hard-screening-startup

Scores startups across eight weighted dimensions with Python to produce an auditable investment verdict.

3.4k|487|Updated Jul 25, 2025
One-click install
npx skills add https://github.com/davepoon/buildwithclaude --skill hard-screening-startup
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hard-screening-startup
Source: https://github.com/davepoon/buildwithclaude/tree/main/plugins/venture-capital-intelligence/skills/hard-screening-startup
Command: npx skills add https://github.com/davepoon/buildwithclaude --skill hard-screening-startup

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Qualitative startup evaluations are inconsistent and hard to audit. This Skill replaces gut-feel screening with a deterministic, weighted-score pipeline where every dimension score, rationale, and verdict is logged to JSON for full traceability.

Core Features & Use Cases

  • Weighted 8-Dimension Scoring: Scores team, market, product, traction, business model, competition, financials, and risk profile on a 1-10 scale with fixed weights.
  • Deterministic Verdict Engine: Python scripts compute the weighted score and emit a PASS, CONDITIONAL PASS, or DECLINE verdict with explicit reasons and weak dimensions.
  • Investor Lens Simulation: Evaluates the startup through Sequoia, YC, Tiger Global, and risk-management lenses for multi-perspective screening.
  • Use Case: A VC analyst receives a Seed-stage B2B SaaS pitch, runs a hard screen, and gets a reproducible scorecard with thesis, key risks, DD priorities, and comparables formatted as a terminal report.

Quick Start

Ask Claude to run a hard screen on a startup by providing its name, stage, team, product, market, traction, and fundraise details.

Frequently Asked Questions about hard-screening-startup

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

FAQPage Schema
How do I run a scored startup screening with Python?

Provide the company details (team, market, product, traction, business model, fundraise) and ask for a hard screen. Claude scores eight dimensions, then Python scripts compute the weighted score and verdict, writing results to JSON audit files.

What dimensions does a startup screening scorecard evaluate?

The scorecard evaluates team (0.25 weight), market (0.20), product (0.15), traction (0.15), business model (0.10), competition (0.08), financials (0.05), and risk profile (0.02), each scored 1-10 with a written rationale.

How is the PASS or DECLINE verdict determined?

A weighted score of 7.5 or higher with no dimension below 4 yields PASS; 6.0 or higher with no dimension below 3 yields CONDITIONAL PASS. Any dimension scored 2 or below triggers an automatic DECLINE regardless of the total.

Does this startup screening work without Python installed?

No, the deterministic scoring pipeline requires Python 3 to run verdict_calc.py and report_formatter.py. If Python is unavailable, the Skill falls back to the conversational soft-screening-startup skill instead.

What happens if company information is incomplete?

The screening proceeds with available data, and missing items are flagged as 0-scored gaps in the company profile. This lowers the weighted score and is visible in the audit trail rather than being silently ignored.