vc-finder
Takes a startup product URL or description, detects the industry and funding stage, identifies 5 comparable funded companies, searches who invested in those companies (Track A), finds VCs who publish investment theses about this space (Track B), and returns a ranked sourced list of relevant investors with deep-dives and outreach hooks. Use when asked to find investors for a startup, identify which VCs fund products like mine, research who backs companies in my space, build a VC target list, or find investor-market fit.
npx skills add Varnan-Tech/opendirectory --skill vc-finder --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Takes a product URL or description, detects the industry and funding stage, identifies 5 comparable funded companies, searches who invested in those companies (Track A), finds VCs who publish investment theses about this space (Track B), and returns a ranked sourced list of relevant investors with deep-dives and outreach hooks.
How it works
- Step 1: Setup checks for API keys (TAVILY_API_KEY required; FIRECRAWL_API_KEY used if present; fallback to Tavily extract).
- Step 2: Gather input: product URL or pasted description; derive product_slug from URL; optional stage hint and geography.
- Step 3: Fetch product page content via Firecrawl (preferred) or Tavily extract fallback; save raw markdown to /tmp/vc-product-raw.md.
- Step 4: Detect stage signals locally from the fetched content using regex to assign a dominant stage and confidence, saving results to /tmp/vc-stage-signals.json.
- Step 5: Product analysis: print content and signals, generate taxonomy, ICP, detected stage, geography bias, and an empty comparable_companies array to be filled in Step 6.
- Step 5b: Curated Pre-Match Against Verified Fund Dataset: map taxonomy to fund dataset tags and stage, write a product context file to /tmp/vc-product-context.json, and score against an embedded fund dataset to identify seed comparables for Track A.
When to use it
Use when asked to find investors for a startup, identify which VCs fund products like mine, research who backs companies in my space, build a VC target list, or find investor-market fit.
What it can touch
Uses the following tools and scripts as described in the Step sections: Firecrawl (via API call), Tavily extract (fallback), Python scripts for parsing and JSON I/O, and embedded datasets for Track A/B matching. All references appear in the Step sections with exact commands and file paths like "/tmp/vc-product-raw.md" and "/tmp/vc-product-analysis.json".
Caveats
Zero-hallucination policy applies: every fact about comparables, funds, and theses must come from Tavily search results or fetched product pages. If a detail is not found in the search data, it should be stated as not found in search data. No speculation or outside knowledge is used. The steps describe how data is gathered, analyzed, and presented, with explicit prompts to fetch content and cite sources in the final tracks.
# VC Finder Take a product URL or description. Detect industry and stage. Find 5 comparable funded companies. Run two research tracks: who invested in those comparables (Track A), and which VCs publish theses about this space (Track B). Return a sourced, ranked investor list with outreach hooks. --- **Zero-hallucination policy:** Every fact in the output must be traceable to a specific Tavily search result or the fetched product page. This applies to: - Comparable company names: must appear in Tavily search results, not AI training knowledge - VC fund names: must appear verbatim in Tavily search results - Check sizes, stage focus, portfolio companies: must come from search snippets, not AI knowledge - Fund overviews and thesis summaries: extracted from search snippets only. If a detail is not in the search data, write "not found in search data" -- do not fill from training knowledge. --- ## Common Mistakes | The agent will want to... | Why that's wrong | |---|---| | Add a16z or Sequoia because they are famous | A famous VC without evidence is noise. Only include VCs that appear in Tavily search results for this specific product. Name-dropping wastes the founder's time. | | Generate
- Common Mistakes
- Step 1: Setup Check
- Step 2: Gather Input
- Step 3: Fetch Product Page
- Step 4: Detect Stage Signals Locally (No API)
- Step 5: Product Analysis (Taxonomy, Stage, ICP)
- Step 5b: Curated Pre-Match Against Verified Fund Dataset
- Step 6: Discover Comparable Companies via Tavily
- Step 7: Track A -- Who Invested in Comparable Companies
- Step 8: Track B -- VCs With Investment Theses About This Space
- Step 9: Synthesize -- Rank and Score All VCs
- Step 10: Self-QA
- Step 11: Save and Present Output
echo "TAVILY_API_KEY: ${TAVILY_API_KEY:+set}"
echo "FIRECRAWL_API_KEY: ${FIRECRAWL_API_KEY:-not set, Tavily extract will be used as fallback}"
from urllib.parse import urlparse
url = 'URL_HERE'
host = urlparse(url).netloc.replace('www.', '')
curl -s -X POST https://api.firecrawl.dev/v1/scrape \
import sys, json
d = json.load(sys.stdin)
content = d.get('data', {}).get('markdown', '') or d.get('markdown', '')
curl -s -X POST https://api.tavily.com/extract \What does the vc-finder skill do?
Takes a startup product URL or description, detects the industry and funding stage, identifies 5 comparable funded companies, searches who invested in those companies (Track A), finds VCs who publish investment theses about this space (Track B), and returns a ranked sourced list of relevant investors with deep-dives and outreach hooks. Use when asked to find investors for a startup, identify which VCs fund products like mine, research who backs companies in my space, build a VC target list, or find investor-market fit.
How do I install it?
Run `npx skills add Varnan-Tech/opendirectory --skill vc-finder --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From Varnan-Tech/opendirectory, a repository with 571 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.