[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-Whatsonyourmind-oraclaw-forecast-zh-CN":3,"guides-for-Whatsonyourmind-oraclaw-forecast":441,"similar-k1781nsw0x98bnp3a0cnw94z1n86mgd4-zh-CN":442},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":254,"isFallback":249,"parentExtension":260,"providers":261,"relations":267,"repo":270,"tags":437,"workflow":438},1778699133476.6787,"k1781nsw0x98bnp3a0cnw94z1n86mgd4",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"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},"Whatsonyourmind/oraclaw","OraClaw Forecast","https://github.com/Whatsonyourmind/oraclaw",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":235,"workflow":252},1778699133476.679,"kn777qer5ek24gwy3pwvjwea9986ndap","zh-CN",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"practices":204,"prerequisites":208,"promptVersionExtension":210,"promptVersionScoring":211,"purpose":212,"rationale":213,"score":214,"summary":215,"tags":216,"tier":224,"useCases":225,"workflow":230},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,117,121,124,127,130,133,136,139,143,146,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","描述清楚地说明了 AI 代理的时间序列预测问题，并命名了收入和流量等具体数据类型。",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","该技能提供（ARIMA、Holt-Winters）的数学上正确的预测算法，这超出了 LLM 的基本功能，并提供了确定性的答案。",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","该技能已生产就绪，拥有清晰的 API、SDK 和 MCP 服务器集成，涵盖了完整的预测生命周期。",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","该技能仅专注于时间序列预测，这与其名称和描述一致。",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","显示的描述准确反映了技能的能力，并且简洁明了。",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","该技能公开了一个单一的、定义明确的工具（`predict_forecast`）用于其核心功能。",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","SKILL.md 清楚地记录了 `predict_forecast` 工具的参数，包括数据、步数、方法和季节长度。",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","单一工具 `predict_forecast` 的命名具有描述性且易于理解。",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","`predict_forecast` 工具的输入参数（`data`、`steps`、`method`、`seasonLength`）具体且对预测是必需的，输出明确定义为带置信区间的时间序列预测值。",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","该扩展在 MIT 许可下分发，该许可是允许的，并在 LICENSE 文件和 README 中明确声明。",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","最后一次提交是在 2026 年 5 月 2 日，在过去 3 个月内。",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","该项目有一个锁文件（`hasLockfile: true`），并且似乎能有效管理其依赖项，具有高测试覆盖率和 CI。",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","提到了 `ORACLAW_API_KEY` 作为要求，但未硬编码或在输出中暴露。README 中没有显示任何敏感信息被记录。",{"category":65,"check":69,"severity":24,"summary":70},"Injection","该技能专注于数值数据处理和预测算法，没有迹象表明会加载或执行不受信任的第三方数据作为指令。",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","该技能似乎不会在运行时获取外部代码或数据。所有必要的算法和数据处理似乎都是自包含的，或依赖于 MCP 服务器。",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","该技能在提供的数据上运行并返回预测；没有迹象表明它试图修改其预期范围之外的文件。",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","在提供的代码片段或描述中未检测到分离的进程生成或拒绝工具调用周围的重试循环。",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","该技能处理用于预测的数值数据，并且似乎不处理或泄露机密信息。",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","提供的 SKILL.md 和 README 内容没有隐藏文本技巧或可疑的 Unicode 字符。",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","该技能的逻辑基于明确定义的算法和工具，没有模糊或不透明的代码执行迹象。",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","该技能以数据作为输入，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，已打开 0 个问题，已关闭 44 个问题，关闭率很高，表明维护活跃。",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","SKILL.md 前端声明版本为 1.0.0，README 指出有实现和更新，这表明版本管理良好。",{"category":103,"check":104,"severity":24,"summary":105},"Code Execution","Validation","SKILL.md 中的工具模式和规则定义了数据、步数和方法的明确输入要求，暗示了验证。",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","该技能纯粹是分析性的，不执行任何破坏性操作。",{"category":110,"check":111,"severity":24,"summary":112},"Errors","Error Handling","SKILL.md 概述了数据点最少要求和季节性等规则，这表明对于无效输入会引发错误，并指导用户进行补救。",{"category":103,"check":114,"severity":115,"summary":116},"Logging","not_applicable","该技能主要是数据处理工具，不执行破坏性操作或进行通常需要本地审计日志记录的传出调用。",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","GDPR","该技能处理数值时间序列数据，这些数据不是个人数据。",{"category":118,"check":122,"severity":24,"summary":123},"Target market","该扩展的预测能力普遍适用，不与任何特定的地理或法律管辖区挂钩。",{"category":91,"check":125,"severity":24,"summary":126},"Runtime stability","该技能依赖于标准算法和数据处理，没有对特定编辑器、Shell 或操作系统的明显假设。",{"category":44,"check":128,"severity":24,"summary":129},"README","README 内容全面，详细介绍了项目的目的、实现和市场分布。",{"category":33,"check":131,"severity":24,"summary":132},"Tool surface size","该扩展公开了一个工具 `predict_forecast`，这与其专注的功能是合适的。",{"category":40,"check":134,"severity":24,"summary":135},"Overlapping near-synonym tools","该扩展只公开了一个工具，因此没有重叠的近义词工具。",{"category":44,"check":137,"severity":24,"summary":138},"Phantom features","所有宣传的功能，例如带置信区间预测的 ARIMA 和 Holt-Winters，都由 `predict_forecast` 工具直接支持。",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","提供了 MCP 服务器、REST API 和 npm SDK 的安装说明，以及清晰的调用示例。",{"category":110,"check":144,"severity":24,"summary":145},"Actionable error messages","SKILL.md 概述了数据点最少要求和季节性长度等规则，这表明会因未满足条件而引发错误，并指导用户进行补救。",{"category":147,"check":148,"severity":24,"summary":149},"Execution","Pinned dependencies","该项目有一个锁文件（`hasLockfile: true`），表明依赖项已固定。",{"category":33,"check":151,"severity":115,"summary":152},"Dry-run preview","该技能纯粹是分析性的，不执行任何状态更改操作或发送外部数据。",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","该技能是分析性的，不涉及需要幂等性或超时设置的远程调用或状态更改操作。",{"category":118,"check":158,"severity":24,"summary":159},"Telemetry opt-in","没有迹象表明此技能会收集遥测数据。",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","该技能清楚地说明了其作为时间序列预测的目的（使用 ARIMA 和 Holt-Winters），其用例涵盖了收入和流量等序列数据的预测。",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","前端内容简洁，有效总结了技能的核心能力和主要功能。",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","SKILL.md 结构良好且简洁，详细说明了技能的目的、工具和规则，无不必要的冗长。",{"category":170,"check":171,"severity":115,"summary":172},"Context","Progressive Disclosure","该技能简洁，不涉及需要通过单独的参考文件进行渐进披露的长程序。",{"category":170,"check":174,"severity":115,"summary":175},"Forked exploration","该技能是一个专注的预测工具，不涉及需要分叉上下文的深入探索或代码审查。",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","SKILL.md 提供了 ARIMA 和 Holt-Winters 方法的清晰、可直接使用的示例，演示了输入和预期输出。",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","SKILL.md 记录了最小数据点要求和更长预测的置信区间变宽等限制，提供了关于失败模式的隐式指导。",{"category":103,"check":183,"severity":115,"summary":184},"Tool Fallback","该技能不依赖外部 MCP 服务器；其功能是自包含的，或通过其自己的 API/SDK 公开。",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","最小数据点和季节性长度的规则隐式定义了前提条件，遵守这些规则可能会在意外状态下停止进程。",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","该技能是自包含的，并且专注于预测，没有表明与其它技能存在隐式依赖。",1778698975157,"该技能使用 ARIMA 和 Holt-Winters 方法提供时间序列预测功能，输出带置信区间的预测。可以通过 MCP 服务器、REST API 或 npm SDK 访问。",[195,196,197,198,199],"ARIMA 时间序列预测（自动拟合）","Holt-Winters 季节性预测","预测的 95% 置信区间","API 推理延迟低于 5 毫秒","MCP 服务器、REST API 和 SDK 访问",[201,202,203],"执行超出预测范围的复杂统计分析","处理非序列或非结构化数据","为高频交易提供实时、低延迟预测",[205,206,207],"时间序列分析","统计建模","预测",[209],"ORACLAW_API_KEY 环境变量（用于高级功能）","3.0.0","4.4.0","为 AI 代理提供精确、确定性的时间序列预测能力，超越启发式预测，实现数学上可靠的结果。","所有检查均通过，表明这是一项高质量、文档齐全、生产就绪的技能，并且在最佳实践方面有出色的遵守度。",100,"一项高质量、生产就绪的技能，可进行准确的时间序列预测，并附有清晰的文档和示例。",[217,218,219,220,221,222,223],"forecasting","time-series","prediction","arima","holt-winters","analytics","data-science","verified",[226,227,228,229],"根据历史数据预测未来的收入、流量或价格","检测序列数据中的趋势、季节性和水平变化","比较不同的预测方法（ARIMA vs. Holt-Winters）","为规划和决策获取统计上合理的预测",[231,232,233,234],"用户或代理识别出时间序列预测的需求。","代理调用 `predict_forecast` 工具，提供历史数据、预测步数和方法。","技能使用 ARIMA 或 Holt-Winters 处理数据。","技能返回预测值和置信区间。",{"codeQuality":236,"collectedAt":238,"documentation":239,"maintenance":242,"security":248,"testCoverage":251},{"hasLockfile":237},true,1778698959303,{"descriptionLength":240,"readmeSize":241},177,9472,{"closedIssues90d":243,"forks":244,"hasChangelog":237,"manifestVersion":245,"openIssues90d":8,"pushedAt":246,"stars":247},44,2,"1.0.0",1777714123000,8,{"hasNpmPackage":249,"license":250,"smitheryVerified":249},false,"MIT",{"hasCi":237,"hasTests":237},{"updatedAt":253},1778699133476,{"basePath":255,"githubOwner":256,"githubRepo":257,"locale":18,"slug":258,"type":259},"mission-control/packages/clawhub-skills/oraclaw-forecast","Whatsonyourmind","oraclaw","oraclaw-forecast","skill",null,{"evaluate":262,"extract":265},{"promptVersionExtension":210,"promptVersionScoring":211,"score":214,"tags":263,"targetMarket":264,"tier":224},[217,218,219,220,221,222,223],"global",{"commitSha":266,"license":250},"HEAD",{"repoId":268,"translatedFrom":269},"kd76fmxm1ng903s4fmj0p7hxxs86ndkg","k17a19x757qjaehqa5jah8k7y986n55p",{"_creationTime":271,"_id":268,"identity":272,"providers":273,"workflow":433},1778698831609.0093,{"githubOwner":256,"githubRepo":257,"sourceUrl":14},{"classify":274,"discover":407,"github":410},{"commitSha":266,"extensions":275},[276,288,296,304,312,320,328,336,344,350,358,366,374,382,390],{"basePath":277,"description":278,"displayName":279,"installMethods":280,"rationale":281,"selectedPaths":282,"source":286,"sourceLanguage":287,"type":259},"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",[283],{"path":284,"priority":285},"SKILL.md","mandatory","rule","en",{"basePath":289,"description":290,"displayName":291,"installMethods":292,"rationale":293,"selectedPaths":294,"source":286,"sourceLanguage":287,"type":259},"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",[295],{"path":284,"priority":285},{"basePath":297,"description":298,"displayName":299,"installMethods":300,"rationale":301,"selectedPaths":302,"source":286,"sourceLanguage":287,"type":259},"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",[303],{"path":284,"priority":285},{"basePath":305,"description":306,"displayName":307,"installMethods":308,"rationale":309,"selectedPaths":310,"source":286,"sourceLanguage":287,"type":259},"mission-control/packages/clawhub-skills/oraclaw-calibrate","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.","oraclaw-calibrate",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-calibrate/SKILL.md",[311],{"path":284,"priority":285},{"basePath":313,"description":314,"displayName":315,"installMethods":316,"rationale":317,"selectedPaths":318,"source":286,"sourceLanguage":287,"type":259},"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",[319],{"path":284,"priority":285},{"basePath":321,"description":322,"displayName":323,"installMethods":324,"rationale":325,"selectedPaths":326,"source":286,"sourceLanguage":287,"type":259},"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",[327],{"path":284,"priority":285},{"basePath":329,"description":330,"displayName":331,"installMethods":332,"rationale":333,"selectedPaths":334,"source":286,"sourceLanguage":287,"type":259},"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",[335],{"path":284,"priority":285},{"basePath":337,"description":338,"displayName":339,"installMethods":340,"rationale":341,"selectedPaths":342,"source":286,"sourceLanguage":287,"type":259},"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",[343],{"path":284,"priority":285},{"basePath":255,"description":345,"displayName":258,"installMethods":346,"rationale":347,"selectedPaths":348,"source":286,"sourceLanguage":287,"type":259},"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.",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-forecast/SKILL.md",[349],{"path":284,"priority":285},{"basePath":351,"description":352,"displayName":353,"installMethods":354,"rationale":355,"selectedPaths":356,"source":286,"sourceLanguage":287,"type":259},"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",[357],{"path":284,"priority":285},{"basePath":359,"description":360,"displayName":361,"installMethods":362,"rationale":363,"selectedPaths":364,"source":286,"sourceLanguage":287,"type":259},"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",[365],{"path":284,"priority":285},{"basePath":367,"description":368,"displayName":369,"installMethods":370,"rationale":371,"selectedPaths":372,"source":286,"sourceLanguage":287,"type":259},"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",[373],{"path":284,"priority":285},{"basePath":375,"description":376,"displayName":377,"installMethods":378,"rationale":379,"selectedPaths":380,"source":286,"sourceLanguage":287,"type":259},"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",[381],{"path":284,"priority":285},{"basePath":383,"description":384,"displayName":385,"installMethods":386,"rationale":387,"selectedPaths":388,"source":286,"sourceLanguage":287,"type":259},"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",[389],{"path":284,"priority":285},{"basePath":391,"description":392,"displayName":393,"installMethods":394,"license":250,"rationale":395,"selectedPaths":396,"source":286,"sourceLanguage":287,"type":406},"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":393},"server.json with namespace/server name at mission-control/packages/mcp-server/server.json",[397,399,401,403],{"path":398,"priority":285},"server.json",{"path":400,"priority":285},"package.json",{"path":402,"priority":285},"README.md",{"path":404,"priority":405},"src/index.ts","low","mcp",{"sources":408},[409],"manual",{"closedIssues90d":243,"description":411,"forks":244,"homepage":412,"license":250,"openIssues90d":8,"pushedAt":246,"readmeSize":241,"stars":247,"topics":413},"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",[414,415,416,417,418,419,420,406,421,422,423,424,425,426,427,428,429,430,431,432],"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":434,"discoverAt":435,"extractAt":436,"githubAt":436,"updatedAt":434},1778698837409,1778698831609,1778698835357,[222,220,223,217,221,219,218],{"evaluatedAt":439,"extractAt":440,"updatedAt":253},1778698975269,1778698837670,[],[443,472,502,528,547,578],{"_creationTime":444,"_id":445,"community":446,"display":447,"identity":453,"providers":458,"relations":466,"tags":468,"workflow":469},1778691799740.4976,"k1719vgzsxtv8exr684y5ww47s86mzqh",{"reviewCount":8},{"description":448,"installMethods":449,"name":451,"sourceUrl":452},"Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.",{"claudeCode":450},"K-Dense-AI/claude-scientific-skills","TimesFM Forecasting","https://github.com/K-Dense-AI/claude-scientific-skills",{"basePath":454,"githubOwner":455,"githubRepo":456,"locale":287,"slug":457,"type":259},"scientific-skills/timesfm-forecasting","K-Dense-AI","claude-scientific-skills","timesfm-forecasting",{"evaluate":459,"extract":465},{"promptVersionExtension":210,"promptVersionScoring":211,"score":214,"tags":460,"targetMarket":264,"tier":224},[218,217,461,462,463,420,464],"univariate","foundation-model","timesfm","python",{"commitSha":266,"license":250},{"repoId":467},"kd79rphh5gexy91xmpxc05h5mh86mm9r",[217,462,420,464,218,463,461],{"evaluatedAt":470,"extractAt":471,"updatedAt":470},1778694590335,1778691799740,{"_creationTime":473,"_id":474,"community":475,"display":476,"identity":482,"providers":486,"relations":496,"tags":498,"workflow":499},1778675145461.8716,"k173knhqazsd87a0kmz3jp3tmn86nty4",{"reviewCount":8},{"description":477,"installMethods":478,"name":480,"sourceUrl":481},"Part of the AlterLab Academic Skills suite. This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.",{"claudeCode":479},"AlterLab-IEU/AlterLab-Academic-Skills","alterlab-aeon","https://github.com/AlterLab-IEU/AlterLab-Academic-Skills",{"basePath":483,"githubOwner":484,"githubRepo":485,"locale":287,"slug":480,"type":259},"skills/domain-specific/alterlab-aeon","AlterLab-IEU","AlterLab-Academic-Skills",{"evaluate":487,"extract":495},{"promptVersionExtension":210,"promptVersionScoring":211,"score":488,"tags":489,"targetMarket":264,"tier":224},98,[218,420,490,491,217,492,493,494],"classification","regression","anomaly-detection","clustering","scikit-learn",{"commitSha":266},{"repoId":497},"kd7fqvj70pvyn4r3q9kctpnd7d86mfqd",[492,490,493,217,420,491,494,218],{"evaluatedAt":500,"extractAt":501,"updatedAt":500},1778678143254,1778675145461,{"_creationTime":503,"_id":504,"community":505,"display":506,"identity":509,"providers":510,"relations":522,"tags":524,"workflow":525},1778699104170.7488,"k17b8k37k50x3v23661204y2w586mtkx",{"reviewCount":8},{"description":507,"installMethods":508,"name":307,"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},{"basePath":305,"githubOwner":256,"githubRepo":257,"locale":18,"slug":307,"type":259},{"evaluate":511,"extract":521},{"promptVersionExtension":210,"promptVersionScoring":211,"score":512,"tags":513,"targetMarket":264,"tier":224},97,[514,217,219,515,516,517,518,519,520],"calibration","accuracy","scoring","convergence","brier-score","statistics","analysis",{"commitSha":266},{"repoId":268,"translatedFrom":523},"k177gnp7tvr9phd9psfw21zgcs86ndx2",[515,520,518,514,517,217,219,516,519],{"evaluatedAt":526,"extractAt":440,"updatedAt":527},1778698906461,1778699104170,{"_creationTime":529,"_id":530,"community":531,"display":532,"identity":535,"providers":538,"relations":543,"tags":544,"workflow":545},1778675145461.859,"k17bkmbgyytbmdsdn8rfyyzwwd86n5h5",{"reviewCount":8},{"description":533,"installMethods":534,"name":451,"sourceUrl":481},"Part of the AlterLab Academic Skills suite. Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.",{"claudeCode":479},{"basePath":536,"githubOwner":484,"githubRepo":485,"locale":287,"slug":537,"type":259},"skills/data-science/alterlab-timesfm","alterlab-timesfm",{"evaluate":539,"extract":542},{"promptVersionExtension":210,"promptVersionScoring":211,"score":540,"tags":541,"targetMarket":264,"tier":224},96,[217,218,462,464,223],{"commitSha":266,"license":250},{"repoId":497},[223,217,462,464,218],{"evaluatedAt":546,"extractAt":501,"updatedAt":546},1778676882391,{"_creationTime":548,"_id":549,"community":550,"display":551,"identity":557,"providers":561,"relations":571,"tags":574,"workflow":575},1778695548458.3625,"k17d4591dpyfqfybnac81wp9y586nh7n",{"reviewCount":8},{"description":552,"installMethods":553,"name":555,"sourceUrl":556},"Forecast infrastructure and application metrics using Prophet or statsmodels for capacity planning, cost optimization, and proactive scaling. Visualize predictions in Grafana and set up alerts for projected resource exhaustion. Use when forecasting infrastructure capacity needs for CPU, memory, or disk, planning hardware procurement for next quarter, predicting cost trends to optimize cloud spending, or setting up proactive scaling policies based on predicted load.\n",{"claudeCode":554},"pjt222/agent-almanac","forecast-operational-metrics","https://github.com/pjt222/agent-almanac",{"basePath":558,"githubOwner":559,"githubRepo":560,"locale":287,"slug":555,"type":259},"skills/forecast-operational-metrics","pjt222","agent-almanac",{"evaluate":562,"extract":570},{"promptVersionExtension":210,"promptVersionScoring":211,"score":563,"tags":564,"targetMarket":264,"tier":224},95,[217,218,565,566,567,568,569],"prophet","statsmodels","capacity-planning","grafana","mlops",{"commitSha":266},{"parentExtensionId":572,"repoId":573},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[567,217,568,569,565,566,218],{"evaluatedAt":576,"extractAt":577,"updatedAt":576},1778698282903,1778695548458,{"_creationTime":579,"_id":580,"community":581,"display":582,"identity":586,"providers":589,"relations":595,"tags":596,"workflow":597},1778691799740.4673,"k178b4tn4gxjqbpqfzkces5qm186m0z3",{"reviewCount":8},{"description":583,"installMethods":584,"name":585,"sourceUrl":452},"This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.",{"claudeCode":450},"Aeon Time Series Machine Learning",{"basePath":587,"githubOwner":455,"githubRepo":456,"locale":287,"slug":588,"type":259},"scientific-skills/aeon","aeon",{"evaluate":590,"extract":593},{"promptVersionExtension":210,"promptVersionScoring":211,"score":563,"tags":591,"targetMarket":264,"tier":224},[218,420,217,490,491,464,592],"data-analysis",{"commitSha":266,"license":594},"BSD-3-Clause",{"repoId":467},[490,592,217,420,464,491,218],{"evaluatedAt":598,"extractAt":471,"updatedAt":598},1778691874025]