vc-finder

Name: vc-finder
Author: Varnan-Tech

21installs59forks

How to install vc-finder?

varnan-tech/opendirectory/vc-finder

$npx -y skills add Varnan-Tech/opendirectory --skill vc-finder

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	# VC Finder
2
3	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.
4
5	---
6
7	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:
8	- Comparable company names: must appear in Tavily search results, not AI training knowledge
9	- VC fund names: must appear verbatim in Tavily search results
10	- Check sizes, stage focus, portfolio companies: must come from search snippets, not AI knowledge
11	- 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.
12
13	---
14
15	## Common Mistakes
16
17	\| The agent will want to... \| Why that's wrong \|
18	\|---\|---\|
19	\| 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. \|
20	\| Generate comparable companies from training knowledge \| Comparables must come from Tavily search results (Step 6). AI knowledge of companies is not evidence -- a company suggested from memory may have wrong funding status or may not be a true comparable. \|
21	\| Continue when all 5 Track A searches return 0 results \| Zero Track A results means the comparables were wrong or too obscure. Stop, re-run Step 6 with broader search queries, and retry. \|
22	\| Include a Track B VC without citing the article or post \| Thesis without a source is indistinguishable from hallucination. The founder cannot verify it and the list loses all credibility. \|
23	\| Fill in fund overview from training knowledge \| Fund overviews must come from Tavily snippet text only. If the snippets don't describe the fund, write "not found in search data". \|
24	\| Detect stage from website aesthetics \| Stage must come from the specific CTA signals detected in Step 4. \|
25	\| Write generic outreach hooks \| Every outreach hook must name this specific product's differentiator and a specific VC portfolio signal or thesis quote from the search data. \|
26	\| Skip the URL fetch when the user also provides a description \| Always fetch the URL. The live page often reveals stage signals that the user's description omits. \|
27
28	---
29
30	## Step 1: Setup Check
31
32	```bash
33	echo "TAVILY_API_KEY: ${TAVILY_API_KEY:+set}"
34	echo "FIRECRAWL_API_KEY: ${FIRECRAWL_API_KEY:-not set, Tavily extract will be used as fallback}"
35	```
36
37	If TAVILY_API_KEY is missing: Stop. Tell the user: "TAVILY_API_KEY is required to research VC investments and theses. There is no fallback for this. Get it at app.tavily.com -- free tier: 1000 credits/month (about 125 full runs). Add it to your .env file."
38
39	If only FIRECRAWL_API_KEY is missing: Continue silently. Tavily extract will be used for the URL fetch.
40
41	---
42
43	## Step 2: Gather Input
44
45	You need:
46	- Product URL (required, unless user pastes a product description directly)
47	- Optional: target stage hint (pre-seed, seed, series-a, series-b) -- if provided, use it and skip stage detection
48	- Optional: geography preference (US, Europe, global) -- defaults to US if not specified
49
50	If the user provides only a pasted description (no URL): Skip Steps 3-4. Go directly to Step 5 with the pasted text as `product_content`. Set `stage_source` to `user_description`.
51
52	If neither URL nor description is provided: Ask: "What is the URL of your product or startup? Or paste a short description: what it does, who it is for, and what stage you are at (pre-seed, seed, Series A)."
53
54	Derive product slug from URL for the output filename:
55
56	```bash
57	PRODUCT_SLUG=$(python3 -c "
58	from urllib.parse import urlparse
59	url = 'URL_HERE'
60	host = urlparse(url).netloc.replace('www.', '')
61	print(host.split('.')[0])
62	")
63	```
64
65	---
66
67	## Step 3: Fetch Product Page
68
69	Primary: Firecrawl (if FIRECRAWL_API_KEY is set)
70
71	```bash
72	curl -s -X POST https://api.firecrawl.dev/v1/scrape \
73	-H "Authorization: Bearer $FIRECRAWL_API_KEY" \
74	-H "Content-Type: application/json" \
75	-d '{"url": "URL_HERE", "formats": ["markdown"], "onlyMainContent": true}' \
76	\| python3 -c "
77	import sys, json
78	d = json.load(sys.stdin)
79	content = d.get('data',

People who liked this also viewed

6 picks

Type

vc-finder

21installs59forks

View on GitHub

How to install vc-finder?

varnan-tech/opendirectory/vc-finder

$npx -y skills add Varnan-Tech/opendirectory --skill vc-finder

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# VC Finder
2
3	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.
4
5	---
6
7	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:
8	- Comparable company names: must appear in Tavily search results, not AI training knowledge
9	- VC fund names: must appear verbatim in Tavily search results
10	- Check sizes, stage focus, portfolio companies: must come from search snippets, not AI knowledge
11	- 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.
12
13	---
14
15	## Common Mistakes
16
17	\| The agent will want to... \| Why that's wrong \|
18	\|---\|---\|
19	\| 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. \|
20	\| Generate comparable companies from training knowledge \| Comparables must come from Tavily search results (Step 6). AI knowledge of companies is not evidence -- a company suggested from memory may have wrong funding status or may not be a true comparable. \|
21	\| Continue when all 5 Track A searches return 0 results \| Zero Track A results means the comparables were wrong or too obscure. Stop, re-run Step 6 with broader search queries, and retry. \|
22	\| Include a Track B VC without citing the article or post \| Thesis without a source is indistinguishable from hallucination. The founder cannot verify it and the list loses all credibility. \|
23	\| Fill in fund overview from training knowledge \| Fund overviews must come from Tavily snippet text only. If the snippets don't describe the fund, write "not found in search data". \|
24	\| Detect stage from website aesthetics \| Stage must come from the specific CTA signals detected in Step 4. \|
25	\| Write generic outreach hooks \| Every outreach hook must name this specific product's differentiator and a specific VC portfolio signal or thesis quote from the search data. \|
26	\| Skip the URL fetch when the user also provides a description \| Always fetch the URL. The live page often reveals stage signals that the user's description omits. \|
27
28	---
29
30	## Step 1: Setup Check
31
32	```bash
33	echo "TAVILY_API_KEY: ${TAVILY_API_KEY:+set}"
34	echo "FIRECRAWL_API_KEY: ${FIRECRAWL_API_KEY:-not set, Tavily extract will be used as fallback}"
35	```
36
37	If TAVILY_API_KEY is missing: Stop. Tell the user: "TAVILY_API_KEY is required to research VC investments and theses. There is no fallback for this. Get it at app.tavily.com -- free tier: 1000 credits/month (about 125 full runs). Add it to your .env file."
38
39	If only FIRECRAWL_API_KEY is missing: Continue silently. Tavily extract will be used for the URL fetch.
40
41	---
42
43	## Step 2: Gather Input
44
45	You need:
46	- Product URL (required, unless user pastes a product description directly)
47	- Optional: target stage hint (pre-seed, seed, series-a, series-b) -- if provided, use it and skip stage detection
48	- Optional: geography preference (US, Europe, global) -- defaults to US if not specified
49
50	If the user provides only a pasted description (no URL): Skip Steps 3-4. Go directly to Step 5 with the pasted text as `product_content`. Set `stage_source` to `user_description`.
51
52	If neither URL nor description is provided: Ask: "What is the URL of your product or startup? Or paste a short description: what it does, who it is for, and what stage you are at (pre-seed, seed, Series A)."
53
54	Derive product slug from URL for the output filename:
55
56	```bash
57	PRODUCT_SLUG=$(python3 -c "
58	from urllib.parse import urlparse
59	url = 'URL_HERE'
60	host = urlparse(url).netloc.replace('www.', '')
61	print(host.split('.')[0])
62	")
63	```
64
65	---
66
67	## Step 3: Fetch Product Page
68
69	Primary: Firecrawl (if FIRECRAWL_API_KEY is set)
70
71	```bash
72	curl -s -X POST https://api.firecrawl.dev/v1/scrape \
73	-H "Authorization: Bearer $FIRECRAWL_API_KEY" \
74	-H "Content-Type: application/json" \
75	-d '{"url": "URL_HERE", "formats": ["markdown"], "onlyMainContent": true}' \
76	\| python3 -c "
77	import sys, json
78	d = json.load(sys.stdin)
79	content = d.get('data',

People who liked this also viewed

6 picks

Type