TrueHOOHA/shanxi-securities-tushare-skill / sxsc-tushare-analysis
sxsc-tushare-analysis
Verified对用户提到的标的(沪深股票、指数、公募基金、期货)进行综合分析,输出带 ECharts 图表的 HTML 分析报告。 触发条件:用户说"分析""研究""评估""看看XX怎么样""XX基本面""XX技术面""XX估值""XX财务""深度研究""对比"等分析类请求,且标的属于 A 股/指数/公募基金/期货。 本 skill 自动调用 sxsc_tushare 取数并输出完整报告,接管数据获取与分析全流程。当本 skill 被触发时,数据获取类 skill 不应同时激活——分析已包含数据。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 43.8 KB |
| scripts/adjustment.py | script | 8.7 KB |
| scripts/analysis_runner.py | script | 120.8 KB |
| scripts/attribution.py | script | 10.1 KB |
| scripts/basic_metrics.py | script | 4.3 KB |
| scripts/check_env.py | script | 8.8 KB |
| scripts/data_api.py | script | 41.2 KB |
| scripts/factor_signals.py | script | 10.3 KB |
| scripts/fund_analysis_runner.py | script | 61.7 KB |
| scripts/fut_analysis_runner.py | script | 41.4 KB |
| scripts/index_analysis_runner.py | script | 54.6 KB |
| scripts/report_html.py | script | 38.0 KB |
| scripts/result_model.py | script | 4.4 KB |
| scripts/risk_modeling.py | script | 6.3 KB |
| scripts/stock_analyzer.py | script | 1.1 KB |
| scripts/technical_indicators.py | script | 5.9 KB |
| scripts/token_util.py | script | 4.0 KB |
scripts/token_util.py
View on GitHub#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""token 文件读取工具:data_api 与 check_env 的唯一实现,避免两份逻辑漂移。
token 文件即 `sxsc_tushare.set_token()` 写入的位置,文件名随包构建而变
(读 `upass.TOKEN_F_P`,例如 sxsc_tk.csv / jsdata_tk.csv),内容为
首行表头 `token`、次行 token 值的 csv。
"""
import os
from typing import Optional
def token_file_path() -> str:
"""返回 token 文件路径。
⚠️ 文件名**不固定**:随 sxsc_tushare 构建来源而变,同为 1.2.12 也可能不同:
- 新版构建(如 20261030):~/sxsc_tk.csv
- 旧版构建(如 20231213):~/jsdata_tk.csv
因此一律读 `upass.TOKEN_F_P`,不硬编码文件名。SDK 不可用时回退为 sxsc_tk.csv。
"""
name = None
try:
import sxsc_tushare.upass as up
name = getattr(up, "TOKEN_F_P", None)
except Exception:
name = None
return os.path.join(os.path.expanduser("~"), name or "sxsc_tk.csv")
def _read_token_text(path: str) -> Optional[str]:
"""按文本解析 token 文件(容忍表头/注释/UTF-16/GBK)。
只接受两种可明确判定的格式,避免把表头或注释当凭证:
- 表头 `token`(或单行 `token,值`)+ 下一行值
- 仅一行有效内容(无表头手写文件)
多行且无 token 表头(如误写成 `tk\\n值`)返回 None,由调用方报"未找到 token"。
"""
text = None
for enc in ("utf-8-sig", "utf-16", "gbk"):
try:
with open(path, "r", encoding=enc) as f:
text = f.read()
break
except (UnicodeDecodeError, UnicodeError):
continue
except OSError:
return None
if text is None:
return None
lines = [ln.strip() for ln in text.splitlines()]
lines = [ln for ln in lines if ln and not ln.lstrip().startswith("#")]
for i, ln in enumerate(lines):
_low = ln.lower()
if _low == "token":
if i + 1 < len(lines):
return lines[i + 1].split(",")[0].strip() or None
return None
if _low.startswith("token,"):
return ln.split(",", 1)[1].strip() or None
if len(lines) == 1:
return lines[0].split(",")[0].strip() or None
return None
def load_token() -> Optional[str]:
"""从 token 文件读取明文 token(不读环境变量)。
该文件即 `sxsc_tushare.set_token()` 写入的位置:65 字节左右的 csv,
首行表头 `token`,次行 token 值。手动创建即可,不需再经过环境变量。
不直接调 `sx.get_token()` 的原因:它在失败时会向 stdout 打 `get token error.`,
会把日志/报告输出弄脏;这里自己读并保持同上解析口径,另容忍“只有一行 token”的
手写文件(无表头)与 UTF-16/GBK 编码(Windows PowerShell 常见)。
Returns:
token 字符串;文件不存在 / 为空 / 解析失败或不可读时返回 None。
"""
path = token_file_path()
if not os.path.isfile(path):
return None
try:
import pandas as pd
# dtype=str:纯数字 token 不会因类型推断丢掉前导零
df = pd.read_csv(path, dtype=str)
if not df.empty and "token" in df.columns:
val = df.loc[0, "token"]
if not pd.isna(val) and str(val).strip():
return str(val).strip()
except Exception:
pass
return _read_token_text(path)
def token_help() -> str:
"""token 缺失时的可操作提示。"""
path = token_file_path()
return (
f"未找到可用 token。请把 token 写入:{path}\n"
f" 方式一(推荐,SDK 自带):python -c \"import sxsc_tushare as sx; sx.set_token('你的token')\"\n"
f" 方式二(手写文件):首行写 token,次行写 token 值,UTF-8 编码无 BOM\n"
f" 若文件已存在仍报错:请检查文件读取权限与编码(支持 UTF-8/UTF-16/GBK)"
)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |