财报分析代理
earnings-financials-agent
by assix
An autonomous agent for monitoring corporate earnings and analyzing financial statements using yfinance.
安装
claude skill add --url github.com/openclaw/skills/tree/main/skills/assix/earnings-financials-agent必需命令行工具
python3pip文档
EarningsFinancialsAgent
This agent provides deep-dive analysis into quarterly earnings and corporate financial health. It is designed to run locally and uses the yfinance library for reliable, real-time data retrieval.
Setup
Before using this skill, ensure the dependencies are installed in your environment:
pip install yfinance
User Instructions
The agent can handle a variety of financial inquiries. Use these as templates for your requests:
- Earnings Performance: "Summarize the latest earnings for NVDA and check if they beat revenue estimates."
- Direct Comparison: "Compare the net income of Google vs Meta for the last 4 quarters."
- Financial Ratios: "What is the debt-to-equity ratio and quick ratio for TSLA?"
- Cash Flow Analysis: "Give me a summary of Amazon's cash flow from the most recent report."
- Growth Trends: "Show me the revenue growth trend for Netflix over the last year."
- Calendar Checks: "Is Broadcom reporting earnings this week? If so, when?"
- Profitability: "Analyze the profit margins for AMD based on their latest financials."
- Dividend Health: "Check the dividend payout ratio for Coca-Cola to see if it's sustainable."
Tools
get_earnings
Fetches the most recent earnings results and compares them to analyst estimates.
- Inputs:
ticker(string) - Call:
python3 logic.py --tool get_earnings --ticker {{ticker}}
get_financials
Retrieves key balance sheet, income statement, and cash flow metrics.
- Inputs:
ticker(string) - Call:
python3 logic.py --tool get_financials --ticker {{ticker}}
相关 Skills
Claude接口
by anthropics
面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景,自动识别项目语言并给出对应示例与默认配置,快速搭建 LLM 应用。
✎ 想把Claude能力接进应用或智能体,用claude-api上手快、兼容Anthropic与Agent SDK,集成路径清晰又省心
提示工程专家
by alirezarezvani
覆盖Prompt优化、Few-shot设计、结构化输出、RAG评测与Agent工作流编排,适合分析token成本、评估LLM输出质量,并搭建可落地的AI智能体系统。
✎ 把提示优化、LLM评测到RAG与智能体设计串成一套方法,适合想系统提升AI开发效率的人。
智能体流程设计
by alirezarezvani
面向生产级多 Agent 编排,梳理顺序、并行、分层、事件驱动、共识五种工作流设计,覆盖 handoff、状态管理、容错重试、上下文预算与成本优化,适合搭建复杂 AI 协作系统。
✎ 帮你把多智能体流程设计、编排和自动化统一起来,复杂工作流也能更稳地落地,适合追求强控制力的团队。
相关 MCP 服务
顺序思维
编辑精选by Anthropic
Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。
✎ 这个服务器展示了如何让 Claude 像人类一样逐步推理,适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例,别指望直接用在生产环境里。
知识图谱记忆
编辑精选by Anthropic
Memory 是一个基于本地知识图谱的持久化记忆系统,让 AI 记住长期上下文。
✎ 帮 AI 和智能体补上“记不住”的短板,用本地知识图谱沉淀长期上下文,连续对话更聪明,数据也更可控。
PraisonAI
编辑精选by mervinpraison
PraisonAI 是一个支持自反思和多 LLM 的低代码 AI 智能体框架。
✎ 如果你需要快速搭建一个能 24/7 运行的 AI 智能体团队来处理复杂任务(比如自动研究或代码生成),PraisonAI 的低代码设计和多平台集成(如 Telegram)让它上手极快。但作为非官方项目,它的生态成熟度可能不如 LangChain 等主流框架,适合愿意尝鲜的开发者。