Can I integrate this with my CRM?

While it provides the framework and schema, it is designed to be used by Claude to process CRM exports or interview notes into a standardized format like CSV or BI-ready data.

Is user privacy maintained?

Yes, the skill includes best practices for publishing sanitized and anonymized snippets to ensure sensitive customer or internal data is protected during broader sharing.

What is the Win-Loss Dataset skill?

It is a specialized Claude Code skill designed to help Go-To-Market teams capture and analyze the reasons behind won or lost deals using a structured data framework.

Why use this over a standard spreadsheet?

This skill provides a consistent taxonomy and automated analysis capabilities, ensuring that every deal is evaluated against the same criteria without manual drift over time.

How does it handle qualitative data?

It uses a qualitative tagging system to categorize feedback into buckets like pricing, product gaps, or implementation issues, allowing Claude to synthesize raw notes into actionable trends.

Win-Loss Analysis Dataset

Name: Win-Loss Analysis Dataset
Author: gtmagents

bygtmagents

•

分析と監視

Standardizes the capture and categorization of qualitative and quantitative sales deal insights to improve win rates.

The Win-Loss Dataset skill provides a structured framework for Claude to manage competitive intelligence by aligning qualitative interview data with quantitative CRM metrics. It enables teams to categorize product gaps, pricing feedback, and competitor movements using a consistent taxonomy, making it easier to identify revenue-impacting trends and translate customer feedback into actionable product backlogs or sales strategies.

主な機能

01Centralized repository for anonymized customer quotes and evidence

02Action tracking to link deal insights directly to product backlogs

03Qualitative tagging system for pricing, product gaps, and brand sentiment

04Analytics layer for tracking driver frequency and revenue impact

0529 GitHub stars

06Structured data model for deal metadata, outcomes, and competitors

ユースケース

01Analyzing churn and loss drivers to inform pricing or feature prioritization

02Synthesizing call transcripts and notes into structured, searchable data

03Establishing a repeatable win/loss program across sales and product teams

主な機能

01Centralized repository for anonymized customer quotes and evidence

02Action tracking to link deal insights directly to product backlogs

03Qualitative tagging system for pricing, product gaps, and brand sentiment

04Analytics layer for tracking driver frequency and revenue impact

0529 GitHub stars

06Structured data model for deal metadata, outcomes, and competitors

ユースケース

01Analyzing churn and loss drivers to inform pricing or feature prioritization

02Synthesizing call transcripts and notes into structured, searchable data

03Establishing a repeatable win/loss program across sales and product teams