Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →指数数据Skill - 提供A股主要指数行情、成分股、估值分析 via AkShare/交易所
.claude/skills/aifinlab-akshare-index/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 37% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 61% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 57% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-index | | 版本 | 1.1.0 | | 分类 | 指数数据 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
指数数据Skill，提供A股主要指数（沪深300/中证500/上证50/创业板指等）的实时行情、成分股查询、估值分析（PE/PB/股息率）等功能。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 沪深300行情 | index_quote | index_quote.py 000300 | | 查询中证500成分股 | index_components | index_components.py 000905 | | 指数估值情况 | index_valuation | index_valuation.py | | 上证指数今天多少点？ | index_quote | index_quote.py 000001 |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | 指数行情 | AkShare-交易所 | 新浪财经 | 无需 | | 指数成分股 | AkShare-中证/交易所 | - | 无需 | | 指数估值 | AkShare-中证 | - | 无需 |
| 指数 | 代码 | 交易所 | 说明 | |:---|:---|:---|:---| | 上证指数 | 000001 | 上交所 | 上海证券交易所综合指数 | | 深证成指 | 399001 | 深交所 | 深圳证券交易所成份指数 | | 创业板指 | 399006 | 深交所 | 创业板指数（成长型企业） | | 科创50 | 000688 | 上交所 | 科创板50指数（科技创新） | | 沪深300 | 000300 | 中证 | 沪深两市市值最大300只 | | 中证500 | 000905 | 中证 | 沪深300之后500只中盘股 | | 上证50 | 000016 | 上交所 | 沪市市值最大50只 | | 中证1000 | 000852 | 中证 | 小盘股代表（1000只） |
| 指数 | 代码 | 行业 | |:---|:---|:---| | 全指医药 | 000991 | 医药生物 | | 全指消费 | 000990 | 主要消费 | | 全指金融 | 000992 | 金融地产 | | 全指信息 | 000993 | 信息技术 | | 证券公司 | 399975 | 券商行业 | | 中证银行 | 399986 | 银行业 |
bash python scripts/index_quote.py 000300 # 沪深300 python scripts/index_quote.py 000001 # 上证指数 python scripts/index_quote.py 399006 # 创业板指
bash python scripts/index_components.py 000300 # 沪深300成分股 python scripts/index_components.py 000905 # 中证500成分股
bash python scripts/index_valuation.py
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | index_quote.py | 指数行情 | ✅ | | index_components.py | 指数成分股 | ✅ | | index_valuation.py | 指数估值 | ✅ |
| 估值指标 | 低估 | 合理 | 高估 | 极度高估 | |:---|:---:|:---:|:---:|:---:| | 沪深300 PE | <10 | 10-15 | 15-20 | >20 | | 中证500 PE | <20 | 20-30 | 30-40 | >40 | | 创业板指 PE | <30 | 30-50 | 50-70 | >70 | | PB | <1.5 | 1.5-2.5 | 2.5-4.0 | >4.0 | | 股息率 | >3% | 2-3% | 1-2% | <1% |
| 指数 | 场内ETF | ETF代码 | |:---|:---|:---:| | 沪深300 | 华泰柏瑞沪深300ETF | 510300 | | 中证500 | 南方中证500ETF | 510500 | | 上证50 | 华夏上证50ETF | 510050 | | 创业板指 | 易方达创业板ETF | 159915 | | 科创50 | 华夏科创50ETF | 588000 | | 中证1000 | 华夏中证1000ETF | 159845 |
本Skill所有输出数据将按以下格式标注来源：
markdown--- 📊 **数据来源**: AkShare-中证指数/交易所 ⏱️ **数据时间**: 2026-03-19 10:30:15 📌 **指数代码**: 000300 📌 **指数名称**: 沪深300 🔗 **原始来源**: 中证指数有限公司 🔧 **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-01 | fail→fail | 12,967 | 15,975 | +23% | 1 | 1 | 0% | 1,272 | 2,621 | +106% | 0 | 0 | — |
case-02 | fail→fail | 15,711 | 9,477 | -40% | 1 | 1 | 0% | 2,149 | 2,616 | +22% | 0 | 0 | — |
case-03 | fail→fail | 21,881 | 14,800 | -32% | 1 | 1 | 0% | 3,188 | 4,595 | +44% | 0 | 0 | — |
case-04 | fail→pass | 13,956 | 6,663 | -52% | 1 | 1 | 0% | 1,997 | 3,138 | +57% | 0 | 0 | — |
case-05 | fail→fail | 13,153 | 18,243 | +39% | 1 | 1 | 0% | 2,234 | 5,274 | +136% | 0 | 0 | — |
case-06 | fail→fail | 7,641 | 14,047 | +84% | 1 | 1 | 0% | 1,270 | 3,635 | +186% | 0 | 0 | — |
case-07 | pass→pass | 12,558 | 9,382 | -25% | 1 | 1 | 0% | 2,089 | 3,838 | +84% | 0 | 0 | — |
case-08 | pass→pass | 10,759 | 7,635 | -29% | 1 | 1 | 0% | 1,809 | 3,074 | +70% | 0 | 0 | — |
case-09 | pass→pass | 14,525 | 5,326 | -63% | 1 | 1 | 0% | 2,424 | 2,855 | +18% | 0 | 0 | — |
case-10 | pass→pass | 14,302 | 4,403 | -69% | 1 | 1 | 0% | 2,568 | 2,848 | +11% | 0 | 0 | — |
case-11 | pass→pass | 15,483 | 3,400 | -78% | 1 | 1 | 0% | 2,092 | 2,607 | +25% | 0 | 0 | — |
case-12 | pass→pass | 15,575 | 3,209 | -79% | 1 | 1 | 0% | 2,041 | 2,548 | +25% | 0 | 0 | — |
case-13 | fail→pass | 19,689 | 7,960 | -60% | 1 | 1 | 0% | 2,884 | 3,453 | +20% | 0 | 0 | — |
case-14 | fail→pass | 13,117 | 7,356 | -44% | 1 | 1 | 0% | 2,261 | 3,088 | +37% | 0 | 0 | — |
case-15 | fail→pass | 11,278 | 5,958 | -47% | 1 | 1 | 0% | 1,889 | 3,038 | +61% | 0 | 0 | — |
case-16 | pass→pass | 6,912 | 4,249 | -39% | 1 | 1 | 0% | 1,075 | 2,575 | +140% | 0 | 0 | — |
case-17 | pass→pass | 3,053 | 2,283 | -25% | 1 | 1 | 0% | 411 | 2,319 | +464% | 0 | 0 | — |
case-18 | pass→pass | 9,395 | 3,610 | -62% | 1 | 1 | 0% | 1,273 | 2,425 | +90% | 0 | 0 | — |
case-19 | fail→pass | 10,698 | 6,198 | -42% | 1 | 1 | 0% | 1,878 | 2,953 | +57% | 0 | 0 | — |
case-20 | fail→pass | 15,699 | 6,364 | -59% | 1 | 1 | 0% | 2,911 | 3,174 | +9% | 0 | 0 | — |
case-21 | fail→pass | 27,176 | 23,599 | -13% | 1 | 1 | 0% | 2,386 | 6,016 | +152% | 0 | 0 | — |
case-22 | fail→fail | 19,508 | 15,301 | -22% | 1 | 1 | 0% | 1,925 | 4,185 | +117% | 0 | 0 | — |
case-23 | fail→fail | 23,986 | 21,583 | -10% | 1 | 1 | 0% | 3,039 | 5,224 | +72% | 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 20 counted toward the lift figure. The other 3 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 +30 percentage points is the difference between those two pass rates over the 20 comparable cases. 2 cases got worse with the skill loaded, and they are 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.