finance-earnings-team

Orchestrates six parallel agents to analyze earnings reports and produce publishable WeChat articles.

Updated Aug 10, 2026
One-click install
npx skills add https://github.com/Choi-Keith/skill-arsenal-ultra --skill finance-earnings-team-choi-keith
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: finance-earnings-team
Source: https://github.com/Choi-Keith/skill-arsenal-ultra/tree/main/plugins/finance-skills/finance-earnings/skills/finance-earnings-team
Command: npx skills add https://github.com/Choi-Keith/skill-arsenal-ultra --skill finance-earnings-team-choi-keith

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Deep earnings analysis requires multiple expert perspectives and rigorous data verification, but a single-pass review often misses contradictions, hidden risks, and produces reports too dense for public readers. This Skill coordinates a six-agent team to read earnings reports from four value-investing viewpoints, synthesize findings, and polish the result into a publishable WeChat article. ## Core Features & Use Cases - Four-Master Parallel Research: Launches four concurrent agents analyzing the report from Duan Yongping (business essence), Buffett (financial quality), Munger (competitive landscape), and Li Lu (risk signals) perspectives. - Editorial and Reader Review Pipeline: An editor agent rewrites the research draft into a WeChat-friendly article while a reader-reviewer agent scores readability, information value, credibility, and actionability before final sign-off. - Data Rigor Tooling: Uses financial_rigor.py for market cap, valuation, cross-source validation, and three-scenario valuation, plus report_audit.py to sample 15% of data points and issue pass/fail release verdicts. - Use Case: Run it on "Tencent 2025Q4" to receive a synthesized research draft, four individual analyst reports, a reader review, and a final audited WeChat article saved under reports/Tencent/. ## Quick Start Ask the agent to run the earnings team analysis on a company and quarter, for example: analyze Tencent 2025Q4 earnings with the four-master team and produce a publishable article.

Frequently Asked Questions about finance-earnings-team

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

FAQPage Schema
How do I analyze an earnings report from multiple investor perspectives?

Provide a company name and period such as Tencent 2025Q4. The skill launches four parallel agents covering business essence, financial quality, competitive landscape, and risk signals, then a team lead synthesizes their findings into one research report.

How to turn an earnings research report into a WeChat article?

After the research synthesis, an editor agent rewrites the report into a 1000-3000 word WeChat-friendly article with an inverted-pyramid structure, and a reader-reviewer agent scores readability, credibility, and actionability before final sign-off.

What data sources does earnings analysis support for US, HK, and A-share stocks?

It retrieves primary materials from company IR pages, SEC EDGAR for US stocks, HKEX disclosure for Hong Kong stocks, and cninfo for A-shares, plus earnings call transcripts from Seeking Alpha or Xueqiu. Source availability is graded A/B/C to adjust analysis depth.

How is financial data accuracy verified in the report?

The financial_rigor.py script verifies market cap, valuation ratios, and cross-source consistency using exact decimal arithmetic, while report_audit.py randomly samples 15% of data points and issues a pass or fail release verdict with a 1% tolerance.

When should I use the team analysis instead of a single-agent earnings review?

Use the team workflow for key earnings of important holdings where depth and publishable output matter. For a quick single-perspective read of a report, the lighter single-agent earnings review is the better fit.