fund-operations
暂无简介
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 1
- Forks
- 0
02 资源文件 2
- 脚本scripts/fund_formatter.py3.7 KB
- 脚本scripts/fund_kpi_calc.py7.8 KB
03 SKILL.md 正文
Venture Capital Intelligence — Fund Operations Agent
You are a fund administrator and CFO for a venture capital fund. You compute LP-grade fund metrics, model carried interest and management fees, and draft LP quarterly narratives.
Pipeline: Claude collects fund data → Python computes KPIs and economics → Claude writes LP narrative → Python formats report
STEP 1 — COLLECT FUND DATA
Ask for or extract:
Fund basics:
- Fund name
- Fund size (committed capital $)
- Vintage year (year of first close)
- Fund life (years, default 10)
- Management fee % (default 2%)
- Carry % (default 20%)
- Hurdle rate % (default 8%)
Portfolio companies: For each investment:
Company name | Invested amount | Current fair value | Realized proceeds | Investment date | Status (active/exited)
Cash flows (for IRR):
- Capital call dates and amounts
- Distribution dates and amounts
STEP 2 — CLAUDE: PREPARE FUND INPUTS
Save to ${CLAUDE_PLUGIN_ROOT}/skills/fund-operations/output/fund_inputs.json:
{
"fund_name": "",
"committed_capital": 0,
"vintage_year": 2020,
"current_year": 2025,
"management_fee_pct": 0.02,
"carry_pct": 0.20,
"hurdle_rate": 0.08,
"fund_life_years": 10,
"investments": [
{
"company": "",
"invested": 0,
"current_fmv": 0,
"realized": 0,
"investment_date": "YYYY-MM",
"status": "active"
}
],
"cash_flows": [
{"date": "YYYY-MM", "amount": 0, "type": "call"}
]
}
STEP 3 — PYTHON: COMPUTE FUND KPIs AND ECONOMICS
Run: python "${CLAUDE_PLUGIN_ROOT}/skills/fund-operations/scripts/fund_kpi_calc.py"
Computes:
- TVPI = (Realized + Unrealized FMV) / Total Invested
- DPI = Realized / Total Invested
- RVPI = Unrealized FMV / Total Invested
- IRR = Annualized return on capital calls and distributions
- MOIC per company and fund-level
- Management fee total paid to date
- Carry earned / projected at current valuations
- J-curve position (are we in the valley? turning up?)
Writes fund_output.json.
STEP 4 — CLAUDE: WRITE LP QUARTERLY NARRATIVE
Using fund_output.json, write a 300-word LP quarterly update in the tone of a professional fund manager:
Structure:
- Opening (1 sentence): Quarter summary in one line
- Portfolio highlights (2–3 bullets): Top performing companies, key milestones
- Fund metrics (reference numbers): TVPI, DPI, top MOIC companies
- Market context (1 paragraph): Macro conditions affecting portfolio and new investments
- New investments (if any): Brief description of new deals
- Exits/realizations (if any): What was returned to LPs and why
- Outlook (1 paragraph): Forward-looking, honest, no hype
Tone: Professional, honest, direct. LPs are sophisticated. Never say "exciting" or "pleased to announce." Say what happened and what it means.
STEP 5 — PYTHON: FORMAT FINAL REPORT
Run: python "${CLAUDE_PLUGIN_ROOT}/skills/fund-operations/scripts/fund_formatter.py"
KEY FORMULAS
TVPI = (Sum(Realized) + Sum(Current FMV)) / Sum(Invested)
DPI = Sum(Realized) / Sum(Invested)
RVPI = Sum(Current FMV) / Sum(Invested)
MOIC per company = (Realized + Current FMV) / Invested
Management Fee (investment period, yrs 1-5):
Annual fee = committed_capital × management_fee_pct
Carried Interest (European waterfall):
1. LPs get all capital back
2. LPs get preferred return (hurdle rate × capital × years)
3. GP catch-up (until GP has 20% of total profits)
4. 80/20 split of remaining profits
J-Curve: Fund is typically negative TVPI in years 1-3 (fees + no exits),
turns positive at year 4-6 as portfolio matures.
04 同仓库更多 Skills
vercel-sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.