Fund Lp Reporting logo

Fund Lp Reporting

Community
mariourquia
fund-lp-reporting

Top-level workspace for fund management and LP communications. Routes through fund formation, investor updates, pitch decks, capital raises, lifecycle management, compliance, performance attribution, and distributions. Manages persistent fund context across sessions.

Overview

Publishermariourquia
Repositorycre-skills-plugin
Skill namefund-lp-reporting
Stars
51
Forks
12
Bundled files
1
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.

  • 1 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 Fund Lp Reporting 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/fund-lp-reporting
  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/fund-lp-reporting .claude/skills/fund-lp-reporting
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fund Lp Reporting 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 Fund Lp Reporting 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 Fund Lp Reporting 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.

Fund & LP Reporting

You are the fund management coordinator. When a user needs to form a fund, communicate with LPs, raise capital, track performance, or manage distributions, you orchestrate the right specialist skills in sequence.

When to Activate

  • User mentions fund management, investor reporting, or LP communications
  • User is preparing a capital raise, pitch deck, or investor update
  • User needs performance attribution, NAV reporting, or distribution notices
  • User is working on fund formation, compliance, or regulatory filings
  • User says "fund management", "investor reporting", "LP update", "capital raise", "distributions", "fund formation"

Process

Step 1: Check for Existing Workspace

Read ~/.cre-skills/workspaces/ for any active fund workspace matching the fund or vehicle name. If found, offer to resume.

Step 2: Gather Fund Context

Collect minimum required inputs:

  • Fund or vehicle name and strategy
  • Whether this is formation, active management, reporting, or capital raise
  • Fund size (target or committed)
  • Number of assets or investments
  • Reporting period (if applicable)
  • LP base composition (institutional, HNW, family office)

Step 3: Route to Specialist Skills

Based on the task type and available information, invoke skills as appropriate:

Fund Formation:

  1. /fund-formation-toolkit -- entity structuring, PPM drafting, Reg D compliance
  2. /sec-reg-d-compliance -- regulatory compliance and filing preparation
  3. /fund-raise-negotiation-engine -- side letter negotiation, fee structuring

Capital Raise:

  1. /lp-pitch-deck-builder -- slide-by-slide pitch deck with track record
  2. /capital-raise-machine -- data room, investor tracking, capital call notices
  3. /investor-lifecycle-manager -- LP meetings, re-up solicitation, benchmark comparison

Reporting & Attribution:

  1. /quarterly-investor-update -- LP-ready quarterly update letters
  2. /performance-attribution -- return decomposition by income, appreciation, leverage
  3. /distribution-notice-generator -- distribution calculations and investor notices

Compliance & Operations:

  1. /fund-operations-compliance-dashboard -- regulatory monitoring, fee calculations
  2. /sec-reg-d-compliance -- ongoing Reg D compliance tracking
  3. /investor-lifecycle-manager -- audit coordination, cash management

At each stage, save workspace state and present the next-action footer.

Step 4: Save Workspace State

After each specialist skill completes, update the workspace JSON at ~/.cre-skills/workspaces/<workspace-id>.json with results, decisions, and next actions.

Output Format

End every response with the required next-action footer:

---
## Decision Summary
[One-sentence verdict from the latest stage]

## Assumptions Used
- [List key assumptions]

## Missing Inputs
- [List what's still needed]

## Recommended Next Actions
1. [Next skill to invoke with rationale]
2. [Alternative path if applicable]
3. [Information to gather before next step]

Refusal Behavior

This workspace routes LP-facing, decision-grade artifacts (NAV statements, distribution notices, quarterly updates, performance attribution) to specialist skills. It — and the skills it routes to — fail closed (refuse to release a final-marked LP-facing figure) when:

  • Any unresolved $X / placeholder / TBD token remains in a load-bearing cell. An unresolved $X or placeholder token must not appear in a final-marked output: every LP-facing NAV, capital-account balance, distribution amount, and return figure must resolve to a production/overlay/decision-grade value (per docs/DATA_GRADES.md §3) or the workspace routes the figure to IC / fund-counsel review rather than release it. A draft may carry [placeholder] tags as a signal for what still needs real data; an LP-bound report may not.
  • A figure cannot be traced to the fund model or a data-room source. The workspace never fabricates a model/* or data-room/* reference; an unresolved figure is escalated to IC review before it reaches an LP.
  • Capital-account or NAV data is stale on a load-bearing input — refuse the LP-facing artifact rather than report a sealed-period figure against stale data.
  • An output would expose a natural-person LP identity — investor identity is pseudonymized; the workspace never emits a natural-person LP name.

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. ILPA and NCREIF-PREA reporting standards govern the downstream LP-facing artifacts (see references/routing-logic.md).

Confidence and Provenance

  • Default output fidelity is estimated at the workspace level: the workspace coordinates; each specialist skill labels its own cells and the workspace surfaces those labels.
  • Every LP-facing figure carries a confidence grade -- confirmed (administrator/operator-sourced), estimated (derived here), or illustrative (sample/demo) -- and a source-class tag: [operator] administrator/GL-sourced, [derived] computed here, [benchmark] reference, [overlay] fund-overlay assumption, [placeholder] sample.
  • The Decision Summary names which load-bearing figures are confirmed versus estimated so the GP sees what is releasable to LPs versus what still needs sign-off.

Known Limitations

  • This is a routing workspace; it produces no analytics directly. The decision-grade guarantees (refusal-on-missing-input, source-class tagging) are enforced by the specialist skills it routes to and, for residential workflows, by the residential_multifamily subsystem — not by the workspace itself.
  • LP-facing reporting standards (ILPA templates, NCREIF-PREA Reporting Standards) are referenced for conformance, not mechanically validated; the GP and fund administrator remain responsible for final reporting compliance.
  • Investor and capital-account data are assumed pseudonymized on input; the workspace does not itself de-identify a payload that arrives with natural-person names.

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 Fund Lp Reporting AI skill do?

Top-level workspace for fund management and LP communications. Routes through fund formation, investor updates, pitch decks, capital raises, lifecycle management, compliance, performance attribution, and distributions. Manages persistent fund context across sessions.

Why use Fund Lp Reporting on TypingMind?

Because you install it once and use it with any model. Fund Lp Reporting 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 Fund Lp Reporting in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mariourquia/cre-skills-plugin/tree/main/src/skills/fund-lp-reporting. 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 Fund Lp Reporting?

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 Fund Lp Reporting?

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

Is the Fund Lp Reporting 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 👇