Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →基金数据Skill - 提供ETF/LOF/开放式基金实时行情、净值查询、基金搜索 via 腾讯财经/AkShare
.claude/skills/aifinlab-akshare-fund/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 50% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 62% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 121% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 192% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-fund | | 版本 | 1.1.0 | | 分类 | 基金数据 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
基金数据Skill，提供ETF/LOF/开放式基金的实时行情、净值查询、基金搜索等服务。ETF/LOF支持实时行情，开放式基金提供每日净值。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 沪深300ETF多少钱？ | fund_realtime | fund_quote_tx.py 510300 | | 查询创业板ETF净值 | fund_realtime | fund_quote_tx.py 159915 | | 搜索白酒基金 | fund_search | fund_search_tx.py 白酒 | | 有哪些科技ETF | fund_search | fund_search_tx.py 科技ETF | | 华夏成长基金怎么样 | fund_realtime | fund_quote_tx.py 000001 |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | ETF/LOF实时行情 | 腾讯财经 | 新浪财经 | 无需 | | 基金净值 | AkShare-东方财富 | - | 无需 | | 基金搜索 | 腾讯财经 | - | 无需 | | 基金排行 | AkShare-东方财富 | - | 无需 |
bash python scripts/fund_quote_tx.py 510300 python scripts/fund_quote_tx.py 000001
bash python scripts/fund_search_tx.py 白酒 python scripts/fund_search_tx.py 科技ETF python scripts/fund_search_tx.py 沪深300
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | fund_quote_tx.py | 基金实时行情/净值（腾讯） | ✅ | | fund_search_tx.py | 基金搜索（腾讯） | ✅ |
bash# 查询ETF实时行情 python scripts/fund_quote_tx.py 510300 python scripts/fund_quote_tx.py 159915 # 查询开放式基金净值 python scripts/fund_quote_tx.py 000001 # 搜索基金 python scripts/fund_search_tx.py 白酒 python scripts/fund_search_tx.py 新能源
pythonfrom finclaw.core.data_annotator import annotate_data # 获取基金数据后标注来源 fund_data = { "基金名称": "华泰柏瑞沪深300ETF", "基金代码": "510300", "最新净值": "3.854", "日涨跌": "+0.52%" } output = annotate_data(fund_data, source="tencent_finance") print(output)
本Skill所有输出数据将按以下格式标注来源：
markdown--- 📊 **数据来源**: 腾讯财经 ⏱️ **数据时间**: 2026-03-19 10:30:15 ⚡ **获取延迟**: 180ms 🔗 **数据接口**: https://qt.gtimg.cn 🔧 **分析工具**: FinClaw v1.0
requests>=2.25.0
akshare>=1.10.0
pandas>=1.3.0
pyyaml>=5.4.0| 类型 | 代码格式 | 示例 | |:---|:---|:---| | ETF | 51xxxx/15xxxx/56xxxx | 510300 (沪深300ETF) | | LOF | 16xxxx | 160106 (南方高增) | | 开放式基金 | 000xxx/001xxx | 000001 (华夏成长) | | 货币基金 | 如余额宝等 | 000198 (天弘余额宝) |
| ETF名称 | 代码 | 跟踪指数 | |:---|:---|:---| | 沪深300ETF | 510300 | 沪深300指数 | | 创业板ETF | 159915 | 创业板指数 | | 科创50ETF | 588000 | 科创50指数 | | 中证500ETF | 510500 | 中证500指数 | | 芯片ETF | 512760 | 半导体指数 | | 新能源ETF | 516160 | 新能源指数 |
| 指标 | 目标值 | 当前值 | |:---|:---:|:---:| | ETF行情延迟 | < 500ms | ~200ms | | 可用性 | > 99% | 99.5% | | 数据准确率 | > 98% | 99% |
| 版本 | 日期 | 变更内容 | |:---|:---:|:---| | 1.1.0 | 2026-03-19 | 符合FinClaw数据规范v1.0，新增数据来源强制标注 | | 1.0.0 | 2026-03-12 | 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-01 | fail→pass | 13,317 | 9,042 | -32% | 1 | 1 | 0% | 2,200 | 3,305 | +50% | 0 | 0 | — |
case-02 | fail→pass | 16,187 | 13,814 | -15% | 1 | 1 | 0% | 2,721 | 3,828 | +41% | 0 | 0 | — |
case-03 | fail→pass | 13,185 | 8,688 | -34% | 1 | 1 | 0% | 2,092 | 3,384 | +62% | 0 | 0 | — |
case-04 | fail→fail | 10,939 | 7,973 | -27% | 1 | 1 | 0% | 1,778 | 3,114 | +75% | 0 | 0 | — |
case-05 | fail→fail | 9,643 | 8,935 | -7% | 1 | 1 | 0% | 1,448 | 3,165 | +119% | 0 | 0 | — |
case-06 | fail→pass | 14,207 | 12,951 | -9% | 1 | 1 | 0% | 1,945 | 4,291 | +121% | 0 | 0 | — |
case-07 | fail→fail | 23,057 | 17,665 | -23% | 1 | 1 | 0% | 3,842 | 4,930 | +28% | 0 | 0 | — |
case-08 | fail→fail | 16,403 | 10,900 | -34% | 1 | 1 | 0% | 2,775 | 3,505 | +26% | 0 | 0 | — |
case-09 | fail→fail | 13,445 | 15,094 | +12% | 1 | 1 | 0% | 1,853 | 3,110 | +68% | 0 | 0 | — |
case-10 | fail→pass | 6,598 | 7,711 | +17% | 1 | 1 | 0% | 1,012 | 2,953 | +192% | 0 | 0 | — |
case-11 | fail→fail | 7,206 | 14,864 | +106% | 1 | 1 | 0% | 1,111 | 2,777 | +150% | 0 | 0 | — |
case-12 | fail→fail | 20,509 | 14,207 | -31% | 1 | 1 | 0% | 3,198 | 4,009 | +25% | 0 | 0 | — |
case-13 | pass→pass | 11,752 | 4,953 | -58% | 1 | 1 | 0% | 1,800 | 2,790 | +55% | 0 | 0 | — |
case-14 | fail→fail | 9,284 | 3,696 | -60% | 1 | 1 | 0% | 1,131 | 2,333 | +106% | 0 | 0 | — |
case-15 | pass→pass | 13,657 | 8,228 | -40% | 1 | 1 | 0% | 2,137 | 3,452 | +62% | 0 | 0 | — |
case-20 | fail→fail | 16,437 | 21,189 | +29% | 1 | 1 | 0% | 2,512 | 4,950 | +97% | 0 | 0 | — |
case-16 | fail→fail | 14,852 | 3,784 | -75% | 1 | 1 | 0% | 2,530 | 2,434 | -4% | 0 | 0 | — |
case-17 | pass→pass | 20,388 | 12,123 | -41% | 1 | 1 | 0% | 2,751 | 3,903 | +42% | 0 | 0 | — |
case-18 | fail→pass | 19,478 | 5,961 | -69% | 1 | 1 | 0% | 2,190 | 3,133 | +43% | 0 | 0 | — |
case-19 | fail→fail | 9,290 | 14,700 | +58% | 1 | 1 | 0% | 1,288 | 4,369 | +239% | 0 | 0 | — |
case-21 | fail→fail | 14,041 | 14,698 | +5% | 1 | 1 | 0% | 2,390 | 4,563 | +91% | 0 | 0 | — |
case-22 | fail→fail | 20,931 | 20,304 | -3% | 1 | 1 | 0% | 3,598 | 6,145 | +71% | 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. 22 cases were attempted. The headline lift of +27 percentage points is the difference between those two pass rates over the 22 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.