[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-mnemox-ai-trading-memory-zh-CN":3,"guides-for-mnemox-ai-trading-memory":417,"similar-k174n8dznk7k8dr9drb7fwx01586nm5t-zh-CN":418},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":239,"isFallback":234,"parentExtension":244,"providers":276,"relations":280,"repo":282,"tags":414,"workflow":415},1778693819389.531,"k174n8dznk7k8dr9drb7fwx01586nm5t",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"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},"mnemox-ai/tradememory-protocol","trading-memory","https://github.com/mnemox-ai/tradememory-protocol",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":222,"workflow":237},1778693819389.5312,"kn75pm2c72zac6fqgmrcec059986mgts","zh-CN",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"tier":216,"useCases":217},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,116,120,123,126,129,132,135,138,142,146,149,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","描述清楚地说明了 AI 交易记忆的局限性问题以及“结果加权记忆”(OWM) 架构所提供的解决方案。",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","该扩展程序为 AI 交易代理提供了一种新颖的记忆架构 (OWM) 和多种记忆类型，超越了基本的交易记录。",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","该扩展程序提供了一套全面的工具，用于记录、回忆、分析和计划交易，涵盖了交易代理的完整内存管理生命周期。",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","该扩展程序专注于 AI 交易记忆领域，提供了一套连贯的工具来记录、回忆和分析与交易相关的信息。",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","显示的描述准确反映了 SKILL.md 和 README.md 中概述的功能，包括 OWM 架构、记忆类型和用例。",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","工具的命名与其功能（例如 `remember_trade`、`recall_memories`、`get_strategy_performance`）相匹配，并且不依赖于任意字符串输入。",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","SKILL.md 和 README.md 详细介绍了记忆类型、OWM 评分因素和可用的 MCP 工具，为配置和使用提供了充分的参考。",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","工具名称是描述性的，采用动宾短语，清楚地表明了它们在交易记忆领域中的功能。",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","工具描述和 SKILL.md 表明输入请求特定的交易上下文，输出返回相关的记忆或分析数据，而没有过多的诊断信息。",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","该扩展程序根据 MIT 许可证授权，如 LICENSE 文件和 README.md 中所述，这是一种宽松的开源许可证。",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","最后一次提交是在 2026 年 4 月 10 日，这在过去 3 个月内，表明维护活跃。",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","该扩展程序使用标准的 Python 包并通过 PyPI 提供，这意味着它遵循标准的依赖管理实践。",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","该扩展程序是只读的，不处理或暴露任何秘密、API 密钥或敏感用户凭证。",{"category":65,"check":69,"severity":24,"summary":70},"Injection","该扩展程序专注于结构化数据记录和回忆，没有迹象表明加载或执行不受信任的第三方代码或数据。",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","该扩展程序是自包含的，在运行时不获取外部代码或数据；所有必需的组件都已捆绑。",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","作为一个记忆和分析工具，它不会修改其预期范围之外的文件，并且在本地运行，没有外部网络调用。",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","在提供的源文件中，没有证据表明存在分离的进程创建或在拒绝工具调用周围的重试循环。",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","该扩展程序的目的是本地数据存储和分析；它明确说明不进行外部网络调用，也不向第三方发送任何数据。",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","捆绑的 markdown 文件和代码似乎没有隐藏的操纵技巧、控制字符或可疑的 Unicode 序列。",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","提供的源代码是纯粹、可读的 Python 和 markdown，没有证据表明存在混淆、base64 负载或运行时脚本获取。",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","该扩展程序处理提供的交易数据，并且不假定用户的项目文件结构。",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","在过去 90 天内，没有开放和关闭的 issue，这表明该项目非常新或者 issue 管理得非常好。",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","该项目使用 PyPI 版本控制（`pip install tradememory-protocol`），并且存在 GitHub 发布标签/标记，这表明版本控制清晰。",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","虽然在提供的代码片段中没有明确显示特定的模式验证库，但工具设计暗示了对交易数据的结构化输入，并且 README 建议提供全面的 API 参考。",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","该扩展程序主要是一个数据记录和回忆工具，没有提及或暗示任何破坏性操作。",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","SKILL.md 和 README.md 暗示了其操作（特别是合规性和审计功能）具有强大的错误处理和报告能力。",{"category":110,"check":114,"severity":24,"summary":115},"Logging","该扩展程序专注于防篡改审计跟踪，这表明对所有记录的事件都有强大的内部日志记录机制。",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","该扩展程序处理交易数据和代理行为，而不是用户的个人数据。任何个人数据都将是偶发的，并在本地处理。",{"category":117,"check":121,"severity":24,"summary":122},"Target market","该扩展程序在全球范围内适用于任何 AI 交易代理，没有提及区域或管辖权限制。",{"category":91,"check":124,"severity":24,"summary":125},"Runtime stability","该扩展程序是一个可通过 pip 安装的 Python 包，并在本地运行，因此在 POSIX 和 Windows 系统上都具有广泛的兼容性。",{"category":44,"check":127,"severity":24,"summary":128},"README","README 内容详尽，详细说明了扩展程序的目标、工作原理、快速入门、用例和技术细节。",{"category":33,"check":130,"severity":24,"summary":131},"Tool surface size","该扩展程序公开了 17 个 MCP 工具，这对于这样一个复杂的实用程序来说是推荐范围内的。",{"category":40,"check":133,"severity":24,"summary":134},"Overlapping near-synonym tools","工具命名清晰，涵盖了记忆管理的独立方面，避免了近义词的冗余。",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","所有宣传的功能，包括 5 种记忆类型和审计跟踪，都反映在工具描述和文档中。",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","提供了清晰的 pip、Claude Code、Docker 和从源代码安装的说明，以及可用于 Claude Desktop 的复制粘贴示例。",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","对审计跟踪、合规性和结构化回忆的强调表明，错误消息将是可操作且信息丰富的。",{"category":103,"check":147,"severity":24,"summary":148},"Pinned dependencies","作为一个 PyPI 包，依赖项默认是受管理和固定的，并且脚本会使用标准的 shebang。",{"category":33,"check":150,"severity":151,"summary":152},"Dry-run preview","not_applicable","该扩展程序主要是一个数据记录和回忆工具，不涉及需要干燥运行功能的状态更改操作。",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","该扩展程序专注于本地数据操作，不涉及需要显式重试/超时处理（超出标准库功能）的远程调用。",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","该扩展程序明确表示不进行外部网络调用，因此不发送遥测数据。",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","描述清楚地定义了“AI 交易记忆的领域知识”这一目的，并指出了“记录交易”和“分析性能”等用例，以及清晰的触发短语。",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","Frontmatter 简洁、自包含，并有效地总结了核心功能和触发器。",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","SKILL.md 内容简洁，概述了架构和工具，并将更深入的内容委托给单独的文件，如 'docs/'。",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","API 参考和 OWM 框架详细信息等更深入的内容链接在单独的 markdown 文件中，展示了渐进式披露。",{"category":170,"check":174,"severity":151,"summary":175},"Forked exploration","该扩展程序不是为用户项目中的深度探索或研究而设计的；它管理自己的内部记忆状态。",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","README 提供了清晰的 Claude Desktop 集成快速入门示例，并提到了单独文档中的详细演练和用例。",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","文档通过专注于结构化数据记录和回忆，并明确提及“失败分类法”文档中的失败模式，来隐含地处理边缘情况。",{"category":110,"check":183,"severity":24,"summary":184},"Tool Fallback","该扩展程序是一个独立的 Python 包，不依赖于具有回退机制的外部 MCP 服务器。",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","强调审计跟踪和合规性表明，意外状态将导致操作停止并被报告。",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","该扩展程序是自包含的，并且似乎不依赖于加载其他特定技能；任何相关任务都在内部或通过其自身提供的工具来处理。",1778693719704,"此扩展程序为 AI 交易代理提供了一个复杂的记忆系统，实现了具有五种不同记忆类型的“结果加权记忆”(OWM) 架构。它允许使用完整上下文详细记录交易，根据加权相关性（结果、相似性、近期性、置信度）进行回忆，并进行行为分析。它提供了用于创建交易计划和检查代理状态的工具，并高度重视防篡改的审计跟踪以满足监管合规性。",[195,196,197,198,199],"结果加权记忆 (OWM) 架构","五种不同的记忆类型（情景、语义、程序、情感、预期）","基于盈亏、上下文相似性、近期性和置信度的回忆评分","自动化的交易记录和分析","用于监管合规的防篡改 SHA-256 审计跟踪",[201,202,203],"执行交易或访问用户资金/钱包。","提供实时市场数据馈送（尽管它会使用市场上下文）。","取代核心交易执行平台；它是一个记忆层。","3.0.0","4.4.0","为 AI 交易代理配备持久的智能记忆，从过去的交易中学习以指导未来决策、提高性能并满足监管文件要求。","所有检查均通过，表明这是一个高质量、文档齐全且安全的扩展。",100,"一个健壮且文档齐全的 AI 交易记忆系统，具有先进的 OWM 架构和合规功能。",[211,212,213,214,215],"trading","ai","memory","finance","python","verified",[218,219,220,221],"记录带有完整上下文的每笔交易以供以后分析。","回忆过去的相似交易情况以指导当前决策。","按策略分析交易绩效并识别行为模式。","设置带有条件触发器和风险参数的交易计划。",{"codeQuality":223,"collectedAt":225,"documentation":226,"maintenance":229,"security":233,"testCoverage":236},{"hasLockfile":224},true,1778693700818,{"descriptionLength":227,"readmeSize":228},400,10941,{"closedIssues90d":8,"forks":230,"hasChangelog":224,"openIssues90d":8,"pushedAt":231,"stars":232},116,1775836242000,877,{"hasNpmPackage":234,"license":235,"smitheryVerified":234},false,"MIT",{"hasCi":224,"hasTests":224},{"updatedAt":238},1778693819389,{"basePath":240,"githubOwner":241,"githubRepo":242,"locale":18,"slug":13,"type":243},"tradememory-plugin/skills/trading-memory","mnemox-ai","tradememory-protocol","skill",{"_creationTime":245,"_id":246,"community":247,"display":248,"identity":252,"parentExtension":256,"providers":257,"relations":269,"tags":271,"workflow":272},1778693539593.1846,"k170vxkqee48k2xq1v55a025nh86nzn7",{"reviewCount":8},{"description":249,"installMethods":250,"name":251,"sourceUrl":14},"Persistent memory + autonomous strategy evolution for AI traders. 200+ trading MCP servers execute. None remember. TradeMemory does.",{"claudeCode":251},"tradememory",{"basePath":253,"githubOwner":241,"githubRepo":242,"locale":254,"slug":253,"type":255},"tradememory-plugin","en","plugin",null,{"evaluate":258,"extract":264},{"promptVersionExtension":204,"promptVersionScoring":205,"score":259,"tags":260,"targetMarket":263,"tier":216},98,[211,212,213,261,214,262],"strategy","automation","global",{"commitSha":265,"plugin":266},"HEAD",{"mcpCount":8,"provider":267,"skillCount":268},"classify",3,{"repoId":270},"kd73z11kfekksxyrs8ds0snacs86ncdy",[212,262,214,213,261,211],{"evaluatedAt":273,"extractAt":274,"updatedAt":275},1778693569977,1778693539593,1778693832100,{"evaluate":277,"extract":279},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":278,"targetMarket":263,"tier":216},[211,212,213,214,215],{"commitSha":265},{"parentExtensionId":246,"repoId":270,"translatedFrom":281},"k173a67a16bpq0e29wjd85v71986nx03",{"_creationTime":283,"_id":270,"identity":284,"providers":285,"workflow":410},1778693533831.6553,{"githubOwner":241,"githubRepo":242,"sourceUrl":14},{"classify":286,"discover":396,"github":399},{"commitSha":265,"extensions":287},[288,318,327,339,347,355,363,371,377],{"basePath":253,"description":249,"displayName":251,"installMethods":289,"rationale":290,"selectedPaths":291,"source":317,"sourceLanguage":254,"type":255},{"claudeCode":251},"plugin manifest at tradememory-plugin/.claude-plugin/plugin.json",[292,295,297,300,302,304,306,309,311,313,315],{"path":293,"priority":294},".claude-plugin/plugin.json","mandatory",{"path":296,"priority":294},"README.md",{"path":298,"priority":299},"skills/evolution-engine/SKILL.md","medium",{"path":301,"priority":299},"skills/risk-management/SKILL.md",{"path":303,"priority":299},"skills/trading-memory/SKILL.md",{"path":305,"priority":294},".mcp.json",{"path":307,"priority":308},"commands/daily-review.md","high",{"path":310,"priority":308},"commands/evolve.md",{"path":312,"priority":308},"commands/performance.md",{"path":314,"priority":308},"commands/recall.md",{"path":316,"priority":308},"commands/record-trade.md","rule",{"basePath":319,"description":320,"displayName":321,"installMethods":322,"rationale":323,"selectedPaths":324,"source":317,"sourceLanguage":254,"type":243},".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",[325],{"path":326,"priority":294},"SKILL.md",{"basePath":328,"description":329,"displayName":251,"installMethods":330,"rationale":331,"selectedPaths":332,"source":317,"sourceLanguage":254,"type":243},".skills/tradememory","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",[333,334,337],{"path":326,"priority":294},{"path":335,"priority":336},"scripts/install.sh","low",{"path":338,"priority":336},"scripts/setup_mt5.sh",{"basePath":340,"description":341,"displayName":342,"installMethods":343,"rationale":344,"selectedPaths":345,"source":317,"sourceLanguage":254,"type":243},"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",[346],{"path":326,"priority":294},{"basePath":348,"description":349,"displayName":350,"installMethods":351,"rationale":352,"selectedPaths":353,"source":317,"sourceLanguage":254,"type":243},"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",[354],{"path":326,"priority":294},{"basePath":356,"description":357,"displayName":358,"installMethods":359,"rationale":360,"selectedPaths":361,"source":317,"sourceLanguage":254,"type":243},"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",[362],{"path":326,"priority":294},{"basePath":364,"description":365,"displayName":366,"installMethods":367,"rationale":368,"selectedPaths":369,"source":317,"sourceLanguage":254,"type":243},"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",[370],{"path":326,"priority":294},{"basePath":240,"description":372,"displayName":13,"installMethods":373,"rationale":374,"selectedPaths":375,"source":317,"sourceLanguage":254,"type":243},"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\".",{"claudeCode":12},"SKILL.md frontmatter at tradememory-plugin/skills/trading-memory/SKILL.md",[376],{"path":326,"priority":294},{"basePath":378,"displayName":242,"installMethods":379,"rationale":380,"selectedPaths":381,"source":317,"sourceLanguage":254,"type":395},"",{"pypi":242},"server.json with namespace/server name at server.json",[382,384,386,387,389,391,393],{"path":383,"priority":294},"server.json",{"path":385,"priority":294},"pyproject.toml",{"path":296,"priority":294},{"path":388,"priority":308},"LICENSE",{"path":390,"priority":299},"src/tradememory/cli.py",{"path":392,"priority":299},"src/tradememory/server.py",{"path":394,"priority":336},"hosted/server.py","mcp",{"sources":397},[398],"manual",{"closedIssues90d":8,"description":400,"forks":230,"homepage":401,"license":235,"openIssues90d":8,"pushedAt":231,"readmeSize":228,"stars":232,"topics":402},"Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, SHA-256 tamper detection, 17 MCP tools.","https://mnemox.ai/tradememory/",[403,404,395,213,405,211,406,407,358,408,409],"claude","forex","mt5","ai-agents","crypto","mcp-server","outcome-weighted-memory",{"classifiedAt":411,"discoverAt":412,"extractAt":413,"githubAt":413,"updatedAt":411},1778693539413,1778693533831,1778693537570,[212,214,213,215,211],{"evaluatedAt":416,"extractAt":274,"updatedAt":238},1778693719816,[],[419,448,470,491,513,534],{"_creationTime":420,"_id":421,"community":422,"display":423,"identity":429,"providers":434,"relations":441,"tags":444,"workflow":445},1778696691708.3274,"k170az7r02e9e2v47mpy80kx6n86nff3",{"reviewCount":8},{"description":424,"installMethods":425,"name":427,"sourceUrl":428},"Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy",{"claudeCode":426},"ruvnet/ruflo","Trader Regime","https://github.com/ruvnet/ruflo",{"basePath":430,"githubOwner":431,"githubRepo":432,"locale":254,"slug":433,"type":243},"plugins/ruflo-neural-trader/skills/trader-regime","ruvnet","ruflo","trader-regime",{"evaluate":435,"extract":440},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":436,"targetMarket":263,"tier":216},[214,211,437,212,438,439],"market-analysis","typescript","cli",{"commitSha":265,"license":235},{"parentExtensionId":442,"repoId":443},"k17drge8h1fgzchr0p4jaeg33n86mwmy","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[212,439,214,437,211,438],{"evaluatedAt":446,"extractAt":447,"updatedAt":446},1778701108877,1778696691708,{"_creationTime":449,"_id":450,"community":451,"display":452,"identity":456,"providers":457,"relations":464,"tags":466,"workflow":467},1778693805112.8403,"k177f7s31ysk6nw1qw3sak1r3186n795",{"reviewCount":8},{"description":453,"installMethods":454,"name":455,"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":356,"githubOwner":241,"githubRepo":242,"locale":18,"slug":358,"type":243},{"evaluate":458,"extract":463},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":459,"targetMarket":263,"tier":216},[211,212,213,460,461,462],"audit","compliance","llm",{"commitSha":265,"license":235},{"parentExtensionId":246,"repoId":270,"translatedFrom":465},"k171p5pgbfbm5g4k5sa3y4cj9s86m6hk",[212,460,461,462,213,211],{"evaluatedAt":468,"extractAt":274,"updatedAt":469},1778693678813,1778693805112,{"_creationTime":471,"_id":472,"community":473,"display":474,"identity":478,"providers":479,"relations":485,"tags":487,"workflow":488},1778693812982.432,"k174dr25ek7cpcrj3876epsnxd86msrb",{"reviewCount":8},{"description":475,"installMethods":476,"name":477,"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":364,"githubOwner":241,"githubRepo":242,"locale":18,"slug":366,"type":243},{"evaluate":480,"extract":484},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":481,"targetMarket":263,"tier":216},[211,366,482,483,214],"ai-agent","behavioral-analysis",{"commitSha":265,"license":235},{"parentExtensionId":246,"repoId":270,"translatedFrom":486},"k17bgwvhb6h29py715de1cm9xd86msq6",[482,483,214,366,211],{"evaluatedAt":489,"extractAt":274,"updatedAt":490},1778693700524,1778693812982,{"_creationTime":492,"_id":493,"community":494,"display":495,"identity":499,"providers":501,"relations":509,"tags":510,"workflow":511},1778696691708.2983,"k17c6tkghtgnr7jnsh6gf5mf9h86nk00",{"reviewCount":8},{"description":496,"installMethods":497,"name":498,"sourceUrl":428},"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":426},"agentdb-memory-patterns",{"basePath":500,"githubOwner":431,"githubRepo":432,"locale":254,"slug":498,"type":243},".claude/skills/agentdb-memory-patterns",{"evaluate":502,"extract":508},{"promptVersionExtension":204,"promptVersionScoring":205,"score":503,"tags":504,"targetMarket":263,"tier":216},99,[212,505,213,506,438,507],"agent","database","nodejs",{"commitSha":265},{"repoId":443},[505,212,506,213,507,438],{"evaluatedAt":512,"extractAt":447,"updatedAt":512},1778698807267,{"_creationTime":514,"_id":515,"community":516,"display":517,"identity":521,"providers":523,"relations":530,"tags":531,"workflow":532},1778696691708.328,"k172nv5vbyw1c60vavz8f9esw186m2q7",{"reviewCount":8},{"description":518,"installMethods":519,"name":520,"sourceUrl":428},"Generate trading signals using npx neural-trader anomaly detection engine with Z-score scoring and neural prediction",{"claudeCode":426},"trader-signal",{"basePath":522,"githubOwner":431,"githubRepo":432,"locale":254,"slug":520,"type":243},"plugins/ruflo-neural-trader/skills/trader-signal",{"evaluate":524,"extract":529},{"promptVersionExtension":204,"promptVersionScoring":205,"score":503,"tags":525,"targetMarket":263,"tier":216},[211,214,526,527,528],"anomaly-detection","machine-learning","prediction",{"commitSha":265},{"parentExtensionId":442,"repoId":443},[526,214,527,528,211],{"evaluatedAt":533,"extractAt":447,"updatedAt":533},1778701148958,{"_creationTime":535,"_id":536,"community":537,"display":538,"identity":541,"providers":542,"relations":547,"tags":549,"workflow":550},1778693790758.6316,"k17b98r3jt7g4ck7c5c52zexkx86nffj",{"reviewCount":8},{"description":539,"installMethods":540,"name":350,"sourceUrl":14},"Binance 交易事件与 TradeMemory Protocol 之间的桥梁。\n自动记录交易，回忆相似的过往设置，检测行为偏差，\n并为 AI 交易代理提供结果加权回忆。\n在执行 Binance 现货交易后使用此技能来构建持久记忆。\n",{"claudeCode":12},{"basePath":348,"githubOwner":241,"githubRepo":242,"locale":18,"slug":350,"type":243},{"evaluate":543,"extract":546},{"promptVersionExtension":204,"promptVersionScoring":205,"score":503,"tags":544,"targetMarket":263,"tier":216},[211,214,213,545,482],"journaling",{"commitSha":265},{"repoId":270,"translatedFrom":548},"k17em57x7pnqhv6x3a2s5g5wv586mjq6",[482,214,545,213,211],{"evaluatedAt":551,"extractAt":274,"updatedAt":552},1778693660212,1778693790758]