Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →外汇数据Skill - 提供全球主要货币对汇率、中国银行牌价 via AkShare/中国银行
.claude/skills/aifinlab-akshare-forex/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 944% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 92% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 95% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 29% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-forex | | 版本 | 1.1.0 | | 分类 | 外汇数据 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
外汇数据Skill，提供全球主要货币对（美元兑人民币、欧元、日元等）的实时汇率、中国银行外汇牌价、美元指数等数据。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 美元兑人民币多少？ | forex_quote | forex_quote.py | | 今天汇率多少？ | forex_quote | forex_quote.py | | 中国银行外汇牌价 | forex_boc | forex_boc.py | | 美元指数走势 | forex_dxy | forex_quote.py --index |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | 汇率行情 | AkShare | - | 无需 | | 银行牌价 | 中国银行 | - | 无需 | | 美元指数 | AkShare | - | 无需 |
| 货币对 | 代码 | 说明 | |:---|:---|:---| | USD/CNY | USDCNY | 美元兑人民币（在岸） | | USD/CNH | USDCNH | 美元兑人民币（离岸） | | EUR/CNY | EURCNY | 欧元兑人民币 | | JPY/CNY | JPYCNY | 100日元兑人民币 | | GBP/CNY | GBPCNY | 英镑兑人民币 | | HKD/CNY | HKDCNY | 港币兑人民币 | | EUR/USD | EURUSD | 欧元兑美元 | | USD/JPY | USDJPY | 美元兑日元 | | GBP/USD | GBPUSD | 英镑兑美元 | | AUD/USD | AUDUSD | 澳元兑美元 |
| 货币 | 权重 | |:---|:---:| | 欧元 EUR | 57.6% | | 日元 JPY | 13.6% | | 英镑 GBP | 11.9% | | 加元 CAD | 9.1% | | 瑞典克朗 SEK | 4.2% | | 瑞士法郎 CHF | 3.6% |
bash python scripts/forex_quote.py python scripts/forex_quote.py --pair USDCNY python scripts/forex_quote.py --index # 美元指数
bash python scripts/forex_boc.py python scripts/forex_boc.py --currency USD
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | forex_quote.py | 汇率行情 | ✅ | | forex_boc.py | 中国银行牌价 | ✅ |
| 汇率水平 | 数值 | 影响 | |:---|:---:|:---| | 强美元 | >7.3 | 出口企业受益，进口成本上升 | | 正常区间 | 6.9-7.3 | 正常波动 | | 强人民币 | <6.9 | 进口成本下降，出口承压 |
| 变动 | 对出口 | 对进口 | 对A股 | |:---|:---:|:---:|:---:| | 人民币贬值 | 利好 | 利空 | 出口股涨，航空股跌 | | 人民币升值 | 利空 | 利好 | 航空股涨，出口股跌 |
本Skill所有输出数据将按以下格式标注来源：
markdown--- 📊 **数据来源**: AkShare / 中国银行 ⏱️ **数据时间**: 2026-03-19 10:30:15 📌 **基准货币**: 人民币(CNY) 🔗 **原始来源**: 中国银行外汇牌价 🔧 **分析工具**: FinClaw v1.0
akshare>=1.10.0
pandas>=1.3.0
pyyaml>=5.4.0| 版本 | 日期 | 变更内容 | |:---|:---:|:---| | 1.1.0 | 2026-03-19 | 符合FinClaw数据规范v1.0 | | 1.0.0 | 2026-03-13 | 初始版本 |
finclaw/config/data_source_config.yaml本Skill遵循 FinClaw 数据规范 v1.0 | 数据来源强制标注 | 禁止训练数据编造
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | pass→pass | 7,563 | 3,547 | -53% | 1 | 1 | 0% | 1,216 | 2,081 | +71% | 0 | 0 | — |
case-01 | fail→pass | 6,823 | 11,689 | +71% | 1 | 1 | 0% | 309 | 3,225 | +944% | 0 | 0 | — |
case-02 | fail→fail | 13,468 | 12,342 | -8% | 1 | 1 | 0% | 2,083 | 2,208 | +6% | 0 | 0 | — |
case-03 | fail→pass | 14,275 | 18,469 | +29% | 1 | 1 | 0% | 2,117 | 4,062 | +92% | 0 | 0 | — |
case-04 | fail→fail | 18,311 | 18,680 | +2% | 1 | 1 | 0% | 3,003 | 4,217 | +40% | 0 | 0 | — |
case-05 | fail→fail | 15,654 | 18,922 | +21% | 1 | 1 | 0% | 2,764 | 5,038 | +82% | 0 | 0 | — |
case-06 | fail→fail | 16,725 | 14,683 | -12% | 1 | 1 | 0% | 2,538 | 3,789 | +49% | 0 | 0 | — |
case-07 | pass→pass | 7,076 | 5,340 | -25% | 1 | 1 | 0% | 994 | 2,187 | +120% | 0 | 0 | — |
case-08 | fail→pass | 5,953 | 2,976 | -50% | 1 | 1 | 0% | 970 | 1,888 | +95% | 0 | 0 | — |
case-10 | pass→pass | 3,787 | 3,099 | -18% | 1 | 1 | 0% | 649 | 2,044 | +215% | 0 | 0 | — |
case-11 | pass→pass | 3,756 | 3,214 | -14% | 1 | 1 | 0% | 567 | 1,951 | +244% | 0 | 0 | — |
case-12 | pass→pass | 4,935 | 4,860 | -2% | 1 | 1 | 0% | 720 | 2,356 | +227% | 0 | 0 | — |
case-13 | fail→pass | 16,323 | 7,409 | -55% | 1 | 1 | 0% | 2,508 | 2,718 | +8% | 0 | 0 | — |
case-14 | fail→pass | 12,804 | 3,548 | -72% | 1 | 1 | 0% | 1,588 | 2,047 | +29% | 0 | 0 | — |
case-15 | fail→pass | 16,321 | 2,889 | -82% | 1 | 1 | 0% | 2,205 | 1,967 | -11% | 0 | 0 | — |
case-16 | pass→pass | 11,950 | 15,205 | +27% | 1 | 1 | 0% | 1,923 | 3,933 | +105% | 0 | 0 | — |
case-17 | pass→pass | 13,453 | 13,479 | +0% | 1 | 1 | 0% | 2,067 | 3,673 | +78% | 0 | 0 | — |
case-18 | pass→pass | 7,663 | 7,219 | -6% | 1 | 1 | 0% | 1,413 | 2,891 | +105% | 0 | 0 | — |
case-19 | pass→pass | 7,081 | 6,874 | -3% | 1 | 1 | 0% | 1,319 | 2,254 | +71% | 0 | 0 | — |
case-20 | fail→pass | 14,857 | 5,091 | -66% | 1 | 1 | 0% | 1,720 | 2,487 | +45% | 0 | 0 | — |
case-21 | fail→pass | 12,442 | 2,996 | -76% | 1 | 1 | 0% | 1,677 | 1,940 | +16% | 0 | 0 | — |
case-22 | fail→pass | 6,341 | 2,444 | -61% | 1 | 1 | 0% | 1,040 | 1,910 | +84% | 0 | 0 | — |
case-23 | pass→pass | 3,447 | 3,055 | -11% | 1 | 1 | 0% | 600 | 2,007 | +235% | 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 +39 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.