score-vc-fit

Name: score-vc-fit
Availability: InStock
Author: Overdrive

Score VC funds against a fundraising brief using an 8-dimension rubric.

3|1|Updated Mar 15, 2026

Search Tags:#scoring #fundraising #outreach #ranking #venture-capital #diligence

Ready to run

npx skills add https://github.com/Overdrive-Consulting/vc-fundraising-skill --skill score-vc-fit

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: score-vc-fit
Source: https://github.com/Overdrive-Consulting/vc-fundraising-skill/tree/main/.claude/skills/score-vc-fit
Command: npx skills add https://github.com/Overdrive-Consulting/vc-fundraising-skill --skill score-vc-fit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Score and rank VC firms and target investors based on fit with the startup's fundraising brief. Uses a weighted 8-dimension rubric. Produces a prioritized outreach list with clear reasoning.

Core Features & Use Cases

8-dimension rubric scores each fund out of 100 for fit across sector, stage, geography, check size, lead behavior, portfolio adjacency, recency, and partner relevance. Generates a sorted ranked list and a data file data/normalized/scored_funds.json with investor_contacts merged.
Handles missing evidence by scoring nulls and flags low-confidence when too many nulls.
Use Case: Given candidate funds and a fundraising brief, compute optimized outreach order for warm introductions.

Quick Start

Input your startup fundraising data and candidate funds, then run step 5 to produce a ranked outreach list.

Frequently Asked Questions about score-vc-fit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I rank and prioritize venture capital funds for fundraising outreach?▼

Rank venture capital funds by scoring each candidate against your startup's fundraising brief using an 8-dimension rubric covering sector, stage, geography, check size, lead behavior, portfolio adjacency, recency, and partner relevance to produce a prioritized outreach list.

What is the best way to score VC fit when missing investor or fund data?▼

Scoring VC fit with missing evidence yields null scores for those dimensions and flags the result as low-confidence, allowing you to proceed with ranking while identifying gaps in your fund candidate data for further diligence.

How do I generate a prioritized outreach list from raw fund candidates and investor contacts?▼

Generate a prioritized outreach list by processing your company profile and fund candidates through an 8-dimension rubric, merging investor contacts, and sorting results by score_total descending into a structured scored_funds.json file.

Can I use my existing fundraising brief and fund candidates to compute an optimized warm introduction order?▼

You can compute an optimized warm introduction order by running your fundraising brief data and fund candidates through the scoring rubric, which merges investor contacts and outputs a ranked list sorted by total fit score.

What dimensions are used to evaluate VC fit and rank target investors?▼

VC fit is evaluated across eight dimensions: sector, stage, geography, check size, lead behavior, portfolio adjacency, recency, and partner relevance, with each fund scored out of 100 based on alignment with your fundraising brief.

Do I need normalized company profile data before scoring venture capital fit?▼

You need normalized company profile data, raw fund candidates, and normalized investor contacts as inputs, since the scoring rubric reads these files to evaluate fund fit and generate the ranked scored_funds output.