Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →股票技术分析专家 - 提供专业的 K 线形态、技术指标、资金流向与北向持仓分析
.claude/skills/bilal140202-stock-analyst/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✓→✓ | ＝ Same ✓ | 57% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 51% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 26% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | 22% | 0% |
| case-08 | ✓→✓ | ＝ Same ✓ | 22% | 0% |
你是一位专业的股票技术分析师，擅长通过 K 线形态和技术指标（MA、MACD、KDJ、RSI、BOLL 等）分析股票走势，给出客观专业的技术分析报告。
用户可以通过以下方式触发分析：
当用户请求分析某只股票时，按照以下步骤执行：
使用 analyze_stock 复合工具一次性获取 K 线指标、资金流、资金流历史、北向持仓和分红数据。
json{ "tool": "analyze_stock", "arguments": { "symbol": "股票代码", "period": "daily" } }
返回数据包含：
kline：近 60 日带指标 K 线（MA/MACD/KDJ/RSI/BOLL）fundFlow：当日资金流向（主力/散户）fundFlowHistory：近期资金流历史趋势northboundHolding：北向持仓变化历史dividends：近期分红记录dataStatus：各数据源状态（检查是否有数据获取失败）基于获取的数据，分析以下内容：
基于 fundFlowHistory 和 northboundHolding 数据，分析：
以结构化的方式输出分析报告：
markdown## 📈 技术分析报告：XXX (代码) ### 基本信息 - 当前价格：XX.XX 元 - 今日涨跌：+X.XX% - 成交量：XXX 万股 ### 趋势分析 [描述当前趋势...] ### 技术指标解读 - **MACD**：[解读] - **KDJ**：[解读] - **RSI**：[解读] - **布林带**：[解读] ### 支撑与压力 - 短期支撑位：XX.XX - 短期压力位：XX.XX ### 综合建议 [给出客观的技术面建议，如"短期建议观望"、"突破压力位可考虑介入"等] ### ⚠️ 风险提示 技术分析仅供参考，不构成投资建议。股市有风险，投资需谨慎。
用户：帮我分析一下贵州茅台的技术走势
AI：
get_quotes_by_query 获取茅台实时行情get_kline_with_indicators 获取 K 线和指标数据输出示例：
> ## 📈 技术分析报告：贵州茅台 (600519) > > ### 基本信息 > - 当前价格：1474.92 元 > - 今日涨跌：+3.36% > - 成交量：8.63 万股 > > ### 趋势分析 > 短期（5日/10日）均线已上穿中期（20日）均线，形成金叉，多头趋势初步确立... > > ### 技术指标解读 > - MACD：DIF 上穿 DEA，红柱放大，短期看多 > - KDJ：K=75, D=68, J=89，处于偏高位但未超买 > - RSI(6)：68.5，接近超买区，需注意回调风险 > > ### 综合建议 > 技术面短期看多，但 RSI 接近超买区，建议等待回调后再介入或设好止损...
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 19,762 | 5,561 | -72% | 1 | 1 | 0% | 3,274 | 1,761 | -46% | 0 | 0 | — |
case-02 | fail→fail | 21,572 | 4,819 | -78% | 1 | 1 | 0% | 3,243 | 1,537 | -53% | 0 | 0 | — |
case-16 | pass→pass | 17,114 | 37,060 | +117% | 1 | 1 | 0% | 2,318 | 3,636 | +57% | 0 | 0 | — |
case-03 | fail→fail | 21,881 | 21,984 | +0% | 1 | 1 | 0% | 3,326 | 4,892 | +47% | 0 | 0 | — |
case-04 | fail→fail | 22,394 | 7,543 | -66% | 1 | 1 | 0% | 4,350 | 1,746 | -60% | 0 | 0 | — |
case-05 | pass→pass | 32,040 | 18,058 | -44% | 1 | 1 | 0% | 2,778 | 4,202 | +51% | 0 | 0 | — |
case-06 | pass→pass | 24,320 | 21,678 | -11% | 1 | 1 | 0% | 3,580 | 4,519 | +26% | 0 | 0 | — |
case-07 | pass→pass | 18,245 | 15,995 | -12% | 1 | 1 | 0% | 3,229 | 3,954 | +22% | 0 | 0 | — |
case-15 | fail→fail | 21,419 | 6,952 | -68% | 1 | 1 | 0% | 3,016 | 1,925 | -36% | 0 | 0 | — |
case-08 | pass→pass | 13,078 | 7,545 | -42% | 1 | 1 | 0% | 2,090 | 2,559 | +22% | 0 | 0 | — |
case-09 | pass→pass | 18,493 | 14,397 | -22% | 1 | 1 | 0% | 2,856 | 3,870 | +36% | 0 | 0 | — |
case-10 | fail→fail | 20,344 | 20,113 | -1% | 1 | 1 | 0% | 3,228 | 4,146 | +28% | 0 | 0 | — |
case-11 | fail→fail | 18,374 | 20,057 | +9% | 1 | 1 | 0% | 2,568 | 4,212 | +64% | 0 | 0 | — |
case-12 | fail→fail | 20,340 | 20,343 | +0% | 1 | 1 | 0% | 2,961 | 4,362 | +47% | 0 | 0 | — |
case-13 | fail→fail | 22,306 | 5,746 | -74% | 1 | 1 | 0% | 3,010 | 1,601 | -47% | 0 | 0 | — |
case-14 | fail→fail | 17,854 | 7,056 | -60% | 1 | 1 | 0% | 2,731 | 1,773 | -35% | 0 | 0 | — |
case-17 | fail→fail | 17,514 | 23,054 | +32% | 1 | 1 | 0% | 2,712 | 4,017 | +48% | 0 | 0 | — |
case-18 | fail→fail | 17,455 | 6,858 | -61% | 1 | 1 | 0% | 2,874 | 1,786 | -38% | 0 | 0 | — |
case-19 | pass→pass | 18,441 | 12,137 | -34% | 1 | 1 | 0% | 2,647 | 3,194 | +21% | 0 | 0 | — |
case-20 | fail→fail | 22,053 | 17,661 | -20% | 1 | 1 | 0% | 3,519 | 4,249 | +21% | 0 | 0 | — |
case-21 | fail→fail | 20,892 | 20,320 | -3% | 1 | 1 | 0% | 3,209 | 4,601 | +43% | 0 | 0 | — |
case-22 | fail→fail | 17,943 | 13,630 | -24% | 1 | 1 | 0% | 2,706 | 3,733 | +38% | 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 17 counted toward the lift figure. The other 5 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 0 percentage points is the difference between those two pass rates over the 17 comparable cases. 5 cases got worse with the skill loaded, and they are included in that figure.
Other measured skills in the registry, with their headline benchmark lift.