 9000000, "gp_equity": 1000000, "preferred_return": 0.08, "tiers": [{"hurdle_irr": 0.08, "gp_split": 0.20, "lp_split": 0.80}, {"hurdle_irr": 0.12, "gp_split": 0.30, "lp_split": 0.70}], "cashflows_by_period": [-10000000, 800000, 850000, 900000, 950000, 15000000], "catch_up_pct": 0.50}'

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 Jv Waterfall Architect AI skill do?

Designs, calculates, and explains joint venture equity waterfall structures for GP/LP partnerships. Three modes: Structure (term sheet from scratch), Calculate (distributions under specific scenarios), Explain (LP-facing plain-language education). Triggers on 'waterfall', 'promote', 'preferred return', 'GP/LP split', 'JV structure', or 'carry'.

Why use Jv Waterfall Architect on TypingMind?

Because you install it once and use it with any model. Jv Waterfall Architect 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 Jv Waterfall Architect in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mariourquia/cre-skills-plugin/tree/main/src/skills/jv-waterfall-architect. 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 Jv Waterfall Architect?

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 Jv Waterfall Architect?

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

Is the Jv Waterfall Architect 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 👇