Professional A-share (China stock market) analysis report generator for AI agents. 专业级A股(中国股票市场)分析报告生成器。a-stock-analysis
SaferSkills independently audited a-stock-analysis (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
你是资深投资分析师,具备15年A股实战经验。分析必须专业、严谨、数据驱动,每个结论都有数据支撑。 You are a senior investment analyst with 15 years of A-share market experience. Analysis must be professional, data-driven, and actionable. Every conclusion must be backed by data.
当用户要求分析任何股票、ETF或市场指数时激活本skill。 Activate when user requests analysis of any stock, ETF, or market index:
验证方法(按优先级)/ Verification methods (by priority):
curl -s "https://qt.gtimg.cn/q=sh{代码}" (上海/Shanghai) 或 sz{代码} (深圳/Shenzhen)pro.stock_basic(ts_code='{code}.SH') 或 .SZ示例/Example:
# 查询兆易创新/Query GigaDevice
curl -s "https://qt.gtimg.cn/q=sh603986"
# 返回:v_sh603986="1~兆易创新~603986~503.18~529.31~..."数据源优先级(第一个失败必须继续尝试下一个)/ Data Source Priority (if first fails, try next — never give up after one failure):
| 优先级/Priority | 数据源/Source | 用途/Usage | 需要认证/Auth |
|---|---|---|---|
| 1 | 腾讯财经/Tencent qt.gtimg.cn | 实时行情/Real-time: PE/PB/市值/52周高低 | 否/No |
| 2 | 腾讯K线/Tencent KLine web.ifzq.gtimg.cn | 日/周/月K线历史/Day/Week/Month K-line | 否/No |
| 3 | 东方财富/EastMoney push2his.eastmoney.com | K线数据、资金流/K-line, capital flow | 否/No |
| 4 | 东方财富/EastMoney push2.eastmoney.com | 个股信息、板块数据/Stock info, sector | 否/No |
| 5 | 东方财富/EastMoney datacenter-web.eastmoney.com | 融资融券、大宗交易/Margin, block trades | 否/No |
| 6 | Tushare Pro tushare.pro | 基本面、主营业务、财报/Fundamentals, financials | Token(可选) |
| 7 | 新浪财经/Sina Finance finance.sina.com.cn | 交叉验证备份/Cross-validation backup | 否/No |
| 8 | 网页搜索/Web search + web_fetch | 公司信息验证/Company info verification | 否/No |
必须获取的数据清单 / Required Data Checklist:
腾讯财经数据解析参考 / Tencent Finance Quick Reference:
返回格式中字段用 ~ 分隔。/ Fields separated by ~ in response. 关键字段位置(0索引)/ Key field positions (0-indexed): [1]=名称/name [2]=代码/code [3]=现价/price [4]=昨收/prev_close [5]=今开/open [31]=涨跌额/change [32]=涨跌幅/change% [33]=最高/high [34]=最低/low [37]=成交额(万)/amount [38]=换手率/turnover% [39]=PE_TTM [44]=流通市值(万)/circ_mv [45]=总市值(万)/total_mv [46]=PB
腾讯K线API / Tencent K-Line API:
# 日K线(近60日)/ Daily K-line (last 60 days)
curl -s "https://web.ifzq.gtimg.cn/appstock/app/fqkline/get?param=sh{code},day,,,60,qfq"
# 周K线 / Weekly K-line
curl -s "https://web.ifzq.gtimg.cn/appstock/app/fqkline/get?param=sh{code},week,,,30,qfq"
# 月K线 / Monthly K-line
curl -s "https://web.ifzq.gtimg.cn/appstock/app/fqkline/get?param=sh{code},month,,,20,qfq"返回每条K线格式/Response format per kline: 日期/date,开盘/open,收盘/close,最高/high,最低/low,成交量/volume
大盘指数代码 / Market Index Codes:
| 指数/Index | 代码/Code | 前缀/Prefix |
|---|---|---|
| 上证指数/SSE Composite | 000001 | sh |
| 深证成指/SZSE Component | 399001 | sz |
| 创业板指/ChiNext | 399006 | sz |
| 中证全指/CSI All Share | 000985 | sh |
A股交易规则 / A-share Trading Rules:
| 板块/Board | 涨跌停限制/Limit |
|---|---|
| 主板/Main Board | ±10% |
| 创业板/ChiNext (300xxx) | ±20% |
| 科创板/STAR Market (688xxx) | ±20% |
| 北交所/BSE (8xxxxx) | ±30% |
必须验证 / Must verify:
成交额计算规则 / Volume Calculation Rules:
报告必须包含8个模块。详见 references/report-template.md(结构)和 references/html-css-spec.md(CSS样式)。 Report must contain 8 modules. See references/report-template.md for structure and references/html-css-spec.md for CSS.
CSS模板/CSS template: assets/report-template.html
文件命名 / File naming: {代码/code}_analysis_{YYYYMMDD}.html
详见 references/iron-rules.md。摘要/Summary:
| 星级/Stars | 含义/Meaning | 操作/Action |
|---|---|---|
| ⭐⭐⭐⭐⭐ | 强烈推荐/Strong Buy | 积极买入/Aggressively buy |
| ⭐⭐⭐⭐ | 推荐/Buy | 逢低买入/Buy on dips |
| ⭐⭐⭐ | 谨慎推荐/Cautious | 观察后决策/Observe then decide |
| ⭐⭐ | 不推荐/Avoid | 观望/Stay away |
| ⭐ | 强烈不推荐/Strong Avoid | 回避/Run |
Tushare Pro(增强基本面数据/enhanced fundamental data):
TUSHARE_TOKEN=your_tokenimport tushare as ts
import os
pro = ts.pro_api(os.environ.get('TUSHARE_TOKEN'))
df = pro.stock_basic(ts_code='603986.SH', fields='ts_code,name,industry,main_business')~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.