Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A股技术分析/K线分析。当用户说"技术分析"、"K线"、"均线"、"MACD"、"支撑位"、"压力位"、"技术面怎么看"、"走势分析"、"形态分析"、"量价分析"时触发。基于 cn-stock-data 获取K线和成交量数据，进行均线系统、量价关系、技术指标、形态识别、支撑压力位分析。支持专业技术分析报告风格（formal）和个人看盘笔记风格（brief）。不适用于基本面分析（用 a-share-earnings-analysis）或估值分析（用 a-share-dcf / a-share-comps）。
.claude/skills/aifinlab-a-share-technical/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-22 | ✗→✓ | ▲ Improved | 73% | 0% |
| case-06 | ✓→✗ | ▼ Worse | -52% | 0% |
| case-10 | ✓→✗ | ▼ Worse | 10% | 0% |
| case-12 | ✓→✗ | ▼ Worse | -11% | 0% |
| case-13 | ✓→✗ | ▼ Worse | -47% | 0% |
bashSCRIPTS="$SKILLS_ROOT/cn-stock-data/scripts" # 日线 K 线（近 1 年，用于中长期分析） python "$SCRIPTS/cn_stock_data.py" kline --code [CODE] --freq daily --start [1年前日期] # 周线 K 线（近 3 年，用于长期趋势判断） python "$SCRIPTS/cn_stock_data.py" kline --code [CODE] --freq weekly --start [3年前日期] # 分钟线（短线分析） python "$SCRIPTS/cn_stock_data.py" kline --code [CODE] --freq 60min --start [近期日期] # 实时行情 python "$SCRIPTS/cn_stock_data.py" quote --code [CODE] # 资金流向（验证量价信号） python "$SCRIPTS/cn_stock_data.py" fund_flow --code [CODE] --days 30
Step 1: 数据获取与预处理
Step 2: 趋势分析 基于日线和周线判断整体趋势：
均线系统（必算）：
趋势判断：
Step 3: 量价分析
关注换手率：
Step 4: 技术指标分析
MACD（必算）：
RSI（相对强弱指标）：
KDJ：
布林带（BOLL）：
Step 5: 支撑压力位与形态
支撑位识别：
压力位识别：
常见形态（如果数据中可识别）：
Step 6: 输出
| 维度 | formal（专业技术分析） | brief（个人看盘笔记） | |------|---------------------|---------------------| | 篇幅 | 2-4 页 | 半页 | | 均线分析 | 完整（6 条均线 + 排列 + 金叉死叉） | MA20/MA60 关键位置 | | 量价分析 | 详细（每日量价关系+资金流向验证） | 一句话量价判断 | | 技术指标 | MACD+RSI+KDJ+BOLL 全面分析 | MACD 方向 + RSI 区间 | | 支撑压力 | 多个层级 + 精确价位 | 最近的 1 个支撑 + 1 个压力 | | 形态分析 | 完整形态识别+量能确认 | 一句话形态判断 | | 结论 | 多空力量分析+关键价位 | 偏多/偏空 + 操作建议 | | 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 | 58,790 | 69,417 | +18% | 1 | 1 | 0% | 4,510 | 2,143 | -52% | 0 | 0 | — |
case-02 | fail→fail | 11,434 | 41,058 | +259% | 1 | 1 | 0% | 1,754 | 2,186 | +25% | 0 | 0 | — |
case-03 | fail→fail | 21,042 | 9,707 | -54% | 1 | 1 | 0% | 3,220 | 2,241 | -30% | 0 | 0 | — |
case-04 | pass→pass | 17,535 | 26,410 | +51% | 1 | 1 | 0% | 3,006 | 6,375 | +112% | 0 | 0 | — |
case-05 | pass→pass | 18,049 | 48,145 | +167% | 1 | 1 | 0% | 2,825 | 4,338 | +54% | 0 | 0 | — |
case-06 | pass→fail | 19,990 | 8,055 | -60% | 1 | 1 | 0% | 4,555 | 2,209 | -52% | 0 | 0 | — |
case-07 | fail→fail | 45,079 | 7,136 | -84% | 1 | 1 | 0% | 8,052 | 1,890 | -77% | 0 | 0 | — |
case-08 | fail→fail | 14,990 | 7,253 | -52% | 1 | 1 | 0% | 2,616 | 2,033 | -22% | 0 | 0 | — |
case-09 | fail→fail | 9,947 | 8,053 | -19% | 1 | 1 | 0% | 1,437 | 2,050 | +43% | 0 | 0 | — |
case-10 | pass→fail | 11,541 | 7,874 | -32% | 1 | 1 | 0% | 1,867 | 2,054 | +10% | 0 | 0 | — |
case-11 | pass→pass | 9,264 | 3,716 | -60% | 1 | 1 | 0% | 1,530 | 2,248 | +47% | 0 | 0 | — |
case-12 | pass→fail | 13,966 | 7,832 | -44% | 1 | 1 | 0% | 2,342 | 2,094 | -11% | 0 | 0 | — |
case-13 | pass→fail | 18,726 | 6,354 | -66% | 1 | 1 | 0% | 3,759 | 1,978 | -47% | 0 | 0 | — |
case-14 | pass→pass | 10,341 | 8,882 | -14% | 1 | 1 | 0% | 1,822 | 3,170 | +74% | 0 | 0 | — |
case-15 | pass→pass | 19,202 | 19,767 | +3% | 1 | 1 | 0% | 3,228 | 4,919 | +52% | 0 | 0 | — |
case-16 | pass→fail | 12,828 | 11,481 | -11% | 1 | 1 | 0% | 2,068 | 2,063 | -0% | 0 | 0 | — |
case-17 | fail→fail | 31,247 | 9,816 | -69% | 1 | 1 | 0% | 5,316 | 2,427 | -54% | 0 | 0 | — |
case-18 | pass→fail | 12,586 | 10,676 | -15% | 1 | 1 | 0% | 2,029 | 1,883 | -7% | 0 | 0 | — |
case-19 | pass→pass | 26,385 | 22,155 | -16% | 1 | 1 | 0% | 4,142 | 5,027 | +21% | 0 | 0 | — |
case-20 | pass→fail | 13,057 | 27,965 | +114% | 1 | 1 | 0% | 2,050 | 2,161 | +5% | 0 | 0 | — |
case-21 | pass→fail | 17,160 | 6,930 | -60% | 1 | 1 | 0% | 2,705 | 1,785 | -34% | 0 | 0 | — |
case-22 | fail→pass | 11,329 | 14,335 | +27% | 1 | 1 | 0% | 1,847 | 3,190 | +73% | 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 7 counted toward the lift figure. The other 15 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 -32 percentage points is the difference between those two pass rates over the 7 comparable cases. 12 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.