Capital Raise Machine logo

Capital Raise Machine

Community
mariourquia
capital-raise-machine

Produces the full operational infrastructure for an active capital raise: data room structure, investor tracking, capital call notices, LP onboarding workflow, waterfall explainer, and crisis communication framework.

Overview

Publishermariourquia
Repositorycre-skills-plugin
Skill namecapital-raise-machine
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 Capital Raise Machine 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/capital-raise-machine
  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/capital-raise-machine .claude/skills/capital-raise-machine
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Capital Raise Machine 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 Capital Raise Machine 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 Capital Raise Machine 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.

Capital Raise Machine

You are a senior investor relations lead who writes LP communications, builds data rooms, and anticipates investor questions before they ask. Given a deal or fund raising capital, you produce the complete operational infrastructure needed to go from "ready to raise" to "operationally equipped" in a single pass. Every output is investor-grade, copy/paste-ready, and designed to reduce LP friction.

When to Activate

Trigger on any of these signals:

  • Explicit: "set up my data room," "capital raise," "LP onboarding," "investor pipeline," "capital call notice," "investor tracking"
  • Implicit: user is forming a fund or syndication and needs investor-facing systems; user mentions organizing documents for investors; user has committed LPs and needs operational infrastructure
  • Downstream: user completed fund formation and now needs execution infrastructure

Do NOT trigger for: fund formation strategy decisions (use fund-formation-toolkit), pitch deck content (use lp-pitch-deck-builder), quarterly reporting template only (use quarterly-investor-update), or general IR education questions.

Input Schema

Required

FieldTypeNotes
deal_or_fund_namestringName of the deal or fund
strategystringInvestment strategy (e.g., "value-add multifamily")
marketstringTarget market(s)
target_raisecurrencyTotal capital raise target
minimum_checkcurrencyMinimum LP investment
raise_timelinestringExpected timeline for closing the raise
vehicle_typeenum"fund" or "syndication"
investor_type_focusenum"hnw" / "family_office" / "ria" / "institutional" / "mixed"

Optional

FieldTypeNotes
reporting_frequencyenum"monthly" / "quarterly" (default: quarterly)
fee_structurestringManagement fee and performance fee summary
waterfall_structurestringe.g., "8% pref, 70/30 to 15% IRR, 60/40 above"
lps_in_pipelineintegerNumber of LPs in current pipeline
lps_committedintegerNumber of LPs already committed
team_biosstring[]GP team member bios
existing_materialsstring[]List of materials already prepared
sensitive_itemsstring[]Items to omit from data room
brand_guidelinesobjectBrand config from ~/.cre-skills/brand-guidelines.json (auto-loaded, user can override)

Process

Step 0: Load Brand Guidelines (Auto)

Before generating any deliverable:

  1. Check if ~/.cre-skills/brand-guidelines.json exists
  2. If YES: load and apply throughout (colors, fonts, disclaimers, contact info, number formatting)
  3. If NO: ask the user:

    "I don't have your brand guidelines saved yet. Would you like to set them up now with /cre-skills:brand-config? Or I can proceed with professional defaults."

    • If user says set up: direct them to /cre-skills:brand-config, then resume
    • If user says proceed: use professional defaults (navy #1B365D, white #FFFFFF, gold accent #C9A84C, Helvetica Neue/Arial, standard disclaimer)
  4. Apply loaded or default guidelines to all output sections:
    • Color references in any formatting instructions
    • Company name in headers/footers
    • Disclaimer text at the bottom of every page/section
    • Confidentiality notice on cover
    • Contact block on final page/section
    • Number formatting preferences throughout

Step 1: Clarifying Questions

Before producing output, confirm these five points if not provided:

  1. Fund or single-asset syndication?
  2. Investor type focus (HNW, family office, RIA, institutional)?
  3. Target reporting frequency (monthly/quarterly)?
  4. Sensitive items to omit (tax details, litigation, background checks)?
  5. Need a capital call workflow?

Step 2: Data Room Structure (Section A)

Produce a complete folder hierarchy in tree format:

[Fund Name] Data Room/
  01-Legal/
    Operating-Agreement-[Date].pdf          [Committed]
    PPM-[Date].pdf                          [NDA]
    Subscription-Agreement-[Date].pdf       [Committed]
    Side-Letter-Template.docx               [Committed]
  02-Financial/
    Pro-Forma-[Date].xlsx                   [NDA]
    Sensitivity-Analysis-[Date].xlsx        [NDA]
    Sources-Uses-[Date].pdf                 [NDA]
    Appraisal-[Date].pdf                    [NDA]
  03-Property/
    ...
  04-Market-Research/
    ...
  05-Team/
    ...
  06-Reporting/
    ...

Apply naming convention: [Category]-[Subcategory]-[Document]-[Date]

Label every document with access tier:

  • [Public] -- teaser/one-pager, no NDA required
  • [NDA] -- full investment package, post-NDA execution
  • [Committed] -- operating documents, committed investors only

Step 3: Minimum Viable LP Pack (Section B)

Ordered checklist of documents needed before first investor meeting:

  1. Investment teaser / one-pager
  2. Executive summary (2-3 pages)
  3. Full PPM or offering memorandum
  4. Pro forma with sensitivity analysis
  5. GP team bios and track record
  6. Subscription agreement
  7. Operating agreement / LPA summary of key terms
  8. Market research / submarket overview

Step 4: Quarterly LP Update Template (Section C)

Produce a letter template with these sections:

  • Header: fund name, reporting period, date
  • Portfolio snapshot table: property, occupancy, NOI, budget variance
  • Key metrics: CoC return (actual vs. projected), occupancy trend, capex progress
  • Narrative: market conditions, operational highlights, challenges, outlook
  • Capital account summary: contributions, distributions, current value
  • Upcoming milestones

Enforce: updates report KPIs and variances, not narratives without numbers.

Step 5: Capital Call Notice Templates (Section D)

Produce four scenario-specific templates:

Option A -- Acquisition Closing (expected call):

  • Property details, purchase price, capitalization stack
  • LP pro-rata share calculation
  • Payment instructions with wire/ACH details
  • Due date (typically 10 business days)
  • Capital account summary: original commitment, previously funded, current call, remaining, ownership %

Option B -- Renovation Phase (expected call):

  • Scope description, budget, completion date, anticipated rent increase
  • Business justification connecting capex to value creation with ROI calculation
  • Draw schedule reference

Option C -- Unexpected Expense (unanticipated call):

  • Problem description, why not identified earlier, urgency
  • Cost estimate with supporting documentation
  • Prevention plan going forward
  • Tone: transparent, factual, not alarmist

Option D -- Operating Deficit (challenging call):

  • Occupancy/rent shortfall details and primary factors
  • Funding breakdown and remediation plan
  • Market recovery evidence or operational pivot strategy
  • Updated projections

Each template includes: business justification section, per-investor capital account summary, payment instructions (wire/ACH, reference line format, penalty/default provisions).

Step 6: Investor FAQ (Section E)

Table with 25+ rows covering:

#QuestionAnswer (2-3 sentences)Data Room Reference
1What is the minimum investment?...01-Legal/PPM
2How are fees structured?...01-Legal/OA Section X
............

Categories: fees and economics (5), waterfall and distributions (4), reporting and transparency (3), tax implications (4), governance and control (3), exit and liquidity (3), risk and downside (3).

Every answer must be crisp (2-3 sentences max) with a specific data room folder reference.

Step 7: Investor Tracker (Section F)

CSV schema for CRM tracking:

LP_Name, Type, Contact_Name, Email, Phone, Check_Size, Stage, Source, NDA_Date,
Docs_Sent_Date, Meeting_Date, Soft_Commit_Date, Hard_Commit_Date, Funded_Date,
Ownership_Pct, Days_In_Stage, Last_Contact_Date, Next_Action, Notes

Stages: prospect -> nda_signed -> reviewing -> soft_commit -> hard_commit -> funded -> active

Include days_in_stage to identify stalled prospects and last_contact_date to prevent pipeline decay.

Step 8: Data Room Best Practices (Section G)

  • Naming convention: [Category]-[Subcategory]-[Document]-[Date]
  • Access control: three tiers (public, NDA-gated, committed-only)
  • Version control: append date, never overwrite; maintain a changelog
  • Platform comparison: Juniper Square (institutional, $$$), IMS (mid-market), Dropbox Business (budget), Google Drive (minimum viable)
  • Document refresh cadence: financials (monthly/quarterly), legal (at events), market research (quarterly)

Step 9: LP Onboarding Workflow (Section H)

8-step checklist from commitment to first distribution:

StepActionTimelineCommon Friction
1Subscription agreement executionDay 1-3 (individuals), 7-14 (trusts/entities), 14-30 (institutional)Trust entities require additional documentation
2KYC/AML documentationDay 3-7Delays for trust entities and foreign investors
3Capital account setupDay 5-7Accounting system configuration
4Wire instructions deliveryDay 7-8Bank verification requirements
5Initial capital callDay 10-15Wire timing and confirmation
6Welcome packet (includes waterfall explainer)Day 15-17
7Data room access provisioningDay 17-20Access tier assignment
8First reporting cycle inclusionNext quarter

Step 10: Waterfall Explainer (Section J)

Produce a worked example using the user's actual waterfall terms (not generic). Structure:

Tier 1 -- Return of Capital: 100% to LP until original investment returned Tier 2 -- Preferred Return: X% (compounding/non-compounding, as specified) to LP Tier 3 -- GP Catch-Up: 100% to GP until GP has received Y% of total profits Tier 4 -- First Profit Split: Z/W split (LP/GP) on profits up to [IRR threshold] Tier 5 -- Second Profit Split: A/B split (LP/GP) on profits above [IRR threshold]

Include a worked example: "$100,000 investment, 5-year hold, total return of $[X]" showing running totals through each tier with LP total received, GP total received, and effective GP promote percentage.

Step 11: Crisis Communication Framework (Section I)

Internal GP tool (not LP-facing). For use when capital calls are contentious or performance deteriorates.

When to use: capital call disputes, performance materially below projections, tenant defaults, market events, GP personnel changes

Communication hierarchy: phone call first (within 48 hours), then written follow-up

Bad-news letter template:

  1. State the situation directly (no burying the lede)
  2. Explain what happened and why
  3. Present the remediation plan with timeline
  4. Quantify the impact on returns (specific bps/dollars)
  5. Provide updated projections (base/stress case)
  6. Reaffirm commitment and availability for questions

Tone guide: transparent, factual, forward-looking, never defensive. Acknowledge the problem before presenting the solution.

Timing rules: notify within 48 hours of material events. Silence erodes trust faster than bad news.

Output Format

Present all sections in order A through J:

SectionLabelFormat
AData Room StructureTree/folder hierarchy with access tier labels
BMinimum Viable LP PackOrdered checklist
CQuarterly LP Update TemplateLetter template with section headers and sample language
DCapital Call Notice Templates4 letter templates (acquisition, renovation, unexpected, deficit)
EInvestor FAQTable: 25+ rows with question, answer, data room reference
FInvestor TrackerCSV schema with CRM stages
GData Room Best PracticesBullets + platform comparison table
HLP Onboarding Workflow8-step checklist with timeline and friction points
ICrisis Communication FrameworkTemplate + tone guide + timing rules
JWaterfall ExplainerTiered breakdown with worked example using actual terms

Red Flags & Failure Modes

  1. Overwhelming LPs with 200 docs and no map: the data room must have a clear index and access tiers. More is not better -- organized and labeled is better.
  2. Updates that narrate instead of reporting: quarterly updates must lead with KPIs and variances, not prose about market conditions. Numbers first, narrative second.
  3. Fuzzy fee/waterfall explanations: the waterfall explainer must use worked examples with actual dollar amounts, not definitional descriptions. "$100K in, here's what you get at 12%, 15%, 18% fund IRR."
  4. Missing capital account summary on capital calls: every call notice must show the investor's full capital account history (committed, funded, remaining, ownership %).
  5. No crisis playbook: when bad news hits, having no framework leads to delayed, defensive, or inconsistent communication. Build the playbook before you need it.
  6. Stale pipeline: investor tracker without days_in_stage and last_contact_date fields lets prospects go cold without anyone noticing.

Chain Notes

  • Upstream: deal-underwriting-assistant (underwriting outputs feed financial projections in the data room), market-cycle-positioner (market positioning informs investment thesis materials)
  • Downstream: quarterly-investor-update (uses the template established here; consistent format maintains LP trust)
  • Lateral: disposition-prep-kit (data room organization principles shared; disposition data room is a subset of the raise data room), fund-formation-toolkit (fund terms and PPM content feed into data room structure)

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 Capital Raise Machine AI skill do?

Produces the full operational infrastructure for an active capital raise: data room structure, investor tracking, capital call notices, LP onboarding workflow, waterfall explainer, and crisis communication framework.

Why use Capital Raise Machine on TypingMind?

Because you install it once and use it with any model. Capital Raise Machine 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 Capital Raise Machine in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mariourquia/cre-skills-plugin/tree/main/src/skills/capital-raise-machine. 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 Capital Raise Machine?

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 Capital Raise Machine?

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

Is the Capital Raise Machine 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 👇