[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-Whatsonyourmind-oraclaw-calibrate-zh-CN":3,"guides-for-Whatsonyourmind-oraclaw-calibrate":431,"similar-k17b8k37k50x3v23661204y2w586mtkx-zh-CN":432},{"_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":427,"workflow":428},1778699104170.7488,"k17b8k37k50x3v23661204y2w586mtkx",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"AI 代理的预测质量评分。Brier 分数、对数分数和多源收敛性分析。了解您的预测是否准确以及您的数据源是否一致。",{"claudeCode":12},"Whatsonyourmind/oraclaw","oraclaw-calibrate","https://github.com/Whatsonyourmind/oraclaw",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":226,"workflow":243},1778699104170.749,"kn7e6knjbp5p5t64580bc43gd586mhr6","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":220,"useCases":221},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,117,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","描述清楚地说明了对 AI 代理预测质量进行评分的问题，并提到了 Brier 分数和对数分数等特定指标。",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","该技能提供用于优化和分析的确定性算法，为数学任务提供的价值超出了通用 LLM 的能力。",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","该技能已准备好投入生产，提供多种集成、SDK 和清晰的 API，涵盖了预测评分的整个生命周期。",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","该技能专注于预测质量评分和相关的数学/统计分析，具有明确的领域。",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","显示的描述准确地反映了该技能在预测质量评分和收敛性分析方面的能力。",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","该技能公开了两个范围明确、定义清晰的工具：`score_calibration` 和 `score_convergence`。",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","SKILL.md 的 frontmatter 和工具描述清楚地列出了参数以及所需的 ORACLAW_API_KEY 环境变量。",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","像 `score_calibration` 和 `score_convergence` 这样的工具名称具有描述性，并表明了它们的功能。",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","工具输入是结构化数组，输出是明确定义的 JSON 对象，仅包含承诺的评分和分析结果。",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","该扩展在 MIT 许可下发布，这是一个宽松的开源许可证，在 LICENSE 文件和 README 中已清楚标明。",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","上次提交是在 2026 年 5 月 2 日，远在 3 个月的时间阈值之内。",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","该项目有一个锁文件（通过 `hasLockfile: true` 推断）和多个 SDK 包，这表明了良好的依赖管理实践。",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","通过环境变量要求提供 `ORACLAW_API_KEY` 并且不将其回显在输出中，这表明了正确的密钥处理方式。",{"category":65,"check":69,"severity":24,"summary":70},"Injection","该技能处理结构化数据，并且似乎不加载或执行外部、不受信任的代码或数据。",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","该技能依赖于其自身的捆绑算法，并且在运行时不获取外部代码或数据进行执行。",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","该技能作为一个服务运行，并且似乎不在其指定范围之外执行文件系统操作。",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","在提供的源代码中未发现分离进程或拒绝重试循环的证据。",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","该技能处理用于评分的数值数据，并且似乎不读取或提交机密用户数据。",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","捆绑的内容似乎没有隐藏的操纵技巧，并使用干净、可打印的 ASCII 和标准 Unicode。",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","该技能的逻辑基于定义的算法和 API 调用，而不是混淆的代码或运行时执行。",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","该技能作为一个服务运行，并且不假定用户项目的文件布局。",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","在过去 90 天内，已关闭 44 个问题，打开 0 个问题，关闭率很高，问题数量表明维护活跃。",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","在 SKILL.md 的 frontmatter 中声明了一个有意义的版本 `version: 1.0.0`。",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","工具输入是类型化的数组，鉴于其作为数学 API 的性质，该服务可能执行内部验证。",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","此技能是只读和分析性的，不执行任何破坏性操作。",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","作为一个服务，它应该在内部处理错误并返回结构化响应，无需可见的脚本级错误处理。",{"category":110,"check":114,"severity":115,"summary":116},"Logging","not_applicable","该技能作为一个服务运行，没有破坏性操作或需要本地记录的出站调用。",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","GDPR","该技能处理数值预测数据，并且似乎不处理个人数据。",{"category":118,"check":122,"severity":24,"summary":123},"Target market","该扩展处理通用的数学概念，没有任何区域或司法限制。",{"category":91,"check":125,"severity":24,"summary":126},"Runtime stability","该技能作为 REST API 和 MCP 服务器运行，抽象了操作系统和 shell 依赖项。",{"category":44,"check":128,"severity":24,"summary":129},"README","README 内容全面，详细说明了目的、验证、快速入门、工具和源代码。",{"category":33,"check":131,"severity":24,"summary":132},"Tool surface size","该扩展公开了 2 个工具，这在理想范围内。",{"category":40,"check":134,"severity":24,"summary":135},"Overlapping near-synonym tools","两个工具 `score_calibration` 和 `score_convergence` 代表不同的功能，并非近义词。",{"category":44,"check":137,"severity":24,"summary":138},"Phantom features","所有宣传的功能，包括工具和 SDK，都在文档中有相应的实现描述。",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","为 MCP 服务器和 npm SDK 提供了清晰的安装说明，以及 API 用法示例。",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","作为一个服务，错误预计是结构化的且可操作的，符合 API 最佳实践。",{"category":103,"check":148,"severity":24,"summary":149},"Pinned dependencies","存在 `hasLockfile: true` 和已发布的 npm 包表明依赖项已被固定。",{"category":33,"check":151,"severity":24,"summary":152},"Dry-run preview","该技能是分析性和只读的，因此不适用预演模式（dry-run preview）。",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","该技能作为无状态服务运行，其操作本质上是幂等计算。",{"category":118,"check":158,"severity":24,"summary":159},"Telemetry opt-in","没有提及遥测收集，这意味着默认情况下不发送遥测数据或严格选择加入。",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","描述清楚地定义了该技能的预测质量评分和收敛性分析目的，并有明确的用例。",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","Frontmatter 简洁且自成一体，清晰地总结了核心功能并提供了相关元数据。",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","SKILL.md 结构良好且简洁，将更深入的内容委托给 README 和外部链接。",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","SKILL.md 简洁，并适当地链接到 README 以获取更多详细信息和示例。",{"category":170,"check":174,"severity":115,"summary":175},"Forked exploration","此技能不是探索性或审计类技能；它执行直接计算，不需要分叉探索上下文。",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","README 提供了清晰、可直接复制的 API 使用和 MCP 服务器及 SDK 安装示例。",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","该技能的数学评分领域本身就处理各种输入范围，描述暗示了健壮的处理能力。",{"category":110,"check":183,"severity":115,"summary":184},"Tool Fallback","该技能不引用具有自定义要求的外部 MCP 服务器；它作为自己的服务运行或使用内部工具。",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","作为一个计算服务，它在遇到意外输入状态时会自然地停止并返回错误。",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","该技能独立运行，不依赖于其他特定技能同时加载。",1778698903765,"此技能使用 Brier 分数和对数分数等指标为 AI 代理的预测提供确定性的数学评分，并分析多源收敛性。它作为 MCP 服务器、REST API 和 SDK 运行。",[195,196,197,198,199],"评分预测准确性（Brier 分数、对数分数）","分析多源一致性/收敛性","检测异常数据源","提供确定性的算法答案","提供 MCP 服务器、REST API 和 SDK",[201,202,203],"提供预测本身","执行通用的 AI 代理推理","作为主要 LLM 功能的替代品","3.0.0","4.4.0","为 AI 代理提供精确的数学工具，用于评估其预测的准确性以及不同信息源之间的一致性。","所有检查均达到高质量，没有警告或严重问题。少量不适用 (not_applicable) 的发现不会影响其整体卓越性。",97,"用于对预测质量进行评分和分析数据源一致性的优秀技能。",[211,212,213,214,215,216,217,218,219],"calibration","forecasting","prediction","accuracy","scoring","convergence","brier-score","statistics","analysis","verified",[222,223,224,225],"评分过去预测的准确性","检查多个数据源是否对预测达成一致","找出与共识不一致的异常数据源","跨不同模型比较预测质量",{"codeQuality":227,"collectedAt":229,"documentation":230,"maintenance":233,"security":239,"testCoverage":242},{"hasLockfile":228},true,1778698883771,{"descriptionLength":231,"readmeSize":232},172,9472,{"closedIssues90d":234,"forks":235,"hasChangelog":228,"manifestVersion":236,"openIssues90d":8,"pushedAt":237,"stars":238},44,2,"1.0.0",1777714123000,8,{"hasNpmPackage":240,"license":241,"smitheryVerified":240},false,"MIT",{"hasCi":228,"hasTests":228},{"updatedAt":244},1778699104170,{"basePath":246,"githubOwner":247,"githubRepo":248,"locale":18,"slug":13,"type":249},"mission-control/packages/clawhub-skills/oraclaw-calibrate","Whatsonyourmind","oraclaw","skill",null,{"evaluate":252,"extract":255},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":253,"targetMarket":254,"tier":220},[211,212,213,214,215,216,217,218,219],"global",{"commitSha":256},"HEAD",{"repoId":258,"translatedFrom":259},"kd76fmxm1ng903s4fmj0p7hxxs86ndkg","k177gnp7tvr9phd9psfw21zgcs86ndx2",{"_creationTime":261,"_id":258,"identity":262,"providers":263,"workflow":423},1778698831609.0093,{"githubOwner":247,"githubRepo":248,"sourceUrl":14},{"classify":264,"discover":397,"github":400},{"commitSha":256,"extensions":265},[266,278,286,294,300,308,316,324,332,340,348,356,364,372,380],{"basePath":267,"description":268,"displayName":269,"installMethods":270,"rationale":271,"selectedPaths":272,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-anomaly","Anomaly detection for AI agents. Z-score, IQR, and streaming detection. Find outliers in data instantly. Sub-millisecond response. Works on single values or full datasets.","oraclaw-anomaly",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-anomaly/SKILL.md",[273],{"path":274,"priority":275},"SKILL.md","mandatory","rule","en",{"basePath":279,"description":280,"displayName":281,"installMethods":282,"rationale":283,"selectedPaths":284,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-bandit","A/B testing and feature optimization for AI agents. Pick the best option automatically using Multi-Armed Bandits and Contextual Bandits (LinUCB). No data warehouse needed — works from request","oraclaw-bandit",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-bandit/SKILL.md",[285],{"path":274,"priority":275},{"basePath":287,"description":288,"displayName":289,"installMethods":290,"rationale":291,"selectedPaths":292,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-bayesian","Bayesian inference engine for AI agents. Update beliefs with new evidence. Prior + evidence = posterior. Multi-factor prediction with calibration tracking.","oraclaw-bayesian",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-bayesian/SKILL.md",[293],{"path":274,"priority":275},{"basePath":246,"description":295,"displayName":13,"installMethods":296,"rationale":297,"selectedPaths":298,"source":276,"sourceLanguage":277,"type":249},"Prediction quality scoring for AI agents. Brier score, log score, and multi-source convergence analysis. Know if your forecasts are accurate and if your data sources agree.",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-calibrate/SKILL.md",[299],{"path":274,"priority":275},{"basePath":301,"description":302,"displayName":303,"installMethods":304,"rationale":305,"selectedPaths":306,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-cmaes","CMA-ES continuous optimization for AI agents. State-of-the-art derivative-free optimizer. 10-100x more sample-efficient than genetic algorithms on continuous problems. Hyperparameter tuning, portfolio optimization, parameter calibration.","oraclaw-cmaes",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-cmaes/SKILL.md",[307],{"path":274,"priority":275},{"basePath":309,"description":310,"displayName":311,"installMethods":312,"rationale":313,"selectedPaths":314,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-decide","Decision intelligence for AI agents. Analyze options, map decision dependencies with PageRank, detect when information sources conflict, and find the choices that matter most.","oraclaw-decide",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-decide/SKILL.md",[315],{"path":274,"priority":275},{"basePath":317,"description":318,"displayName":319,"installMethods":320,"rationale":321,"selectedPaths":322,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-ensemble","Multi-model consensus for AI agents. Combine predictions from multiple LLMs, models, or sources into a mathematically optimal consensus. Auto-weights by historical accuracy.","oraclaw-ensemble",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-ensemble/SKILL.md",[323],{"path":274,"priority":275},{"basePath":325,"description":326,"displayName":327,"installMethods":328,"rationale":329,"selectedPaths":330,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-evolve","Genetic Algorithm optimizer for AI agents. Multi-objective Pareto optimization for portfolio weights, pricing, hyperparameters, marketing mix — any problem with multiple competing goals. Handles nonlinear search spaces that LP solvers cannot.","oraclaw-evolve",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-evolve/SKILL.md",[331],{"path":274,"priority":275},{"basePath":333,"description":334,"displayName":335,"installMethods":336,"rationale":337,"selectedPaths":338,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-forecast","Time series forecasting for AI agents. ARIMA and Holt-Winters predictions with confidence intervals. Predict revenue, traffic, prices, or any sequential data. Sub-5ms inference.","oraclaw-forecast",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-forecast/SKILL.md",[339],{"path":274,"priority":275},{"basePath":341,"description":342,"displayName":343,"installMethods":344,"rationale":345,"selectedPaths":346,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-graph","Network intelligence for AI agents. PageRank, community detection (Louvain), critical path, and bottleneck analysis for any graph of connected things.","oraclaw-graph",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-graph/SKILL.md",[347],{"path":274,"priority":275},{"basePath":349,"description":350,"displayName":351,"installMethods":352,"rationale":353,"selectedPaths":354,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-pathfind","A* pathfinding and task sequencing for AI agents. Find the optimal path through workflows, dependencies, and decision trees. K-shortest paths via Yen's algorithm. Cost/time/risk breakdown.","oraclaw-pathfind",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-pathfind/SKILL.md",[355],{"path":274,"priority":275},{"basePath":357,"description":358,"displayName":359,"installMethods":360,"rationale":361,"selectedPaths":362,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-risk","Risk assessment engine for AI agents. Value at Risk (VaR), CVaR, stress testing, and multi-factor risk scoring. Monte Carlo powered. Built for trading agents, lending agents, and portfolio managers.","oraclaw-risk",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-risk/SKILL.md",[363],{"path":274,"priority":275},{"basePath":365,"description":366,"displayName":367,"installMethods":368,"rationale":369,"selectedPaths":370,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-simulate","Monte Carlo simulation for AI agents. Run thousands of probabilistic scenarios to model risk, forecast revenue, estimate project timelines, and quantify uncertainty. Supports 6 distribution types.","oraclaw-simulate",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-simulate/SKILL.md",[371],{"path":274,"priority":275},{"basePath":373,"description":374,"displayName":375,"installMethods":376,"rationale":377,"selectedPaths":378,"source":276,"sourceLanguage":277,"type":249},"mission-control/packages/clawhub-skills/oraclaw-solver","Industrial-grade scheduling and resource optimization for AI agents. Solve task scheduling with energy matching, budget allocation, and any LP/MIP constraint problem in milliseconds.","oraclaw-solver",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-solver/SKILL.md",[379],{"path":274,"priority":275},{"basePath":381,"description":382,"displayName":383,"installMethods":384,"license":241,"rationale":385,"selectedPaths":386,"source":276,"sourceLanguage":277,"type":396},"mission-control/packages/mcp-server","OraClaw Decision Intelligence — 17 MCP tools for AI agents (6 premium API-key tools + 11 free). Full input/output schemas + MCP behavior annotations on every tool. Optimization (bandit/CMA-ES/genetic/LP-MIP), simulation (Monte Carlo/scenarios), prediction (ARIMA/Holt-Winters/Bayesian/ensemble), scoring (convergence/calibration), graph analytics, anomaly detection, pathfinding, scheduling.","@oraclaw/mcp-server",{"npm":383},"server.json with namespace/server name at mission-control/packages/mcp-server/server.json",[387,389,391,393],{"path":388,"priority":275},"server.json",{"path":390,"priority":275},"package.json",{"path":392,"priority":275},"README.md",{"path":394,"priority":395},"src/index.ts","low","mcp",{"sources":398},[399],"manual",{"closedIssues90d":234,"description":401,"forks":235,"homepage":402,"license":241,"openIssues90d":8,"pushedAt":237,"readmeSize":232,"stars":238,"topics":403},"Deterministic decision-intelligence MCP server for AI agents — 17 tools, 21 algorithms (LinUCB, HiGHS LP/MIP, PageRank, Monte Carlo, CMA-ES, conformal). Sub-25ms. Zero LLM cost. AAA on Glama. Field-validated in 12+ OSS projects.","https://web-olive-one-89.vercel.app",[404,405,406,407,408,409,410,396,411,412,413,414,415,416,417,418,419,420,421,422],"ai-agents","algorithms","api","bandits","decision-intelligence","fastify","machine-learning","optimization","typescript","agent-tools","anthropic","claude-mcp","contextual-bandit","deterministic-tools","linear-programming","llm-tools","model-context-protocol","monte-carlo","pagerank",{"classifiedAt":424,"discoverAt":425,"extractAt":426,"githubAt":426,"updatedAt":424},1778698837409,1778698831609,1778698835357,[214,219,217,211,216,212,213,215,218],{"evaluatedAt":429,"extractAt":430,"updatedAt":244},1778698906461,1778698837670,[],[433,464,488,516,545,566],{"_creationTime":434,"_id":435,"community":436,"display":437,"identity":443,"providers":448,"relations":457,"tags":460,"workflow":461},1778675056600.2537,"k17ask0fam6yfypdvf5562p15986m925",{"reviewCount":8},{"description":438,"installMethods":439,"name":441,"sourceUrl":442},"Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction for strategic decision-making. Use when analyzing financial statements, building valuation models, assessing budget variances, or constructing financial projections and forecasts. Also applicable when users mention financial modeling, cash flow analysis, company valuation, financial projections, or spreadsheet analysis.",{"claudeCode":440},"alirezarezvani/claude-skills","Financial Analyst","https://github.com/alirezarezvani/claude-skills",{"basePath":444,"githubOwner":445,"githubRepo":446,"locale":277,"slug":447,"type":249},"finance/skills/financial-analyst","alirezarezvani","claude-skills","financial-analyst",{"evaluate":449,"extract":456},{"promptVersionExtension":204,"promptVersionScoring":205,"score":450,"tags":451,"targetMarket":254,"tier":220},100,[452,219,453,212,454,455],"finance","valuation","budgeting","python",{"commitSha":256,"license":241},{"parentExtensionId":458,"repoId":459},"k174nmf7jahgcsdnzenmdxfcbh86m85y","kd7ff9s1w43mfyy1n7hf87816186m6px",[219,454,452,212,455,453],{"evaluatedAt":462,"extractAt":463,"updatedAt":462},1778683964036,1778675056600,{"_creationTime":465,"_id":466,"community":467,"display":468,"identity":472,"providers":473,"relations":482,"tags":484,"workflow":485},1778699133476.6787,"k1781nsw0x98bnp3a0cnw94z1n86mgd4",{"reviewCount":8},{"description":469,"installMethods":470,"name":471,"sourceUrl":14},"AI 代理的时间序列预测。ARIMA 和 Holt-Winters 预测（含置信区间）。预测收入、流量、价格或任何序列数据。推理延迟低于 5 毫秒。",{"claudeCode":12},"OraClaw Forecast",{"basePath":333,"githubOwner":247,"githubRepo":248,"locale":18,"slug":335,"type":249},{"evaluate":474,"extract":481},{"promptVersionExtension":204,"promptVersionScoring":205,"score":450,"tags":475,"targetMarket":254,"tier":220},[212,476,213,477,478,479,480],"time-series","arima","holt-winters","analytics","data-science",{"commitSha":256,"license":241},{"repoId":258,"translatedFrom":483},"k17a19x757qjaehqa5jah8k7y986n55p",[479,477,480,212,478,213,476],{"evaluatedAt":486,"extractAt":430,"updatedAt":487},1778698975269,1778699133476,{"_creationTime":489,"_id":490,"community":491,"display":492,"identity":498,"providers":502,"relations":508,"tags":511,"workflow":512},1778675791860.845,"k174f2y3jxg9senxnc66r7j6dx86md8y",{"reviewCount":8},{"description":493,"installMethods":494,"name":496,"sourceUrl":497},"应用提示重复以提高非推理 LLM 的准确性",{"claudeCode":495},"asklokesh/loki-mode","prompt-optimization","https://github.com/asklokesh/loki-mode",{"basePath":499,"githubOwner":500,"githubRepo":501,"locale":18,"slug":496,"type":249},"agent-skills/prompt-optimization","asklokesh","loki-mode",{"evaluate":503,"extract":507},{"promptVersionExtension":204,"promptVersionScoring":205,"score":450,"tags":504,"targetMarket":254,"tier":220},[505,506,214,411],"llm","prompt-engineering",{"commitSha":256},{"repoId":509,"translatedFrom":510},"kd7dy44r49793jt8bt02wdezk586nxsn","k17bjgfyvbnt05kpma9n0gn4j186n152",[214,505,411,506],{"evaluatedAt":513,"extractAt":514,"updatedAt":515},1778675713014,1778675659559,1778675791860,{"_creationTime":517,"_id":518,"community":519,"display":520,"identity":526,"providers":531,"relations":539,"tags":541,"workflow":542},1778696691708.3035,"k17br1j5s86ae90zqeyd7zcg2586mkwr",{"reviewCount":8},{"description":521,"installMethods":522,"name":524,"sourceUrl":525},"Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms\n",{"claudeCode":523},"ruvnet/ruflo","Performance Analysis","https://github.com/ruvnet/ruflo",{"basePath":527,"githubOwner":528,"githubRepo":529,"locale":277,"slug":530,"type":249},".claude/skills/performance-analysis","ruvnet","ruflo","performance-analysis",{"evaluate":532,"extract":538},{"promptVersionExtension":204,"promptVersionScoring":205,"score":450,"tags":533,"targetMarket":254,"tier":220},[534,219,411,535,536,537],"performance","claude-flow","bottleneck-detection","reporting",{"commitSha":256,"license":241},{"repoId":540},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[219,536,535,411,534,537],{"evaluatedAt":543,"extractAt":544,"updatedAt":543},1778699217174,1778696691708,{"_creationTime":546,"_id":547,"community":548,"display":549,"identity":552,"providers":553,"relations":560,"tags":562,"workflow":563},1778699119124.668,"k174xef0y7h5dr9f932g3ax6d986n2dd",{"reviewCount":8},{"description":550,"installMethods":551,"name":311,"sourceUrl":14},"为 AI 代理提供决策智能。分析选项、使用 PageRank 映射决策依赖关系、检测信息源冲突，并找出最重要的选择。",{"claudeCode":12},{"basePath":309,"githubOwner":247,"githubRepo":248,"locale":18,"slug":311,"type":249},{"evaluate":554,"extract":559},{"promptVersionExtension":204,"promptVersionScoring":205,"score":450,"tags":555,"targetMarket":254,"tier":220},[556,219,411,557,558],"decision-making","graph-theory","ai-agent-tools",{"commitSha":256},{"repoId":258,"translatedFrom":561},"k17fe7ybjme5s1n10mmg3emmns86nr26",[558,219,556,557,411],{"evaluatedAt":564,"extractAt":430,"updatedAt":565},1778698934136,1778699119124,{"_creationTime":567,"_id":568,"community":569,"display":570,"identity":576,"providers":580,"relations":588,"tags":590,"workflow":591},1778697652123.8975,"k17egwaz31kmprzw1q8m38fv4586mqah",{"reviewCount":8},{"description":571,"installMethods":572,"name":574,"sourceUrl":575},"Search and analyze your own session logs (older/parent conversations) using jq.",{"claudeCode":573},"steipete/clawdis","session-logs","https://github.com/steipete/clawdis",{"basePath":577,"githubOwner":578,"githubRepo":579,"locale":277,"slug":574,"type":249},"skills/session-logs","steipete","clawdis",{"evaluate":581,"extract":587},{"promptVersionExtension":204,"promptVersionScoring":205,"score":450,"tags":582,"targetMarket":254,"tier":220},[583,584,585,219,586],"logs","session","jq","cli",{"commitSha":256},{"repoId":589},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[219,586,585,583,584],{"evaluatedAt":592,"extractAt":593,"updatedAt":592},1778698902636,1778697652123]