← Back to Skills Marketplace
Earnings Reader
by
_silhouette
· GitHub ↗
· v1.0.0
746
Downloads
1
Stars
5
Active Installs
1
Versions
Install in OpenClaw
/install earnings-reader
Description
A股财报研读助手 - 解读利润表/资产负债表/现金流量表
README (SKILL.md)
Earnings Reader — 财报研读
数据获取
PYTHON=python3.12
EARNINGS=skills/akshare-finance/scripts/earnings.py
# 获取财报摘要
$PYTHON $EARNINGS report \x3C股票代码>
# 例: $PYTHON $EARNINGS report 600519
# 查看业绩预告
$PYTHON $EARNINGS earnings
# 行业概览
$PYTHON $EARNINGS industry
财报分析框架
三表分析
- 利润表: 营收增速、毛利率、净利率趋势
- 资产负债表: 资产负债率、流动比率、商誉占比
- 现金流量表: 经营现金流/净利润比、自由现金流
关键指标
| 指标 | 健康范围 | 红灯 |
|---|---|---|
| ROE | >15% | \x3C8% |
| 净利率 | >10% | \x3C3% |
| 资产负债率 | \x3C60% | >80% |
| 营收增速 | >10% | \x3C0% |
| 经营现金流/净利润 | >0.8 | \x3C0.5 |
估值对比
- PE/PB 历史分位
- 同行业对比
- PEG 合理性
输出格式
个股财报速读
## {公司名} 财报速读
### 核心数据 (最近4个季度)
| 指标 | Q3 | Q2 | Q1 | 全年 |
|------|----|----|----|----|
| 营收 | xx亿 | xx亿 | xx亿 | xx亿 |
| 净利 | xx亿 | xx亿 | xx亿 | xx亿 |
| ROE | xx% | xx% | xx% | xx% |
### 趋势判断
- 增长性: [加速/稳定/减速]
- 盈利质量: [优/良/中/差]
- 风险点: [具体描述]
### 投资观点 (仅供参考)
注意
- 财报数据来源: AKShare (东方财富)
- 仅用于研究分析，不构成投资建议
- Macro agent 关注行业趋势，个股交易建议由 trading agent 负责
Usage Guidance
This skill's documentation expects you to run a local Python script (skills/akshare-finance/scripts/earnings.py) with python3.12 and to use AKShare/东方财富 data, but the skill package contains no code or install instructions. Do not run unknown scripts. Before installing or enabling this skill, ask the publisher for: (1) the missing earnings.py (or include it in the skill), (2) a clear dependency list and installation steps (Python version, AKShare), and (3) confirmation that no credentials or sensitive files are needed. If you must run the provided commands, inspect the earnings.py source yourself to ensure it only fetches financial data and does not access or exfiltrate unrelated files or secrets.
Capability Analysis
Type: OpenClaw Skill
Name: earnings-reader
Version: 1.0.0
The skill bundle contains metadata and a `SKILL.md` file. The `SKILL.md` describes the skill's purpose, how to invoke a local Python script (`earnings.py`) for data retrieval, and provides analysis frameworks and output formats. There are no instructions for data exfiltration, malicious execution, persistence, or prompt injection with harmful intent. The commands shown are standard local script executions, aligning with the stated purpose of an 'earnings-reader' skill.
Capability Assessment
Purpose & Capability
The skill name/description (A股财报研读) matches the instructions' intent (financial-statement analysis). However the SKILL.md expects a local script at skills/akshare-finance/scripts/earnings.py and a specific Python binary (python3.12), but the skill package contains no code files and declares no required binaries or dependencies (e.g., AKShare). That mismatch means required capabilities are not provided or declared.
Instruction Scope
Runtime instructions are limited to running a local Python script and formatting analysis output; they do not request unrelated system files or secrets. The main issue is that the instructions require executing an external script path that is not included with the skill. Executing an out-of-band/unseen script is a risk because its behavior is unknown.
Install Mechanism
There is no install spec (instruction-only skill), so nothing is downloaded or written by an installer. This lowers installation risk but amplifies the problem that required code/dependencies are missing.
Credentials
The skill declares no environment variables or credentials, which is consistent with a read-only data-analysis utility. However SKILL.md assumes a specific Python executable (python3.12) and use of AKShare/东方财富 as the data source — these dependencies are not declared. The lack of declared dependencies or instructions for installing AKShare/Python is an incoherence.
Persistence & Privilege
The skill does not request always: true and has no install behavior that modifies agent-wide settings. Model invocation is allowed (default), which is normal for skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install earnings-reader - After installation, invoke the skill by name or use
/earnings-reader - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
初始发布: 财报数据解读Skill
Metadata
Frequently Asked Questions
What is Earnings Reader?
A股财报研读助手 - 解读利润表/资产负债表/现金流量表. It is an AI Agent Skill for Claude Code / OpenClaw, with 746 downloads so far.
How do I install Earnings Reader?
Run "/install earnings-reader" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Earnings Reader free?
Yes, Earnings Reader is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Earnings Reader support?
Earnings Reader is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Earnings Reader?
It is built and maintained by _silhouette (@lanyasheng); the current version is v1.0.0.
More Skills