A股聪明钱/主力行为识别 (a-share-smart-money)

SkillDev tools

Once added, your AI can analyze Chinese A-share stocks for signs of 'smart money' — institutional or main-force capital — using capital flow and candlestick price data. Ask it whether big players are entering a stock, what they seem to be doing, or whether volume and price are moving apart, and it identifies these behavior patterns with numbers. You can get the answer as a formal research-style report or a short quick-read summary.

Available today. Use it from your connected AI after setup.

After adding it, ask your AI about an A-share stock in plain words — for example 'is there smart money in this stock' or 'what is the main force doing'. Tell it whether you want the formal report style or the brief quick version.

Then ask your AI: use the A股聪明钱/主力行为识别 (a-share-smart-money) skill

What your AI can do with it

  • Spot smart money and institutional activity in A-share stocks
  • Measure main-force behavior patterns from capital flow and candlestick data
  • Run large-order and volume-price divergence analysis
  • Answer plain questions like 'is the main force entering' or 'what are the big players doing'
  • Pull the underlying capital-flow and price data through cn-stock-data
  • Deliver findings as a formal research-style report or a brief quick summary

What this skill tells your AI

The instructions your AI receives, as published by aifinlab/finclaw in skills/a-share-smart-money/SKILL.md and read by ahel’s review.

数据源

通过 cn-stock-data 统一层获取:

  • fund_flow: 个股资金流向(大单/中单/小单净流入)
  • kline: 日K线(open/high/low/close/volume/amount)
  • quote: 实时行情(辅助判断当前状态)

核心指标体系

1. 大单净流入占比 (Large Order Flow Ratio)

  • 公式: 大单净流入 / 总成交额 × 100%
  • 阈值: >5% 强流入, 2%~5% 温和流入, -2%~2% 平衡, <-5% 强流出

2. OBV (On Balance Volume)

  • 收盘上涨: OBV += 当日成交量; 下跌: OBV -= 当日成交量
  • 关注 OBV 与价格的背离(价跌量增 = 吸筹信号)

3. A/D Line (Accumulation/Distribution)

  • 公式: CLV = ((close-low)-(high-close))/(high-low), AD += CLV × volume
  • AD 持续上升但价格横盘 → 主力吸筹

4. MFI (Money Flow Index)

  • 类似 RSI 但加入成交量权重,范围 0-100
  • MFI > 80 超买(可能出货),MFI < 20 超卖(可能吸筹)

主力行为模式识别

模式价格特征量能特征资金流特征
吸筹 accumulation低位横盘/缓跌缩量后间歇放量大单持续净流入
出货 distribution高位震荡/滞涨高位放量大单持续净流出
洗盘 washout急跌后快速收回下跌缩量反弹放量大单流出但占比小
拉升 markup连续上涨/突破持续放量大单强劲流入

工作流程

  1. 调用 cn-stock-data 获取目标股票近 N 日资金流向 + K线数据
  2. 保存为 JSON,调用 scripts/smart_money_detector.py 计算指标
  3. 解读脚本输出的模式分类与置信度
  4. 结合近期市场环境和个股基本面给出综合判断
  5. 按用户偏好输出(formal / brief)

脚本调用

# 准备数据后调用
python scripts/smart_money_detector.py --flow flow.json --kline kline.json
# 可选: --days 20 (分析窗口,默认20)

输出格式

formal(研报风格)

  • 标题 + 股票信息
  • 聪明钱指标总览表(大单占比/OBV趋势/AD方向/MFI值)
  • 主力行为模式判定(模式名 + 置信度 + 证据链)
  • 量价关系分析段落
  • 近期关键信号时间线
  • 风险提示与操作建议

brief(快速分析风格)

  • 一句话结论:主力在做什么(吸筹/出货/洗盘/拉升/无明显迹象)
  • 关键指标速览(3-4个数字)
  • 信号强度评级(强/中/弱)

注意事项

  • 资金流向数据存在滞后性,不可作为唯一决策依据
  • 大单定义因券商而异,跨数据源对比时需注意口径差异
  • 短期资金流向噪声大,建议至少看 5-10 个交易日趋势
  • 本分析为量化辅助工具,不构成投资建议

使用示例

示例 1: 基本使用

# 调用 skill
result = run_skill({
    "param1": "value1",
    "param2": "value2"
})

示例 2: 命令行使用

python scripts/run_skill.py --input data.json

Signals

GitHub stars
241
Forks
38
Last commit
May 2026
Advanced
Catalog kind
skill
Gateway key
a-share-smart-money
Source
github.com/aifinlab/finclaw