{
  "ocm": "1",
  "id": "leong-creator-price-action-trader-strategy",
  "kind": "skill",
  "name": "strategy",
  "description": "本目录负责 PA 策略、setup 识别、bar-by-bar 分析和信号生成。",
  "publisher": "Leong-creator",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "github-agents"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "本目录负责 PA 策略、setup 识别、bar-by-bar 分析和信号生成。"
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github-agents",
      "repository": "https://github.com/Leong-creator/Price-Action-Trader",
      "path": "src/strategy/AGENTS.md",
      "ref": "18a0b4409965c94386adb44c0527fd8ee59a97bc",
      "url": "https://github.com/Leong-creator/Price-Action-Trader/blob/18a0b4409965c94386adb44c0527fd8ee59a97bc/src/strategy/AGENTS.md",
      "key": "Leong-creator/Price-Action-Trader/src/strategy/AGENTS.md"
    }
  },
  "instructions": "# AGENTS.md\n\n本目录负责 PA 策略、setup 识别、bar-by-bar 分析和信号生成。\n\n## 策略原则\n- PA context 优先，技术指标只能辅助。\n- 所有信号必须可解释，并能追溯到知识库来源或规则版本。\n- 不得把未经回测/模拟验证的 setup 写成稳定盈利策略。\n- 任何新增 setup 必须包含适用市场、周期、方向、入场、止损、目标、失效条件。\n\n## 验证要求\n- 新增策略逻辑必须配测试或回测样本。\n- 信号输出必须包含原因、置信度、风险提示和 source_refs。",
  "cost": {
    "context_tokens": 64
  }
}