mcpbeat

Vc Curated Match

varnan-tech/vc-curated-match

Accepts a product description and URL to algorithmically identify relevant Venture Capital investors targeting exactly that stage, industry, and niche based on a curated static dataset.

16k tokens
context cost
the whole folder, loaded on every use
12
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
569
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/Varnan-Tech/opendirectory --skill vc-curated-match

The instruction itself

6 sections, as written by the author

VC Curated Match Skill

Identify targeted VC funds based on a product's description and URL.

When to Trigger This Skill

Use this skill when the user asks to:

  • Find investors for their startup or open-source project.
  • Get a list of relevant VC funds by stage, industry, or space.
  • Match their product built with specific technologies to investor theses.

Step 1: Confirm Input

Ask the user for the product description and the URL.

Optional parameters:

  • Stage: Pre-Seed, Seed, Series A (--stage)
  • Output: e.g., vc-matches.md (--output)

Step 2: Fetch Matches & Generate Report

Run the orchestrator script to handle context fetching, VC matching, and Markdown generation in one command.

python scripts/run.py --description "A fast rust-based web framework" --url "https://example.com"

For custom requests, append overrides:

python scripts/run.py \
  --description "..." \
  --url "..." \
  [--stage Seed] \
  [--output matched-investors.md]

Step 3: Present Results

Summarize the closest matches returned. Mention high-confidence matches explicitly. Provide the output path.

Dependencies

Standard Python 3.10+ library (no external packages required).

How to use it

Copy the folder

Take varnan-tech/vc-curated-match from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.