Skills

Earnings Team

AI Berkshire skill: 财报精读团队:四大师并行解读 + 公众号发布.

Install

npx skills add xbtlin/ai-berkshire --skill earnings-team -g -a claude-code -y
Repository
xbtlin/ai-berkshire17k
Category
Engineering
Updated
3d ago
License
MIT
Context cost
Mediumabout 2,287 tokens
Runs scripts
No, instructions only

What it does

AI Berkshire skill: 财报精读团队:四大师并行解读 + 公众号发布. Source: skills/earnings-team.md.

Codex adapter note

This skill is generated from skills/earnings-team.md so Claude Code and Codex users share one canonical workflow.

  • Treat $ARGUMENTS as the user's request in the current Codex thread.
  • When the source mentions Claude-only surfaces such as Task, Agent, WebSearch, Bash, Read, or Write, use the closest Codex capability available in this session: subagents when available, web search when needed, shell commands for local tools, and normal file edits for workspace files.
  • Use shared project tools from tools/ in this repository. Prefer running commands from the repository root with paths like python3 tools/financial_rigor.py ...; if the current thread starts outside the repo, locate the actual checkout path first instead of assuming a fixed home-directory path.
  • Before starting research, run the date command to confirm today's date; treat it as the baseline for "latest" data and state the data cutoff date in the report header. Never assume the current date from training data.
  • Preserve the research quality rules from AGENTS.md: cross-check financial data, use exact arithmetic tools for valuation/math, and clearly label uncertainty and source gaps.

财报精读团队:四大师并行解读 + 公众号发布

对 $ARGUMENTS 进行团队化财报精读分析。四位大师并行解读财报,编辑润色成文,读者评审把关质量,最终产出可直接发布的公众号文章。

支持输入格式:公司名 季度,例如:腾讯 2025Q4、PDD 2025年报、美团 最新

设计理念

一份好的财报分析要解决两个问题:

  1. 自己能看懂未来, , 需要四个不同视角的深度研究
  2. 读者能看懂价值, , 需要编辑润色和读者视角的质量把关

本 Skill 的流程分三阶段:

  • 阶段一·研究:四大师并行精读财报(段永平看生意本质、巴菲特审财务质量、芒格读竞争变化、李录猎风险信号)
  • 阶段二·合成:Team Lead 综合四个视角,产出研究报告初稿
  • 阶段三·发布:编辑 Agent 改写为公众号文章 + 读者评审 Agent 提出修改意见 → Team Lead 定稿

阶段一:四大师并行研究

第一步:获取一手资料

使用 Agent 工具启动后台 Agent 并行获取以下原始材料:

资料类型获取来源优先级
财报原文公司IR页面、SEC EDGAR(美股)、港交所披露易(港股)、巨潮资讯网(A股)最高
业绩电话会纪要Seeking Alpha、公司IR页面、雪球最高
管理层致股东信年报中提取高(仅年报时)
上一期财报/电话会同上高(用于承诺追踪)

资料可得性评级:

Read the whole SKILL.md on GitHub

More in Engineering