Skills
.Work. You
Rest

eval-pe-output

Community

Evaluate PE document AI outputs with precision and consistency.

Finance & Accounting#consistency check#PE analysis#PE document evaluation#AI output grading#source-of-truth validation
Authorbolnet
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a deterministic and reproducible evaluation of AI-generated PE documents, ensuring accuracy and consistency without relying on LLMs.

Core Features & Use Cases

  • Citation Accuracy: Ensures every financial figure in the document traces back to a source field.
  • Hallucination Rate: Checks for the presence of named entities in the source.
  • Coverage: Measures the fraction of source opportunities addressed in the memo.
  • Consistency: Verifies that memos derived from the same source agree on the headline number.
  • Use Case: Use this Skill to grade a PE document AI output against its structured source-of-truth, closing the trust gap for PE shops.

Quick Start

Run the eval_pe_output skill with the memo JSON path and source JSON path.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: eval-pe-output
Download link: https://github.com/bolnet/private-equity/archive/main.zip#eval-pe-output

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.