closed-lost-winback

Name: closed-lost-winback
Availability: InStock
Author: Utkarsh

Cross-reference CRM closed-lost exports with Format MCP conversation data to identify win-back opportunities.

Updated Apr 10, 2026

Search Tags:#analysis #sales #crm #revenue #objection #win-back

Ready to run

npx skills add https://github.com/utkarshformat/skills --skill closed-lost-winback

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: closed-lost-winback
Source: https://github.com/utkarshformat/skills/tree/main/closed-lost-winback
Command: npx skills add https://github.com/utkarshformat/skills --skill closed-lost-winback

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openpyxl, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This skill solves the problem of sales leaders receiving CRM reports of lost deals without understanding the true, underlying reasons, often relying on potentially inaccurate or incomplete rep notes.

Core Features & Use Cases

Evidence-Based Analysis: Cross-references CRM closed-lost data with actual customer conversation transcripts to identify discrepancies between rep notes and reality.
Win-Back Prioritization: RAG-rates accounts based on winnability, providing concrete, data-backed next steps for re-engagement.
Objection Theming: Clusters buying objections across all deals to identify systemic loss drivers like budget, authority, or product fit.

Quick Start

Run the closed-lost-winback skill by providing your CRM export file and specifying the customer organization to analyze their lost opportunities.

Frequently Asked Questions about closed-lost-winback

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

FAQPage Schema

How do I analyze closed-lost CRM opportunities to find real loss reasons?▼

Closed-lost win-back analysis cross-references CRM opportunity exports with customer conversation data to validate loss reasons and identify actionable turnaround plays. It applies RAG-rating to prioritize accounts based on winnability for re-engagement campaigns.

What is the best way to prioritize lost deals for a win-back campaign?▼

Prioritizing lost deals for a win-back campaign is best achieved by RAG-rating accounts based on winnability using evidence from customer conversations. This method provides concrete, data-backed next steps for re-engaging stalled or lost accounts effectively.

How do I cluster buying objections across lost sales opportunities?▼

Clustering buying objections across lost sales opportunities requires analyzing CRM exports alongside conversation insights to theme systemic loss drivers like budget, authority, or product fit. This process highlights recurring patterns in lost deals for targeted re-engagement.

Can I use CRM exports with openpyxl to validate inaccurate sales rep notes?▼

You can use CRM exports processed with openpyxl to validate inaccurate sales rep notes by cross-referencing them with customer conversation data. This identifies discrepancies between rep-reported loss reasons and the actual evidence found in transcripts.

How do I run a loss post-mortem on stalled or lost accounts?▼

Running a loss post-mortem on stalled or lost accounts requires parsing CRM closed-lost opportunity exports and querying conversation insights to validate loss reasons. This generates data-backed next steps for re-engagement campaigns and sales performance reviews.

Does closed-lost win-back analysis work for sales performance reviews?▼

Closed-lost win-back analysis works for sales performance reviews by parsing CRM exports and querying conversation insights to validate loss reasons. It identifies systemic loss drivers and generates actionable turnaround plays for stalled or lost accounts.