Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Ashare 最轻量 A 股行情获取工具(3.2k Stars),基于新浪+腾讯双核心数据源,零依赖(仅需 requests+pandas),无需注册,支持日/周/月线及 1m/5m/15m/30m/60m 分钟级K线。当用户需要快速获取 A 股/指数行情而其他数据源不可用时,Ashare 是最可靠的回退方案——它使用新浪为主、腾讯为备的双核心架构,自动切换,极少出错。
.claude/skills/aifinlab-ashare-data/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -36% | 0% |
Ashare 是 GitHub 上 3.2k Stars 的极简 A 股行情库,单文件、零配置、零注册。核心只有一个函数 get_price(),用新浪+腾讯双数据源自动切换,稳定性极高。
它的价值不在于数据丰富度(只有行情K线),而在于可靠性——当 akshare、efinance、adata 因为上游网站改版或反爬而暂时不可用时,Ashare 几乎总是能正常工作。
bashpip install requests pandas
无需安装额外包,requests 和 pandas 通常已存在于 Python 环境中。
唯一脚本:scripts/quote_data.py
bash# 日线(最近30天) python quote_data.py quote --code sh000001 --count 30 # 周线 python quote_data.py quote --code sh600519 --freq 1w --count 20 # 月线 python quote_data.py quote --code sz000001 --freq 1M --count 12 # 5分钟线 python quote_data.py quote --code sh600519 --freq 5m --count 48 # 指定结束日期 python quote_data.py quote --code sh600519 --freq 1d --count 60 --end 2026-01-31
bashpython quote_data.py multi --code sh600519,sz000001,sh000300 --count 10
| 格式 | 说明 | 示例 | |------|------|------| | sh + 代码 | 上海证券交易所 | sh600519(茅台)、sh000001(上证指数) | | sz + 代码 | 深圳证券交易所 | sz000001(平安银行) | | 代码.XSHG | JoinQuant 格式(沪) | 000001.XSHG | | 代码.XSHE | JoinQuant 格式(深) | 000001.XSHE |
| 周期 | 参数 | 数据源 | |------|------|--------| | 日线 | 1d | 新浪(主)→ 腾讯(备) | | 周线 | 1w | 新浪(主)→ 腾讯(备) | | 月线 | 1M | 新浪(主)→ 腾讯(备) | | 1分钟 | 1m | 腾讯(独占) | | 5分钟 | 5m | 新浪(主)→ 腾讯(备) | | 15分钟 | 15m | 新浪(主)→ 腾讯(备) | | 30分钟 | 30m | 新浪(主)→ 腾讯(备) | | 60分钟 | 60m | 新浪(主)→ 腾讯(备) |
time, open, close, high, low, volume(前复权)
Ashare 只做行情K线,没有财务、资金流、北向资金等数据。它的定位是:
使用优先级建议:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→fail | 12,149 | 3,572 | -71% | 1 | 1 | 0% | 2,443 | 1,460 | -40% | 0 | 0 | — |
case-01 | fail→fail | 17,217 | 8,617 | -50% | 1 | 1 | 0% | 2,643 | 1,389 | -47% | 0 | 0 | — |
case-03 | fail→fail | 21,053 | 7,271 | -65% | 1 | 1 | 0% | 3,624 | 1,343 | -63% | 0 | 0 | — |
case-04 | fail→fail | 8,737 | 4,342 | -50% | 1 | 1 | 0% | 1,488 | 1,734 | +17% | 0 | 0 | — |
case-05 | fail→pass | 13,724 | 5,015 | -63% | 1 | 1 | 0% | 2,420 | 1,628 | -33% | 0 | 0 | — |
case-06 | fail→pass | 12,080 | 3,532 | -71% | 1 | 1 | 0% | 1,680 | 1,443 | -14% | 0 | 0 | — |
case-07 | fail→pass | 16,071 | 3,564 | -78% | 1 | 1 | 0% | 3,058 | 1,486 | -51% | 0 | 0 | — |
case-08 | fail→pass | 8,244 | 3,742 | -55% | 1 | 1 | 0% | 1,479 | 1,462 | -1% | 0 | 0 | — |
case-09 | fail→pass | 15,222 | 3,470 | -77% | 1 | 1 | 0% | 2,262 | 1,437 | -36% | 0 | 0 | — |
case-10 | fail→pass | 10,243 | 3,763 | -63% | 1 | 1 | 0% | 1,922 | 1,674 | -13% | 0 | 0 | — |
case-11 | fail→pass | 10,019 | 4,502 | -55% | 1 | 1 | 0% | 1,673 | 1,810 | +8% | 0 | 0 | — |
case-12 | pass→pass | 21,521 | 2,635 | -88% | 1 | 1 | 0% | 2,707 | 1,392 | -49% | 0 | 0 | — |
case-13 | fail→pass | 13,762 | 1,875 | -86% | 1 | 1 | 0% | 1,999 | 1,281 | -36% | 0 | 0 | — |
case-14 | pass→pass | 7,652 | 3,433 | -55% | 1 | 1 | 0% | 1,250 | 1,551 | +24% | 0 | 0 | — |
case-15 | fail→pass | 26,112 | 14,624 | -44% | 1 | 1 | 0% | 3,531 | 3,531 | 0% | 0 | 0 | — |
case-16 | pass→pass | 16,823 | 5,094 | -70% | 1 | 1 | 0% | 2,863 | 1,567 | -45% | 0 | 0 | — |
case-17 | pass→pass | 8,693 | 5,820 | -33% | 1 | 1 | 0% | 1,397 | 2,045 | +46% | 0 | 0 | — |
case-18 | fail→pass | 9,383 | 3,937 | -58% | 1 | 1 | 0% | 1,724 | 1,765 | +2% | 0 | 0 | — |
case-19 | fail→pass | 12,455 | 4,069 | -67% | 1 | 1 | 0% | 2,091 | 1,615 | -23% | 0 | 0 | — |
case-20 | pass→pass | 16,529 | 5,914 | -64% | 1 | 1 | 0% | 2,228 | 2,051 | -8% | 0 | 0 | — |
case-21 | pass→pass | 15,508 | 5,688 | -63% | 1 | 1 | 0% | 2,443 | 1,819 | -26% | 0 | 0 | — |
case-22 | fail→pass | 11,601 | 4,686 | -60% | 1 | 1 | 0% | 1,959 | 1,684 | -14% | 0 | 0 | — |
case-23 | fail→pass | 14,636 | 8,337 | -43% | 1 | 1 | 0% | 2,632 | 2,176 | -17% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 21 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +57 percentage points is the difference between those two pass rates over the 21 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.