Tuige shortline trading
Skill shouldnotappearcalm/a-share-skill/tuige-shortline-trading
基于退哥短线交易规则的A股场景化决策技能。Use when 用户要按交易场景查看短线规则、做选股、判断趋势回踩、涨停回调、连板接力、洗盘结束、卖出失效或仓位纪律。From its SKILL.md
npx -y skills add shouldnotappearcalm/a-share-skill --skill tuige-shortline-tradingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- runs commandsInstructs the agent to run 1 command, including `python3 "$SKILL_DIR/scripts/daily_decisions.py" --json`.
SKILL.md
4.4 KB, ~1.6k tokens by cl100k_base, as published. Nobody here has run it
Tuige Shortline Trading
适用范围
这个 skill 用来把退哥体系中的短线规则整理成可复用的决策框架,重点回答 4 类问题:
- 当前市场环境适合做什么
- 哪些股票值得进入观察和候选池
- 不同交易场景下的触发条件与失效条件
- 仓位、纪律、退出规则如何统一约束
能力边界
- 输出的是决策参考,不是收益承诺
- 优先使用结构化规则,不直接复述口号
- 不自动下单,不替代回测,不代替投顾
- 遇到模糊概念时先回到
glossary.md
推荐使用顺序
- 先读 market-regime.md
- 再读 stock-selection.md
- 根据场景进入以下文档:
- 最后用 exit-failure-rules.md 和 position-discipline.md 复核
- 如需统一术语,查 glossary.md
场景地图
api-reference/market-regime.md- 先判断今天是否允许激进短线、仅允许回调确认,还是应该空仓
api-reference/stock-selection.md- 统一股票池构建、强势股筛选、回避规则
api-reference/trend-setups.md- 处理趋势延续、回踩均线、缩量整理后的再起
api-reference/limit-up-pullback-setups.md- 处理涨停后整理结构,例如三阴不破阳、揉搓线、缩倍量回调
api-reference/relay-setups.md- 处理一进二、二进三、2+2 这类高风险接力
api-reference/washout-breakout-setups.md- 处理黄金坑、假跌破、极度缩量后放量突破等洗盘末端确认
api-reference/exit-failure-rules.md- 统一止盈兑现、趋势失效、结构失败、风险离场
api-reference/position-discipline.md- 统一仓位等级、试错纪律、降频规则
标准输出模板
输出时统一包含以下结构:
- 当前市场环境
- 今日允许使用的场景模块
- 候选池分级
- 当前结构类型
- 触发条件
- 失效条件
- 卖出观察点
- 仓位建议
- 明确回避原因
单只标的建议使用以下字段组织:
- 标的
- 所属题材
- 当前结构
- 入场依据
- trigger
- invalidation
- 卖出参考
- risk
- position_grade
使用约束
- 所有结论尽量写成“条件 / 风险 / 失效”
- 没有触发,不算买点
- 市场环境是总开关,环境不支持时不强行升级结论
- 同一只标的若同时命中多个场景,优先保留风险更低、定义更清晰的场景解释
工程化转换
当前目录已提供可执行脚本,采用统一的 daily_decisions / realtime_quotes / strategy_lab 结构:
scripts/daily_decisions.py- 主板流动性池扫描 +
trend_pullback信号 - 输出两类买入参考:
from_previous_day_close与from_last_close - 支持持仓文件卖出信号检查
- 默认最大持仓上限
8(可通过--max-holdings下调)
- 主板流动性池扫描 +
scripts/realtime_quotes.py- 对指定代码批量拉取现价快照
scripts/strategy_lab/strategy_params.py- 参数与仓位上限配置
scripts/strategy_lab/strategies.py- 规则引擎核心(当前版本:趋势回踩 + RSI 区间 + 失效退出)
运行
SKILL_DIR="<本 skill 绝对路径>"
python3 "$SKILL_DIR/scripts/daily_decisions.py" --json
常用参数:
--top-n:股票池大小,默认 120--max-holdings:最大持仓上限,默认 8--max-buys:买入输出上限,默认 8(最终会再受max-holdings约束)--holdings:持仓文件路径,一行一个代码--roundtrip-cost-bps:成本过滤,默认 45--entry-consensus-min:鲁棒一致性阈值,默认 0.67--disable-robust-check:关闭鲁棒性检查(仅调试)
说明
- 当前工程化版本是
tuige_shortline_v1,优先落地“可量化且可复测”的部分。 - 题材语义、公告语义、盘口封单博弈等仍属于下一阶段增强项。
What ships with it: 9 files
21.1 KB alongside SKILL.md
api-reference/
- exit-failure-rules.md2.0 KB
- glossary.md3.1 KB
- limit-up-pullback-setups.md2.2 KB
- market-regime.md2.7 KB
- position-discipline.md2.2 KB
- relay-setups.md2.3 KB
- stock-selection.md2.0 KB
- trend-setups.md2.0 KB
- washout-breakout-setups.md2.5 KB
Gives 0 of the 12 instructions most finance skills give in ~1.6k tokens
Counted across 469 of the 469 authors here whose files we hold, read 2026-08-07
- Extract date vendor amount and descriptionin 15 of 469, across 3 files
- Scan folder for invoice filesin 14 of 469, across 2 files
- Rename files to standard formatin 14 of 469, across 2 files
- Show organization plan before movingin 14 of 469, across 2 files
- Generate summary CSVin 14 of 469, across 2 files
- Organize files by categoryin 13 of 469, across 1 file
- Preserve original filesin 13 of 469, across 1 file
- Flag files missing critical infoin 13 of 469, across 1 file
- Produce the requested output filein 9 of 469, across 4 files
- Build best, base, and worst case scenariosin 9 of 469, across 5 files
- Implement backoff if rate limit errors occurin 8 of 469, across 3 files
- Determine the weighted average cost of capitalin 8 of 469, across 4 files
Said here and by no other author read
- Determine market regime before allowing aggressive shortline trading
- Screen stocks and build candidate pools by selection rules
- Apply setup rules based on specific trading scenarios
- Verify exits, failure conditions, and position discipline
- Output market environment assessment
- Output candidate pool tiers
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.