earnings-analysis

Generate equity research earnings reports with beat/miss analysis and updated estimates.

Updated May 9, 2026
One-click install
npx skills add https://github.com/mahyarmalekii/MarketIntel --skill earnings-analysis-mahyarmalekii
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: earnings-analysis
Source: https://github.com/mahyarmalekii/MarketIntel/tree/main/backend/financial-services/plugins/vertical-plugins/equity-research/skills/earnings-analysis
Command: npx skills add https://github.com/mahyarmalekii/MarketIntel --skill earnings-analysis-mahyarmalekii

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires matplotlib, pandas, seaborn, python-docx, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the creation of comprehensive equity research earnings update reports for companies under coverage, providing a fast-turnaround format with in-depth analysis and updated estimates.

Core Features & Use Cases

  • Earnings Report Generation: Automatically generate reports analyzing quarterly results with beat/miss analysis, key metrics, and revised thesis.
  • Quick Turnaround: Reports completed within 24-48 hours of earnings release.
  • Use Case: Use when a user requests an earnings update for a covered company, focusing on quarterly results analysis and estimate revisions.

Quick Start

Use the earnings-analysis skill to generate an earnings update report for [Company] covering Q3 2024 results.

Frequently Asked Questions about earnings-analysis

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

FAQPage Schema
How do I automate equity research earnings report generation for quarterly results?

Automating equity research earnings report generation involves processing quarterly results to perform beat/miss analysis, updating financial estimates, and exporting a comprehensive DOCX file detailing the revised investment thesis.

What is the best way to perform a beat/miss analysis for a recently released earnings report?

Performing a beat/miss analysis involves comparing actual quarterly results against previous financial estimates to identify variances, updating key metrics, and generating a detailed report reflecting the revised equity thesis.

Do I need Python data analysis libraries to generate financial analysis reports for quarterly results?

Yes, generating financial analysis reports requires Python data analysis libraries like pandas for data manipulation, matplotlib and seaborn for visualizations, and python-docx to create the final DOCX report.

Can I use this approach to quickly turnaround an equity research update within 48 hours of an earnings release?

Yes, you can use this automated approach to achieve a quick turnaround for an equity research update, generating comprehensive earnings reports analyzing quarterly results and revised estimates within 24 to 48 hours.

What are the limitations of using Python scripts for earnings report generation compared to other financial analysis tools?

Using Python scripts for earnings report generation requires manual dependency management and coding knowledge, whereas specialized financial analysis platforms offer built-in data feeds but lack the customizable automated DOCX reporting provided here.