数据规划
- 作者仓库星标 6,018
- 作者更新于 实时读取
- 作者仓库 OctoBot
- 领域
- AI 智能
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @Drakkar-Software · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: trading-strategy
description: Use this skill for developing and evaluating trading strategies by synthesizing technical analys…
category: AI 智能
runtime: 无特殊运行时
---
# trading-strategy 输出预览
## PART A: 任务判断
- 适用问题:提示词、Agent 工作流、模型评估或自动化推理。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Overview / Instructions / 1. Synthesize Multiple Signals”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于提示词、Agent 工作流、模型评估或自动化推理,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Overview / Instructions / 1. Synthesize Multiple Signals”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件;主要在本地完成;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文没有稳定的斜杠命令要求。安装验证后通常全局生效,直接在对话里点名这个 Skill 并描述任务即可。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件。
先用一个小任务确认它会围绕“Overview / Instructions / 1. Synthesize Multiple Signals”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: trading-strategy
description: Use this skill for developing and evaluating trading strategies by synthesizing technical analys…
category: AI 智能
source: Drakkar-Software/OctoBot
---
# trading-strategy
## 什么时候使用
- 把AI / Agent方向的常用动作沉淀成 Agent 可调用的技能 适合处理AI Agent、提示词、模型评估与自动化推理,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查…
- 面向提示词、Agent 工作流、模型评估或自动化推理,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Overview / Instructions / 1. Synthesize Multiple Signals」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件;主要在本地完成;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "trading-strategy" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Overview / Instructions / 1. Synthesize Multiple Signals
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} trading-strategy
Overview
This skill provides comprehensive guidance on synthesizing multiple analyses into coherent trading strategies and actionable recommendations. Use this for final decision-making and trade structuring.
Instructions
1. Synthesize Multiple Signals
Integrate analysis from different sources:
- Technical Analysis: Trend, momentum, support/resistance
- Sentiment Analysis: Market mood, fear/greed levels
- Real-Time Data: Order flow, liquidity, recent price action
Weight each component by:
- Confidence level (higher confidence = higher weight)
- Timeframe alignment (multiple timeframes agreeing)
- Signal strength (strong vs weak signals)
2. Resolve Conflicting Signals
When analyses disagree:
- Technical bullish, Sentiment bearish: Often means "buy the dip" if technical is strong
- Technical bearish, Sentiment bullish: Often means "sell the rally" if technical is strong
- Mixed timeframes: Defer to higher timeframe for trend direction
- Low confidence all around: Recommend staying out or reducing position size
3. Generate eval_note (-1 to 1 scale)
Strong Buy Signals (0.6 to 1.0)
- Multiple timeframes aligned bullish
- Technical indicators show strong uptrend
- Sentiment at extreme fear (contrarian buy)
- High confidence from all analyses
Moderate Buy (0.3 to 0.6)
- Majority of signals bullish
- Some conflicting indicators
- Medium confidence
- Trend supports upside
Neutral (−0.3 to 0.3)
- Mixed signals across analyses
- Ranging market conditions
- Low confidence or uncertainty
- Wait for clearer setup
Moderate Sell (−0.6 to −0.3)
- Majority of signals bearish
- Some conflicting indicators
- Medium confidence
- Trend supports downside
Strong Sell (−1.0 to −0.6)
- Multiple timeframes aligned bearish
- Technical indicators show strong downtrend
- Sentiment at extreme greed (contrarian sell)
- High confidence from all analyses
4. Risk Assessment
Consider before making recommendations:
- Volatility: High volatility = reduce position size
- Liquidity: Low liquidity = widen stops, smaller size
- Time in market: Newer trends are riskier
- Correlation: Diversification reduces risk
- Black swan risk: Extreme events possible
5. Position Sizing Guidelines
Based on confidence and volatility:
- High confidence, Low volatility: Larger positions (up to max allowed)
- High confidence, High volatility: Medium positions
- Medium confidence, Any volatility: Smaller positions
- Low confidence: Minimal or no position
6. Entry and Exit Strategy
Entry Points
- Strong signals: Enter on market orders or limit near current price
- Medium signals: Enter on pullbacks to support
- Weak signals: Scale in gradually
Stop Loss Placement
- Below recent swing low (for longs)
- Above recent swing high (for shorts)
- Below key moving averages
- Account for volatility (wider stops in volatile markets)
Take Profit Targets
- First target: 1-2 risk/reward ratio
- Second target: Major resistance/support level
- Final target: Trailing stop to ride trend
7. Timeframe Considerations
Short-term trading (minutes to hours)
- Focus on 1H and below timeframes
- More sensitive to real-time data and sentiment shifts
- Tighter stops and quicker exits
Medium-term trading (days to weeks)
- Focus on 4H and daily timeframes
- Align with daily trend direction
- Wider stops, let positions breathe
Long-term trading (weeks to months)
- Focus on daily and weekly timeframes
- Strong fundamental and macro support needed
- Very wide stops, focus on major trend
8. Market Regime Adaptation
Trending Markets
- Follow the trend direction
- Use pullbacks for entries
- Trail stops to ride trends
- Ignore minor counter-trend signals
Ranging Markets
- Fade extremes (sell highs, buy lows)
- Tighter profit targets
- Avoid trend-following strategies
- Reduce position sizes
Volatile Markets
- Wider stops to avoid whipsaws
- Smaller positions
- Quick profit taking
- Consider staying out if too chaotic
Output Format
When synthesizing into a trading recommendation, provide:
{
"eval_note": <float -1 to 1>,
"confidence": <float 0-1>,
"eval_note_description": "Comprehensive synthesis of all analyses with clear reasoning",
"key_factors": [
"Technical: Strong uptrend confirmed",
"Sentiment: Extreme fear (contrarian buy)",
"Real-time: Strong buying pressure"
],
"recommended_action": "BUY" | "SELL" | "HOLD",
"position_size": "FULL" | "MEDIUM" | "SMALL" | "NONE",
"entry_strategy": "Market order | Limit at X | Scale in on pullback",
"stop_loss": "Below X at Y",
"take_profit": ["First: X at R:R 1.5", "Second: Y at resistance", "Final: Trailing stop"]
}
Decision Framework
Strong Conviction Trade Checklist
- Multiple timeframes aligned
- 2+ independent confirmations
- Clear support/resistance levels identified
- Sentiment supports the move (or contrarian extreme)
- Risk/reward ratio > 2:1
- Market structure supportive
- Liquidity adequate
Trade Rejection Criteria
- Mixed signals with no clear edge
- Low confidence across analyses
- Highly uncertain market conditions
- Risk/reward ratio < 1.5:1
- Counter to strong higher timeframe trend
- Illiquid or highly manipulated market
Best Practices
- Never force trades: Wait for high-probability setups
- Quality over quantity: Fewer high-quality trades beat many mediocre trades
- Always know your exit: Plan stop loss and take profit before entry
- Manage risk first: Protect capital over maximizing gains
- Adapt to changing conditions: What works in trending markets fails in ranging markets
- Keep it simple: Complex strategies with many rules often underperform
- Document reasoning: Track what works and what doesn't
- Stay disciplined: Stick to your strategy and don't chase
- Cut losses quickly: Don't hope losing trades will reverse
- Let winners run: Trail stops on profitable positions
Common Mistakes to Avoid
- Over-trading in low-conviction setups
- Revenge trading after losses
- Moving stops further away (hoping for reversal)
- Adding to losing positions
- Taking profits too early on winning trades
- Ignoring risk management rules
- Trading against the higher timeframe trend
- Fighting the tape (market momentum)
- Letting emotions override analysis
- Failing to adapt strategy to market regime
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核