Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A股大盘/指数分析。当用户说"大盘分析"、"大盘怎么看"、"指数分析"、"上证指数"、"沪深300"、"创业板指"、"中证500"、"中证1000"、"今天大盘"、"大盘走势"、"指数估值"时触发。基于 cn-stock-data 获取指数行情、成交额、资金流向，结合技术面和资金面进行大盘综合研判。支持策略报告风格（formal）和快速判断风格（brief）。与 a-share-technical 的区别：本 skill 聚焦指数层面综合分析，technical 聚焦个股技术形态。
.claude/skills/aifinlab-a-share-index-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -17% | 0% |
bashSCRIPTS="$SKILLS_ROOT/cn-stock-data/scripts" # 主要指数实时行情 python "$SCRIPTS/cn_stock_data.py" quote --code SH000001,SZ399001,SZ399006,SH000300,SH000905,SH000852 # 指数K线（近60个交易日） python "$SCRIPTS/cn_stock_data.py" kline --code SH000001 --freq daily --start [60日前日期] # 大盘资金流向 python "$SCRIPTS/cn_stock_data.py" fund_flow --code SH000001
web 搜索补充（数据源无法覆盖的关键信息）：
Step 1: 指数概览 获取 6 大指数实时行情，构建概览表： | 指数 | 最新点位 | 涨跌幅(%) | 成交额(亿) | 特征说明 | |------|---------|----------|-----------|---------| | 上证指数 | | | | 大盘蓝筹主导 | | 深证成指 | | | | 中小盘+成长 | | 创业板指 | | | | 成长/科技风向标 | | 沪深300 | | | | 核心资产代表 | | 中证500 | | | | 中盘股代表 | | 中证1000 | | | | 小盘股代表 |
Step 2: 趋势分析 获取上证指数日线 K 线，计算均线系统：
Step 3: 量能分析
Step 4: 资金分析
Step 5: 综合研判 & 输出 汇总四维分析，给出大盘状态判断：
| 维度 | formal（策略报告） | brief（快速判断） | |------|------------------|-----------------| | 指数覆盖 | 6 个主要指数全分析 | 仅上证+创业板 | | 技术分析 | 多周期（日/周线） | 仅日线关键位置 | | 量能 | 详细量价关系分析 | 放量/缩量一句话 | | 资金面 | 主力+北向+融资全覆盖 | 北向资金方向 | | 风格判断 | 大小盘+价值成长+行业轮动 | 无 | | 结论 | 客观多空分析+风险提示 | 可加方向判断 | | 免责声明 | 需要 | 不需要 |
python# 调用 skill result = run_skill({ "param1": "value1", "param2": "value2" })
bashpython scripts/run_skill.py --input data.json
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 30,294 | 12,455 | -59% | 1 | 1 | 0% | 4,031 | 1,962 | -51% | 0 | 0 | — |
case-02 | fail→fail | 32,685 | 11,339 | -65% | 1 | 1 | 0% | 4,125 | 1,942 | -53% | 0 | 0 | — |
case-03 | pass→fail | 13,287 | 9,925 | -25% | 1 | 1 | 0% | 1,638 | 1,691 | +3% | 0 | 0 | — |
case-04 | pass→fail | 12,763 | 13,198 | +3% | 1 | 1 | 0% | 1,940 | 1,867 | -4% | 0 | 0 | — |
case-05 | fail→pass | 15,571 | 7,329 | -53% | 1 | 1 | 0% | 2,371 | 2,375 | +0% | 0 | 0 | — |
case-06 | pass→pass | 12,317 | 6,021 | -51% | 1 | 1 | 0% | 1,996 | 2,182 | +9% | 0 | 0 | — |
case-07 | fail→pass | 13,647 | 4,958 | -64% | 1 | 1 | 0% | 1,840 | 1,919 | +4% | 0 | 0 | — |
case-08 | pass→pass | 19,822 | 16,362 | -17% | 1 | 1 | 0% | 2,391 | 3,656 | +53% | 0 | 0 | — |
case-09 | pass→pass | 17,994 | 25,815 | +43% | 1 | 1 | 0% | 2,396 | 3,553 | +48% | 0 | 0 | — |
case-10 | pass→pass | 17,857 | 13,301 | -26% | 1 | 1 | 0% | 2,027 | 3,062 | +51% | 0 | 0 | — |
case-11 | fail→pass | 16,478 | 3,148 | -81% | 1 | 1 | 0% | 2,282 | 1,840 | -19% | 0 | 0 | — |
case-12 | fail→pass | 15,105 | 3,896 | -74% | 1 | 1 | 0% | 1,986 | 1,927 | -3% | 0 | 0 | — |
case-13 | pass→fail | 15,191 | 12,389 | -18% | 1 | 1 | 0% | 2,209 | 1,773 | -20% | 0 | 0 | — |
case-14 | pass→pass | 8,524 | 8,449 | -1% | 1 | 1 | 0% | 1,444 | 2,639 | +83% | 0 | 0 | — |
case-15 | pass→pass | 26,514 | 34,636 | +31% | 1 | 1 | 0% | 3,955 | 5,890 | +49% | 0 | 0 | — |
case-16 | fail→pass | 23,488 | 3,772 | -84% | 1 | 1 | 0% | 2,093 | 1,745 | -17% | 0 | 0 | — |
case-17 | pass→pass | 13,588 | 2,886 | -79% | 1 | 1 | 0% | 1,929 | 1,730 | -10% | 0 | 0 | — |
case-18 | pass→pass | 19,515 | 18,964 | -3% | 1 | 1 | 0% | 2,468 | 3,851 | +56% | 0 | 0 | — |
case-19 | pass→pass | 15,643 | 25,657 | +64% | 1 | 1 | 0% | 2,996 | 3,699 | +23% | 0 | 0 | — |
case-20 | pass→fail | 29,270 | 46,090 | +57% | 1 | 1 | 0% | 4,059 | 6,451 | +59% | 0 | 0 | — |
case-21 | pass→fail | 25,277 | 9,040 | -64% | 1 | 1 | 0% | 3,914 | 1,753 | -55% | 0 | 0 | — |
case-22 | pass→fail | 24,052 | 8,826 | -63% | 1 | 1 | 0% | 3,347 | 1,844 | -45% | 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, and 14 counted toward the lift figure. The other 8 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 -5 percentage points is the difference between those two pass rates over the 14 comparable cases. 7 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.