[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-mnemox-ai-tradememory-zh-CN":3,"guides-for-mnemox-ai-tradememory":400,"similar-k1740dfs7gp4xegjrtm8qeadh186m5vg-zh-CN":401},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":245,"isFallback":240,"parentExtension":250,"providers":251,"relations":257,"repo":260,"tags":396,"workflow":397},1778693775861.6565,"k1740dfs7gp4xegjrtm8qeadh186m5vg",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"AI 交易记忆，具备结果加权回忆和自主策略演进功能。包含 17 个 MCP 工具，1,233 项测试，兼容任何交易平台。",{"claudeCode":12},"mnemox-ai/tradememory-protocol","tradememory","https://github.com/mnemox-ai/tradememory-protocol",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":227,"workflow":243},1778693775861.6567,"kn77qrvkm1asgyv3swabaksntx86nn4w","zh-CN",{"checks":20,"evaluatedAt":195,"extensionSummary":196,"features":197,"nonGoals":203,"promptVersionExtension":207,"promptVersionScoring":208,"purpose":209,"rationale":210,"score":211,"summary":212,"tags":213,"tier":221,"useCases":222},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,116,120,123,126,129,132,135,138,142,146,149,153,157,160,163,166,169,173,176,179,182,185,188,192],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","描述清楚地阐述了 AI 代理缺乏持久记忆以及无法解释过去交易决策的问题，而 TradeMemory 旨在解决这些问题。",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","TradeMemory 提供了独特的价值主张，为 AI 交易代理提供了一个专用的记忆层，包括结果加权回忆和自主策略演进，这超越了简单的 API 包装器或默认的 LLM 行为。",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","该扩展看起来已准备好投入生产，拥有全面的文档、安装说明，并明确侧重于记录和回忆交易数据，涵盖了其既定目的所需的整个生命周期。",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","该技能专注于为 AI 交易代理提供记忆和策略演进，这是一个连贯且单一的领域。",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","显示的描述准确且简洁地反映了扩展的核心功能，突出了记忆、回忆和策略演进。",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","该扩展公开了一组狭窄的、动词-名词组合的专业工具，用于管理交易记忆和演进，避免了单一的通用执行工具。",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","环境变量及其用途有清晰的文档说明，包括适用的默认值。",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","工具名称具有描述性，并遵循与交易记忆和策略演进相关的、一致的动词-名词模式。",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","工具的输入和输出是结构化的，并且似乎只请求/返回其指定任务所必需的数据，没有过多的诊断转储。",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","该扩展根据 MIT 许可证授权，如 LICENSE 文件和 README 所述，这是一种宽松的开源许可证。",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","该存储库显示了最近的提交，最后一次推送在 2026 年 4 月，表明维护活跃。",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","该项目似乎通过 pip 管理其依赖项，并且设置脚本和安装说明表明采用了标准的 Python 依赖管理方法。",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","像 API 密钥这样的密钥通过环境变量处理，并被明确标记为可选，没有迹象表明它们被硬编码或在日志中回显。",{"category":65,"check":69,"severity":24,"summary":70},"Injection","该扩展似乎将外部数据视为不受信任的，没有迹象表明它会执行加载数据中的任意代码或下载并执行远程脚本。",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","该扩展依赖于标准的 Python 包安装，并且在运行时似乎不获取或执行来自远程 URL 的代码。",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","该扩展在项目目录内运行，写入本地 SQLite 数据库，并且不尝试修改其指定范围之外的文件。",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","在提供的代码片段中未发现分离进程生成或围绕被拒绝的工具调用进行重试循环的证据。",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","该扩展明确表示，除获取 Binance 的市场数据（已记录）和（可选的、已记录的）Anthropic API 身份验证外，不进行任何出站网络调用。未发现明显的数据泄露。",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","捆绑的内容似乎不包含隐藏的指令文本、HTML 注释中的指令或不可见的 Unicode 字符。",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","捆绑的脚本是纯 Python，并且不使用 base64 编码或运行时脚本获取等混淆技术。",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","该扩展程序管理自己的本地数据存储，并且不假定用户项目文件布局（除了其自己的数据库）之外的任何内容。",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","过去 90 天内有 0 个打开和 0 个关闭的 issue，这表明项目非常新，或者 issue 跟踪器未积极用于讨论。",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","该扩展在 SKILL.md 的 frontmatter 中声明了版本（0.5.1）以及 PyPI 版本，并附带 CHANGELOG.md。",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","虽然提供的代码片段中没有明确详细说明特定的模式验证库，但将 Pydantic 用于 API 设置表明了输入处理的稳健方法。",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","该扩展主要用于数据记录和回忆；破坏性操作不是主要功能，也没有明显迹象。",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","提供的脚本和文档表明了适当的错误处理，对于非关键性问题（如操作系统兼容性）有清晰的消息和回退。MT5 连接测试也包括了错误处理。",{"category":110,"check":114,"severity":24,"summary":115},"Logging","该扩展专注于记录到自己的 SQLite 数据库，并且似乎没有供用户审查的显式日志记录机制，鉴于其性质，这是可以接受的。",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","该扩展操作交易数据和策略参数，如果由个人交易员使用，可能间接涉及个人数据，但它不会在未经批准的情况下明确处理或将 PII 提交给第三方。",{"category":117,"check":121,"severity":24,"summary":122},"Target market","该扩展被设计为全球通用且平台无关的，未检测到任何特定的区域或管辖权逻辑。",{"category":91,"check":124,"severity":24,"summary":125},"Runtime stability","该扩展指定了 Python 3.10+，并指出了 MT5 Python API 的仅限 Windows 兼容性，为其他操作系统提供了优雅的回退。",{"category":44,"check":127,"severity":24,"summary":128},"README","README 文件内容全面，清楚地说明了扩展的目的、功能以及安装/设置说明。",{"category":33,"check":130,"severity":24,"summary":131},"Tool surface size","该扩展公开了 17 个 MCP 工具，这在推荐范围内，提供了全面的功能，但又不会过于臃肿。",{"category":40,"check":133,"severity":24,"summary":134},"Overlapping near-synonym tools","工具名称清晰明了，涵盖了记忆管理和策略演进中的特定功能，没有明显的近义词重叠。",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","所有宣传的功能，包括 17 个 MCP 工具，都已在 SKILL.md 和 README 中实现并记录。",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","README 和 SKILL.md 都提供了通过 pip 进行安装的清晰说明，以及 Claude Desktop/Code 的设置说明，并附带了验证步骤。",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","设置和连接测试的错误消息清晰，指明了问题并提出了后续步骤或潜在原因。",{"category":103,"check":147,"severity":24,"summary":148},"Pinned dependencies","安装脚本使用 pip 安装依赖项，并且项目结构暗示遵循标准的 Python 依赖管理实践。",{"category":33,"check":150,"severity":151,"summary":152},"Dry-run preview","not_applicable","该扩展的核心功能是数据记录和回忆，而不是需要干运行预览的状态更改操作。",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","该扩展的操作，特别是交易记录，在适用的情况下设计为幂等的，并且可以预期在网络调用上进行标准的 Python 错误处理和潜在的重试。",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","该扩展明确表示，除了可选的 LLM API 调用和 Binance 数据获取之外，不向第三方发送任何数据，符合选择加入原则。",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","SKILL.md 和 README 清楚地定义了该扩展提供 AI 交易记忆和策略演进的目的，并概述了具体用例和触发器。",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","SKILL.md 的 frontmatter 简洁，有效地总结了 AI 交易记忆和策略演进的核心功能。",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","SKILL.md 的正文结构良好，且在一般行数限制内，将更深入的内容委托给单独的文档文件。",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","更深入的内容，如 OWM Framework 和 API Reference，链接到单独的文档文件，实现了渐进式披露。",{"category":170,"check":174,"severity":151,"summary":175},"Forked exploration","此技能不是主要用于代码审查或探索的工具，不需要 fork 上下文。",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","README 和 SKILL.md 提供了清晰的端到端示例，用于记录交易、回忆记忆、检查性能和使用演进引擎。",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","文档提到了平台兼容性和环境变量，暗示了对不同设置的处理。失败分类链接也表明了对失败模式的考虑。",{"category":110,"check":183,"severity":24,"summary":184},"Tool Fallback","该技能列出了 Python 和 MCP 服务器等要求，并提供了手动设置和本地服务器执行的说明，表明存在可选性和回退路径。",{"category":91,"check":186,"severity":24,"summary":187},"Stack assumptions","文档清楚地指明了 Python 3.10+ 作为要求，并指出了 MT5 API 的特定于操作系统的限制，确保声明了堆栈假设。",{"category":189,"check":190,"severity":24,"summary":191},"Safety","Halt on unexpected state","安装和设置脚本包括对 Python 和依赖项的检查，MT5 同步设置脚本包括对操作系统和连接的检查，并在意外状态下停止。",{"category":91,"check":193,"severity":24,"summary":194},"Cross-skill coupling","该技能专注于其核心的记忆和演进任务，并明确链接到相关的技能（“策略验证器”），避免了隐式耦合。",1778693611111,"此技能为 AI 交易代理提供持久记忆，记录带有结果加权回忆的交易，并实现自主策略演进。它提供 17 个 MCP 工具，并包含一个强大的设置，可与各种交易平台和 AI 代理集成。",[198,199,200,201,202],"结果加权记忆回忆","LLM 驱动的自主策略演进","SHA-256 防篡改交易决策记录","平台无关的交易数据集成","17 个全面的 MCP 工具，用于记忆和演进",[204,205,206],"执行交易或管理用户资金","直接与交易平台交互（需要单独的同步脚本）","取代核心 AI 代理的决策能力","3.0.0","4.4.0","为 AI 交易代理提供持久记忆，使它们能够从过去的交易中学习，回忆相关信息，并自主演进新的交易策略。","所有检查的文档和实现质量都非常出色。关于特定验证库和日志记录细节的少量信息并不影响整体的优秀表现。",99,"一个高质量、生产就绪的技能，用于 AI 交易记忆和策略演进，拥有全面的文档和工具。",[214,215,216,217,218,219,220],"trading","finance","memory","strategy","ai","python","mcp","verified",[223,224,225,226],"使用结果加权评分来记录和回忆交易历史","从原始价格数据中发现新的交易模式和策略","分析行为模式和代理状态（置信度、回撤）","为法规遵从性生成和验证防篡改审计跟踪",{"codeQuality":228,"collectedAt":230,"documentation":231,"maintenance":234,"security":239,"testCoverage":242},{"hasLockfile":229},true,1778693588873,{"descriptionLength":232,"readmeSize":233},141,10941,{"closedIssues90d":8,"forks":235,"hasChangelog":229,"manifestVersion":236,"openIssues90d":8,"pushedAt":237,"stars":238},116,"0.5.1",1775836242000,877,{"hasNpmPackage":240,"license":241,"smitheryVerified":240},false,"MIT",{"hasCi":229,"hasTests":229},{"updatedAt":244},1778693775861,{"basePath":246,"githubOwner":247,"githubRepo":248,"locale":18,"slug":13,"type":249},".skills/tradememory","mnemox-ai","tradememory-protocol","skill",null,{"evaluate":252,"extract":255},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":253,"targetMarket":254,"tier":221},[214,215,216,217,218,219,220],"global",{"commitSha":256},"HEAD",{"repoId":258,"translatedFrom":259},"kd73z11kfekksxyrs8ds0snacs86ncdy","k174jrt9tnryf6b31jfh0hn3js86ny47",{"_creationTime":261,"_id":258,"identity":262,"providers":263,"workflow":392},1778693533831.6553,{"githubOwner":247,"githubRepo":248,"sourceUrl":14},{"classify":264,"discover":378,"github":381},{"commitSha":256,"extensions":265},[266,300,309,320,328,336,344,352,360],{"basePath":267,"description":268,"displayName":13,"installMethods":269,"rationale":270,"selectedPaths":271,"source":297,"sourceLanguage":298,"type":299},"tradememory-plugin","Persistent memory + autonomous strategy evolution for AI traders. 200+ trading MCP servers execute. None remember. TradeMemory does.",{"claudeCode":13},"plugin manifest at tradememory-plugin/.claude-plugin/plugin.json",[272,275,277,280,282,284,286,289,291,293,295],{"path":273,"priority":274},".claude-plugin/plugin.json","mandatory",{"path":276,"priority":274},"README.md",{"path":278,"priority":279},"skills/evolution-engine/SKILL.md","medium",{"path":281,"priority":279},"skills/risk-management/SKILL.md",{"path":283,"priority":279},"skills/trading-memory/SKILL.md",{"path":285,"priority":274},".mcp.json",{"path":287,"priority":288},"commands/daily-review.md","high",{"path":290,"priority":288},"commands/evolve.md",{"path":292,"priority":288},"commands/performance.md",{"path":294,"priority":288},"commands/recall.md",{"path":296,"priority":288},"commands/record-trade.md","rule","en","plugin",{"basePath":301,"description":302,"displayName":303,"installMethods":304,"rationale":305,"selectedPaths":306,"source":297,"sourceLanguage":298,"type":249},".skills/strategy-validator","Validate trading strategies for overfitting using 4 statistical tests (DSR, Walk-Forward, Regime, CPCV)","strategy-validator",{"claudeCode":12},"SKILL.md frontmatter at .skills/strategy-validator/SKILL.md",[307],{"path":308,"priority":274},"SKILL.md",{"basePath":246,"description":310,"displayName":13,"installMethods":311,"rationale":312,"selectedPaths":313,"source":297,"sourceLanguage":298,"type":249},"AI trading memory with outcome-weighted recall and autonomous strategy evolution. 17 MCP tools, 1,233 tests, works with any trading platform.",{"claudeCode":12},"SKILL.md frontmatter at .skills/tradememory/SKILL.md",[314,315,318],{"path":308,"priority":274},{"path":316,"priority":317},"scripts/install.sh","low",{"path":319,"priority":317},"scripts/setup_mt5.sh",{"basePath":321,"description":322,"displayName":323,"installMethods":324,"rationale":325,"selectedPaths":326,"source":297,"sourceLanguage":298,"type":249},"skills/binance-skills-hub/trade-memory","Compliance-grade decision audit trail for AI trading agents. Records every trading decision with full context (conditions, filters, indicators, risk state), SHA-256 tamper detection, and structured export for MiFID II / EU AI Act readiness. Works alongside Binance Spot, Futures, and Web3 skills — they execute trades, TradeMemory records why.","trade-memory",{"claudeCode":12},"SKILL.md frontmatter at skills/binance-skills-hub/trade-memory/SKILL.md",[327],{"path":308,"priority":274},{"basePath":329,"description":330,"displayName":331,"installMethods":332,"rationale":333,"selectedPaths":334,"source":297,"sourceLanguage":298,"type":249},"skills/tradememory-bridge","Bridge between Binance trading events and TradeMemory Protocol.\nAutomatically journals trades, recalls similar past setups, detects behavioral biases,\nand provides outcome-weighted recall for AI trading agents.\nUse this skill after executing Binance spot trades to build persistent memory.\n","tradememory-bridge",{"claudeCode":12},"SKILL.md frontmatter at skills/tradememory-bridge/SKILL.md",[335],{"path":308,"priority":274},{"basePath":337,"description":338,"displayName":339,"installMethods":340,"rationale":341,"selectedPaths":342,"source":297,"sourceLanguage":298,"type":249},"tradememory-plugin/skills/evolution-engine","Domain knowledge for the Evolution Engine — LLM-powered autonomous strategy discovery from raw OHLCV data. Covers the generate-backtest-select-evolve loop, vectorized backtesting, out-of-sample validation, and strategy graduation. Use when discovering trading patterns, running backtests, evolving strategies, or reviewing evolution logs. Triggers on \"evolve\", \"discover patterns\", \"backtest\", \"evolution\", \"strategy generation\", \"candidate strategy\".","evolution-engine",{"claudeCode":12},"SKILL.md frontmatter at tradememory-plugin/skills/evolution-engine/SKILL.md",[343],{"path":308,"priority":274},{"basePath":345,"description":346,"displayName":347,"installMethods":348,"rationale":349,"selectedPaths":350,"source":297,"sourceLanguage":298,"type":249},"tradememory-plugin/skills/risk-management","Risk management domain knowledge for trading agents — affective state monitoring, position sizing, drawdown management, tilt detection, and behavioral guardrails. Use when checking risk before trades, managing drawdowns, detecting behavioral drift, or enforcing discipline. Triggers on \"risk\", \"drawdown\", \"tilt\", \"position size\", \"lot size\", \"confidence\", \"revenge trading\", \"overtrading\", \"discipline\".","risk-management",{"claudeCode":12},"SKILL.md frontmatter at tradememory-plugin/skills/risk-management/SKILL.md",[351],{"path":308,"priority":274},{"basePath":353,"description":354,"displayName":355,"installMethods":356,"rationale":357,"selectedPaths":358,"source":297,"sourceLanguage":298,"type":249},"tradememory-plugin/skills/trading-memory","Domain knowledge for AI trading memory — Outcome-Weighted Memory (OWM) architecture, 5 memory types, recall scoring, and behavioral analysis. Use when recording trades, recalling similar contexts, analyzing performance, or checking behavioral drift. Triggers on \"record trade\", \"remember trade\", \"recall\", \"similar trades\", \"performance\", \"behavioral\", \"disposition\", \"affective state\", \"confidence\".","trading-memory",{"claudeCode":12},"SKILL.md frontmatter at tradememory-plugin/skills/trading-memory/SKILL.md",[359],{"path":308,"priority":274},{"basePath":361,"displayName":248,"installMethods":362,"rationale":363,"selectedPaths":364,"source":297,"sourceLanguage":298,"type":220},"",{"pypi":248},"server.json with namespace/server name at server.json",[365,367,369,370,372,374,376],{"path":366,"priority":274},"server.json",{"path":368,"priority":274},"pyproject.toml",{"path":276,"priority":274},{"path":371,"priority":288},"LICENSE",{"path":373,"priority":279},"src/tradememory/cli.py",{"path":375,"priority":279},"src/tradememory/server.py",{"path":377,"priority":317},"hosted/server.py",{"sources":379},[380],"manual",{"closedIssues90d":8,"description":382,"forks":235,"homepage":383,"license":241,"openIssues90d":8,"pushedAt":237,"readmeSize":233,"stars":238,"topics":384},"Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, SHA-256 tamper detection, 17 MCP tools.","https://mnemox.ai/tradememory/",[385,386,220,216,387,214,388,389,339,390,391],"claude","forex","mt5","ai-agents","crypto","mcp-server","outcome-weighted-memory",{"classifiedAt":393,"discoverAt":394,"extractAt":395,"githubAt":395,"updatedAt":393},1778693539413,1778693533831,1778693537570,[218,215,220,216,219,217,214],{"evaluatedAt":398,"extractAt":399,"updatedAt":244},1778693611218,1778693539593,[],[402,422,451,473,494,523],{"_creationTime":403,"_id":404,"community":405,"display":406,"identity":409,"providers":410,"relations":415,"tags":418,"workflow":419},1778693819389.531,"k174n8dznk7k8dr9drb7fwx01586nm5t",{"reviewCount":8},{"description":407,"installMethods":408,"name":355,"sourceUrl":14},"AI交易记忆的领域知识 — 结果加权记忆 (OWM) 架构、5种记忆类型、回忆评分和行为分析。用于记录交易、回忆相似的上下文、分析性能或检查行为漂移。在 \"record trade\"、\"remember trade\"、\"recall\"、\"similar trades\"、\"performance\"、\"behavioral\"、\"disposition\"、\"affective state\"、\"confidence\" 时触发。",{"claudeCode":12},{"basePath":353,"githubOwner":247,"githubRepo":248,"locale":18,"slug":355,"type":249},{"evaluate":411,"extract":414},{"promptVersionExtension":207,"promptVersionScoring":208,"score":412,"tags":413,"targetMarket":254,"tier":221},100,[214,218,216,215,219],{"commitSha":256},{"parentExtensionId":416,"repoId":258,"translatedFrom":417},"k170vxkqee48k2xq1v55a025nh86nzn7","k173a67a16bpq0e29wjd85v71986nx03",[218,215,216,219,214],{"evaluatedAt":420,"extractAt":399,"updatedAt":421},1778693719816,1778693819389,{"_creationTime":423,"_id":424,"community":425,"display":426,"identity":432,"providers":437,"relations":444,"tags":447,"workflow":448},1778696691708.3274,"k170az7r02e9e2v47mpy80kx6n86nff3",{"reviewCount":8},{"description":427,"installMethods":428,"name":430,"sourceUrl":431},"Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy",{"claudeCode":429},"ruvnet/ruflo","Trader Regime","https://github.com/ruvnet/ruflo",{"basePath":433,"githubOwner":434,"githubRepo":435,"locale":298,"slug":436,"type":249},"plugins/ruflo-neural-trader/skills/trader-regime","ruvnet","ruflo","trader-regime",{"evaluate":438,"extract":443},{"promptVersionExtension":207,"promptVersionScoring":208,"score":412,"tags":439,"targetMarket":254,"tier":221},[215,214,440,218,441,442],"market-analysis","typescript","cli",{"commitSha":256,"license":241},{"parentExtensionId":445,"repoId":446},"k17drge8h1fgzchr0p4jaeg33n86mwmy","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[218,442,215,440,214,441],{"evaluatedAt":449,"extractAt":450,"updatedAt":449},1778701108877,1778696691708,{"_creationTime":452,"_id":453,"community":454,"display":455,"identity":459,"providers":460,"relations":467,"tags":469,"workflow":470},1778693805112.8403,"k177f7s31ysk6nw1qw3sak1r3186n795",{"reviewCount":8},{"description":456,"installMethods":457,"name":458,"sourceUrl":14},"Evolution Engine 的领域知识 — 支持 LLM 从原始 OHLCV 数据中自主发现策略。涵盖生成-回测-选择-进化循环、向量化回测、样本外验证和策略梯度。在发现交易模式、运行回测、进化策略或审查进化日志时使用。由“evolve”、“discover patterns”、“backtest”、“evolution”、“strategy generation”、“candidate strategy”触发。",{"claudeCode":12},"TradeMemory Protocol",{"basePath":337,"githubOwner":247,"githubRepo":248,"locale":18,"slug":339,"type":249},{"evaluate":461,"extract":466},{"promptVersionExtension":207,"promptVersionScoring":208,"score":412,"tags":462,"targetMarket":254,"tier":221},[214,218,216,463,464,465],"audit","compliance","llm",{"commitSha":256,"license":241},{"parentExtensionId":416,"repoId":258,"translatedFrom":468},"k171p5pgbfbm5g4k5sa3y4cj9s86m6hk",[218,463,464,465,216,214],{"evaluatedAt":471,"extractAt":399,"updatedAt":472},1778693678813,1778693805112,{"_creationTime":474,"_id":475,"community":476,"display":477,"identity":481,"providers":482,"relations":488,"tags":490,"workflow":491},1778693812982.432,"k174dr25ek7cpcrj3876epsnxd86msrb",{"reviewCount":8},{"description":478,"installMethods":479,"name":480,"sourceUrl":14},"交易代理的风险管理领域知识 — 情感状态监控、仓位调整、回撤管理、交易心态检测和行为控制。在交易前检查风险、管理回撤、检测行为漂移或强制执行纪律时使用。触发词包括“风险”、“回撤”、“心态”、“仓位大小”、“手数”、“信心”、“报复性交易”、“过度交易”、“纪律”。",{"claudeCode":12},"风险管理",{"basePath":345,"githubOwner":247,"githubRepo":248,"locale":18,"slug":347,"type":249},{"evaluate":483,"extract":487},{"promptVersionExtension":207,"promptVersionScoring":208,"score":412,"tags":484,"targetMarket":254,"tier":221},[214,347,485,486,215],"ai-agent","behavioral-analysis",{"commitSha":256,"license":241},{"parentExtensionId":416,"repoId":258,"translatedFrom":489},"k17bgwvhb6h29py715de1cm9xd86msq6",[485,486,215,347,214],{"evaluatedAt":492,"extractAt":399,"updatedAt":493},1778693700524,1778693812982,{"_creationTime":495,"_id":496,"community":497,"display":498,"identity":504,"providers":508,"relations":517,"tags":519,"workflow":520},1778688112811.7527,"k17enr6rktmxh0enswrmze6et186mq12",{"reviewCount":8},{"description":499,"installMethods":500,"name":502,"sourceUrl":503},"Model best-case, worst-case, and likely revenue scenarios with sensitivity analysis for strategic planning. Use when: building financial forecasts; presenting board scenarios; planning headcount around revenue uncertainty; modeling pricing changes impact; preparing investor updates with upside/downside ranges",{"claudeCode":501},"guia-matthieu/clawfu-skills","forecast-scenarios","https://github.com/guia-matthieu/clawfu-skills",{"basePath":505,"githubOwner":506,"githubRepo":507,"locale":298,"slug":502,"type":249},"skills/revops/forecast-scenarios","guia-matthieu","clawfu-skills",{"evaluate":509,"extract":516},{"promptVersionExtension":207,"promptVersionScoring":208,"score":412,"tags":510,"targetMarket":254,"tier":221},[215,511,512,513,217,514,515],"forecasting","revenue","planning","sensitivity-analysis","mckinsey",{"commitSha":256},{"repoId":518},"kd72qvzyvm658ya7pbyh5ey47h86md53",[215,511,515,513,512,514,217],{"evaluatedAt":521,"extractAt":522,"updatedAt":521},1778690475880,1778688112811,{"_creationTime":524,"_id":525,"community":526,"display":527,"identity":531,"providers":533,"relations":540,"tags":541,"workflow":542},1778696691708.2983,"k17c6tkghtgnr7jnsh6gf5mf9h86nk00",{"reviewCount":8},{"description":528,"installMethods":529,"name":530,"sourceUrl":431},"Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.",{"claudeCode":429},"agentdb-memory-patterns",{"basePath":532,"githubOwner":434,"githubRepo":435,"locale":298,"slug":530,"type":249},".claude/skills/agentdb-memory-patterns",{"evaluate":534,"extract":539},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":535,"targetMarket":254,"tier":221},[218,536,216,537,441,538],"agent","database","nodejs",{"commitSha":256},{"repoId":446},[536,218,537,216,538,441],{"evaluatedAt":543,"extractAt":450,"updatedAt":543},1778698807267]