[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-Whatsonyourmind-oraclaw-forecast-de":3,"guides-for-Whatsonyourmind-oraclaw-forecast":440,"similar-k174n2mwmn4jp9gk557441fakn86n9w1-de":441},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":253,"isFallback":248,"parentExtension":259,"providers":260,"relations":266,"repo":269,"tags":436,"workflow":437},1778699134715.357,"k174n2mwmn4jp9gk557441fakn86n9w1",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Zeitreihenprognose für KI-Agenten. ARIMA- und Holt-Winters-Vorhersagen mit Konfidenzintervallen. Prognostizieren Sie Umsatz, Traffic, Preise oder beliebige sequentielle Daten. Inferenz unter 5 ms.",{"claudeCode":12},"Whatsonyourmind/oraclaw","OraClaw Forecast","https://github.com/Whatsonyourmind/oraclaw",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":234,"workflow":251},1778699134715.3572,"kn7dp2gjmzbt1hgnyf9jrk2sa186mz51","de",{"checks":20,"evaluatedAt":191,"extensionSummary":192,"features":193,"nonGoals":199,"practices":203,"prerequisites":207,"promptVersionExtension":209,"promptVersionScoring":210,"purpose":211,"rationale":212,"score":213,"summary":214,"tags":215,"tier":223,"useCases":224,"workflow":229},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,117,121,124,127,130,133,136,139,143,146,150,153,157,160,163,166,169,173,176,179,182,185,188],{"category":22,"check":23,"severity":24,"summary":25},"Praktischer Nutzen","Problemrelevanz","pass","Die Beschreibung gibt klar das Problem der Zeitreihenprognose für KI-Agenten an und nennt spezifische Datentypen wie Umsatz und Traffic.",{"category":22,"check":27,"severity":24,"summary":28},"Alleinstellungsmerkmal","Die Fähigkeit bietet mathematisch korrekte Algorithmen (ARIMA, Holt-Winters) für Prognosen, was über grundlegende LLM-Fähigkeiten hinausgeht und deterministische Antworten liefert.",{"category":22,"check":30,"severity":24,"summary":31},"Produktionsreife","Die Fähigkeit ist produktionsreif, mit einer klaren API, SDKs und MCP-Server-Integration, die den gesamten Prognoselebenszyklus abdeckt.",{"category":33,"check":34,"severity":24,"summary":35},"Umfang","Prinzip der einzigen Verantwortung","Die Fähigkeit konzentriert sich ausschließlich auf die Zeitreihenprognose, was ihrem Namen und ihrer Beschreibung entspricht.",{"category":33,"check":37,"severity":24,"summary":38},"Qualität der Beschreibung","Die angezeigte Beschreibung spiegelt die Fähigkeiten der Fähigkeit genau wider und ist prägnant.",{"category":40,"check":41,"severity":24,"summary":42},"Aufruf","Geltungsbereichbezogene Werkzeuge","Die Fähigkeit stellt ein einzelnes, klar definiertes Werkzeug (`predict_forecast`) für ihre Kernfunktionalität bereit.",{"category":44,"check":45,"severity":24,"summary":46},"Dokumentation","Konfigurations- & Parameterreferenz","Die SKILL.md dokumentiert klar das Werkzeug `predict_forecast` und seine Parameter, einschließlich Daten, Schritte, Methode und Saisonalitätslänge.",{"category":33,"check":48,"severity":24,"summary":49},"Werkzeugbenennung","Das einzelne Werkzeug `predict_forecast` ist beschreibend benannt und leicht verständlich.",{"category":33,"check":51,"severity":24,"summary":52},"Minimale I/O-Oberfläche","Die Eingabeparameter des Werkzeugs `predict_forecast` (`data`, `steps`, `method`, `seasonLength`) sind spezifisch und für die Prognose notwendig, und die Ausgabe ist klar als Prognosewerte mit Konfidenzintervallen definiert.",{"category":54,"check":55,"severity":24,"summary":56},"Lizenz","Lizenznutzbarkeit","Die Erweiterung wird unter der MIT-Lizenz vertrieben, die freizügig ist und in der LICENSE-Datei und im README klar deklariert ist.",{"category":58,"check":59,"severity":24,"summary":60},"Wartung","Aktualität der Commits","Der letzte Commit war am 2. Mai 2026, was innerhalb der letzten 3 Monate liegt.",{"category":58,"check":62,"severity":24,"summary":63},"Abhängigkeitsmanagement","Das Projekt hat eine Lock-Datei (`hasLockfile: true`) und scheint seine Abhängigkeiten effektiv zu verwalten, mit hoher Testabdeckung und CI.",{"category":65,"check":66,"severity":24,"summary":67},"Sicherheit","Geheimnisverwaltung","Der `ORACLAW_API_KEY` wird als Anforderung erwähnt, ist aber nicht hartcodiert oder in der Ausgabe verfügbar. Das README zeigt keine sensiblen Informationen, die protokolliert werden.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","Die Fähigkeit konzentriert sich auf die Verarbeitung numerischer Daten und Prognosealgorithmen, ohne Anzeichen für das Laden oder Ausführen von nicht vertrauenswürdigen Drittanbieterdaten als Anweisungen.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Lieferketten-Granaten","Die Fähigkeit scheint zur Laufzeit keine externen Codes oder Daten abzurufen. Alle notwendigen Algorithmen und Datenverarbeitung scheinen eigenständig zu sein oder sich auf den MCP-Server zu verlassen.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox-Isolation","Die Fähigkeit arbeitet mit bereitgestellten Daten und gibt Prognosen zurück; es gibt keine Hinweise darauf, dass sie versucht, Dateien außerhalb ihres beabsichtigten Geltungsbereichs zu ändern.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox-Escape-Primitive","In den bereitgestellten Code-Snippets oder Beschreibungen wurden keine separaten Prozessaufrufe oder Wiederholungsschleifen um verweigerte Werkzeugaufrufe herum erkannt.",{"category":65,"check":81,"severity":24,"summary":82},"Datenexfiltration","Die Fähigkeit verarbeitet numerische Daten für Prognosen und scheint keine vertraulichen Informationen zu verarbeiten oder zu exfiltrieren.",{"category":65,"check":84,"severity":24,"summary":85},"Versteckte Texttricks","Der bereitgestellte Inhalt von SKILL.md und README ist frei von versteckten Texttricks oder verdächtigen Unicode-Zeichen.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Undurchsichtige Codeausführung","Die Logik der Fähigkeit basiert auf klar definierten Algorithmen und Werkzeugen, ohne Anzeichen für verschleierten oder undurchsichtigen Code.",{"category":91,"check":92,"severity":24,"summary":93},"Portabilität","Strukturelle Annahme","Die Fähigkeit nimmt Daten als Eingabe entgegen und trifft keine Annahmen über die Dateistruktur des Benutzerprojekts.",{"category":95,"check":96,"severity":24,"summary":97},"Vertrauen","Aufmerksamkeit bei Issues","Mit 0 geöffneten und 44 geschlossenen Issues in den letzten 90 Tagen ist die Abschlussrate hoch, was auf aktive Wartung hinweist.",{"category":99,"check":100,"severity":24,"summary":101},"Versionierung","Release-Management","Das SKILL.md-Frontmatter deklariert Version 1.0.0, und das README zeigt Implementierungen und Updates, was auf gute Versionierungspraktiken hindeutet.",{"category":103,"check":104,"severity":24,"summary":105},"Codeausführung","Validierung","Das Werkzeugschema und die Regeln in SKILL.md definieren klare Eingabeanforderungen für Daten, Schritte und Methode, was auf Validierung hindeutet.",{"category":65,"check":107,"severity":24,"summary":108},"Ungeschützte destruktive Operationen","Die Fähigkeit ist rein analytisch und führt keine destruktiven Operationen durch.",{"category":110,"check":111,"severity":24,"summary":112},"Fehler","Fehlerbehandlung","SKILL.md beschreibt Regeln und Anforderungen (minimale Datenpunkte, Erweiterung des Konfidenzintervalls), was auf Fehlerbehandlung bei ungültigen Eingaben hindeutet.",{"category":103,"check":114,"severity":115,"summary":116},"Protokollierung","not_applicable","Die Fähigkeit ist in erster Linie ein Datenverarbeitungswerkzeug und führt keine destruktiven Aktionen oder ausgehenden Aufrufe durch, die normalerweise eine lokale Audit-Protokollierung erfordern würden.",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","DSGVO","Die Fähigkeit arbeitet mit numerischen Zeitreihendaten, die keine personenbezogenen Daten sind.",{"category":118,"check":122,"severity":24,"summary":123},"Zielmarkt","Die Prognosefähigkeiten der Erweiterung sind universell anwendbar und nicht an eine bestimmte geografische oder rechtliche Gerichtsbarkeit gebunden.",{"category":91,"check":125,"severity":24,"summary":126},"Laufzeitstabilität","Die Fähigkeit basiert auf Standardalgorithmen und Datenverarbeitung, ohne offensichtliche Annahmen über einen bestimmten Editor, eine Shell oder ein Betriebssystem.",{"category":44,"check":128,"severity":24,"summary":129},"README","Das README ist umfassend und beschreibt den Zweck, die Implementierungen und die Marktverteilung des Projekts.",{"category":33,"check":131,"severity":24,"summary":132},"Größe der Werkzeugoberfläche","Die Erweiterung stellt ein einziges Werkzeug, `predict_forecast`, bereit, was für ihre fokussierte Funktionalität angemessen ist.",{"category":40,"check":134,"severity":24,"summary":135},"Überlappende fast-synonyme Werkzeuge","Die Erweiterung stellt nur ein Werkzeug bereit, daher gibt es keine überlappenden fast-synonymen Werkzeuge.",{"category":44,"check":137,"severity":24,"summary":138},"Phantom-Funktionen","Alle beworbenen Funktionen, wie ARIMA- und Holt-Winters-Vorhersagen mit Konfidenzintervallen, werden direkt vom Werkzeug `predict_forecast` unterstützt.",{"category":140,"check":141,"severity":24,"summary":142},"Installation","Installationsanleitung","Installationsanweisungen werden für den MCP-Server, die REST-API und das npm-SDK bereitgestellt, zusammen mit klaren Aufrufbeispielen.",{"category":110,"check":144,"severity":24,"summary":145},"Handlungsfähige Fehlermeldungen","Das SKILL.md beschreibt Regeln für die Datenlänge und Saisonalität, was impliziert, dass Fehler bei Nichterfüllung der Bedingungen ausgelöst würden, und den Benutzer bei der Behebung anleitet.",{"category":147,"check":148,"severity":24,"summary":149},"Ausführung","Angepinnte Abhängigkeiten","Das Projekt verfügt über eine Lock-Datei (`hasLockfile: true`), was darauf hindeutet, dass Abhängigkeiten angepinnt sind.",{"category":33,"check":151,"severity":115,"summary":152},"Dry-Run-Vorschau","Die Fähigkeit ist rein analytisch und führt keine Zustandsänderungen oder ausgehenden Datenübertragungen durch.",{"category":154,"check":155,"severity":24,"summary":156},"Protokoll","Idempotente Wiederholung & Timeouts","Die Fähigkeit ist analytisch und beinhaltet keine Remote-Aufrufe oder zustandsverändernden Operationen, die Idempotenz oder Timeouts erfordern würden.",{"category":118,"check":158,"severity":24,"summary":159},"Telemetrie-Opt-in","Es gibt keine Anzeichen dafür, dass von dieser Fähigkeit Telemetrie gesammelt wird.",{"category":40,"check":161,"severity":24,"summary":162},"Präziser Zweck","Die Fähigkeit gibt klar ihren Zweck als Zeitreihenprognose mit ARIMA und Holt-Winters an, und ihre Anwendungsfälle umfassen die Vorhersage sequentieller Daten wie Umsatz und Traffic.",{"category":40,"check":164,"severity":24,"summary":165},"Prägnantes Frontmatter","Das Frontmatter ist prägnant und fasst die Kernkompetenz und die wichtigsten Funktionen der Fähigkeit effektiv zusammen.",{"category":44,"check":167,"severity":24,"summary":168},"Prägnanter Body","Das SKILL.md ist gut strukturiert und prägnant und beschreibt den Zweck, die Werkzeuge und die Regeln der Fähigkeit ohne unnötige Weitschweifigkeit.",{"category":170,"check":171,"severity":115,"summary":172},"Kontext","Progressive Offenlegung","Die Fähigkeit ist prägnant und beinhaltet keine langen Verfahren, die eine progressive Offenlegung über separate Referenzdateien erfordern würden.",{"category":170,"check":174,"severity":115,"summary":175},"Gegabelte Erkundung","Diese Fähigkeit ist ein fokussiertes Prognosewerkzeug und beinhaltet keine tiefgehende Erkundung oder Code-Überprüfung, die einen gegabelten Kontext erfordern würde.",{"category":22,"check":177,"severity":24,"summary":178},"Anwendungsbeispiele","Das SKILL.md liefert klare, direkt verwendbare Beispiele für die Methoden ARIMA und Holt-Winters, die Eingabe und erwartete Ausgabe demonstrieren.",{"category":22,"check":180,"severity":24,"summary":181},"Grenzfälle","Das SKILL.md dokumentiert Einschränkungen wie die erforderliche Mindestanzahl an Datenpunkten und die Erweiterung der Konfidenzintervalle für längere Prognosen und gibt damit implizite Hinweise auf Fehlerfälle.",{"category":103,"check":183,"severity":115,"summary":184},"Werkzeug-Fallback","Die Fähigkeit ist nicht auf einen externen MCP-Server angewiesen; ihre Funktionalität ist eigenständig oder wird über ihre eigene API/SDKs bereitgestellt.",{"category":65,"check":186,"severity":24,"summary":187},"Abbruch bei unerwartetem Zustand","Die Regeln für minimale Datenpunkte und Saisonalität definieren implizit Vorbedingungen, und die Einhaltung dieser Regeln würde bei unerwartetem Zustand wahrscheinlich den Prozess abbrechen.",{"category":91,"check":189,"severity":24,"summary":190},"Übergreifende Kopplung von Fähigkeiten","Die Fähigkeit ist in sich abgeschlossen und auf Prognosen fokussiert, ohne Anzeichen für eine implizite Abhängigkeit von anderen Fähigkeiten.",1778698975157,"Diese Fähigkeit bietet Zeitreihenprognosefunktionen unter Verwendung von ARIMA- und Holt-Winters-Methoden und gibt Vorhersagen mit Konfidenzintervallen aus. Sie kann über einen MCP-Server, eine REST-API oder ein npm-SDK abgerufen werden.",[194,195,196,197,198],"ARIMA-Zeitreihenprognose (automatische Anpassung)","Holt-Winters saisonale Prognose","95%-Konfidenzintervalle für Vorhersagen","Inferenz unter 5 ms über die API","Zugriff auf MCP-Server, REST-API und SDK",[200,201,202],"Durchführung komplexer statistischer Analysen über die Prognose hinaus","Verarbeitung nicht-sequentieller oder unstrukturierter Daten","Bereitstellung von Echtzeit-Vorhersagen mit geringer Latenz für Hochfrequenzhandel",[204,205,206],"Zeitreihenanalyse","Statistische Modellierung","Prognose",[208],"Umgebungsvariable ORACLAW_API_KEY (für Premium-Funktionen)","3.0.0","4.4.0","KI-Agenten mit präzisen, deterministischen Zeitreihenprognosefähigkeiten auszustatten und über heuristische Vorhersagen zu mathematisch fundierten Ergebnissen zu gelangen.","Alle Prüfungen bestanden, was auf eine qualitativ hochwertige, gut dokumentierte und produktionsreife Fähigkeit mit hervorragender Einhaltung von Best Practices hinweist.",100,"Eine qualitativ hochwertige, produktionsreife Fähigkeit für genaue Zeitreihenprognosen mit klarer Dokumentation und Beispielen.",[216,217,218,219,220,221,222],"forecasting","time-series","prediction","arima","holt-winters","analytics","data-science","verified",[225,226,227,228],"Vorhersage zukünftiger Umsätze, Traffic oder Preise aus historischen Daten","Erkennung von Trends, Saisonalität und Pegelverschiebungen in sequentiellen Daten","Vergleich verschiedener Prognoseansätze (ARIMA vs. Holt-Winters)","Erhalt statistisch fundierter Vorhersagen für Planung und Entscheidungsfindung",[230,231,232,233],"Benutzer oder Agent identifiziert den Bedarf an Zeitreihenvorhersagen.","Agent ruft das Werkzeug `predict_forecast` mit historischen Daten, Schritten und Methode auf.","Fähigkeit verarbeitet Daten mit ARIMA oder Holt-Winters.","Fähigkeit gibt Prognosewerte und Konfidenzintervalle zurück.",{"codeQuality":235,"collectedAt":237,"documentation":238,"maintenance":241,"security":247,"testCoverage":250},{"hasLockfile":236},true,1778698959303,{"descriptionLength":239,"readmeSize":240},177,9472,{"closedIssues90d":242,"forks":243,"hasChangelog":236,"manifestVersion":244,"openIssues90d":8,"pushedAt":245,"stars":246},44,2,"1.0.0",1777714123000,8,{"hasNpmPackage":248,"license":249,"smitheryVerified":248},false,"MIT",{"hasCi":236,"hasTests":236},{"updatedAt":252},1778699134715,{"basePath":254,"githubOwner":255,"githubRepo":256,"locale":18,"slug":257,"type":258},"mission-control/packages/clawhub-skills/oraclaw-forecast","Whatsonyourmind","oraclaw","oraclaw-forecast","skill",null,{"evaluate":261,"extract":264},{"promptVersionExtension":209,"promptVersionScoring":210,"score":213,"tags":262,"targetMarket":263,"tier":223},[216,217,218,219,220,221,222],"global",{"commitSha":265,"license":249},"HEAD",{"repoId":267,"translatedFrom":268},"kd76fmxm1ng903s4fmj0p7hxxs86ndkg","k17a19x757qjaehqa5jah8k7y986n55p",{"_creationTime":270,"_id":267,"identity":271,"providers":272,"workflow":432},1778698831609.0093,{"githubOwner":255,"githubRepo":256,"sourceUrl":14},{"classify":273,"discover":406,"github":409},{"commitSha":265,"extensions":274},[275,287,295,303,311,319,327,335,343,349,357,365,373,381,389],{"basePath":276,"description":277,"displayName":278,"installMethods":279,"rationale":280,"selectedPaths":281,"source":285,"sourceLanguage":286,"type":258},"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",[282],{"path":283,"priority":284},"SKILL.md","mandatory","rule","en",{"basePath":288,"description":289,"displayName":290,"installMethods":291,"rationale":292,"selectedPaths":293,"source":285,"sourceLanguage":286,"type":258},"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",[294],{"path":283,"priority":284},{"basePath":296,"description":297,"displayName":298,"installMethods":299,"rationale":300,"selectedPaths":301,"source":285,"sourceLanguage":286,"type":258},"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",[302],{"path":283,"priority":284},{"basePath":304,"description":305,"displayName":306,"installMethods":307,"rationale":308,"selectedPaths":309,"source":285,"sourceLanguage":286,"type":258},"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",[310],{"path":283,"priority":284},{"basePath":312,"description":313,"displayName":314,"installMethods":315,"rationale":316,"selectedPaths":317,"source":285,"sourceLanguage":286,"type":258},"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",[318],{"path":283,"priority":284},{"basePath":320,"description":321,"displayName":322,"installMethods":323,"rationale":324,"selectedPaths":325,"source":285,"sourceLanguage":286,"type":258},"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",[326],{"path":283,"priority":284},{"basePath":328,"description":329,"displayName":330,"installMethods":331,"rationale":332,"selectedPaths":333,"source":285,"sourceLanguage":286,"type":258},"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",[334],{"path":283,"priority":284},{"basePath":336,"description":337,"displayName":338,"installMethods":339,"rationale":340,"selectedPaths":341,"source":285,"sourceLanguage":286,"type":258},"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",[342],{"path":283,"priority":284},{"basePath":254,"description":344,"displayName":257,"installMethods":345,"rationale":346,"selectedPaths":347,"source":285,"sourceLanguage":286,"type":258},"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",[348],{"path":283,"priority":284},{"basePath":350,"description":351,"displayName":352,"installMethods":353,"rationale":354,"selectedPaths":355,"source":285,"sourceLanguage":286,"type":258},"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",[356],{"path":283,"priority":284},{"basePath":358,"description":359,"displayName":360,"installMethods":361,"rationale":362,"selectedPaths":363,"source":285,"sourceLanguage":286,"type":258},"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",[364],{"path":283,"priority":284},{"basePath":366,"description":367,"displayName":368,"installMethods":369,"rationale":370,"selectedPaths":371,"source":285,"sourceLanguage":286,"type":258},"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",[372],{"path":283,"priority":284},{"basePath":374,"description":375,"displayName":376,"installMethods":377,"rationale":378,"selectedPaths":379,"source":285,"sourceLanguage":286,"type":258},"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",[380],{"path":283,"priority":284},{"basePath":382,"description":383,"displayName":384,"installMethods":385,"rationale":386,"selectedPaths":387,"source":285,"sourceLanguage":286,"type":258},"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",[388],{"path":283,"priority":284},{"basePath":390,"description":391,"displayName":392,"installMethods":393,"license":249,"rationale":394,"selectedPaths":395,"source":285,"sourceLanguage":286,"type":405},"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":392},"server.json with namespace/server name at mission-control/packages/mcp-server/server.json",[396,398,400,402],{"path":397,"priority":284},"server.json",{"path":399,"priority":284},"package.json",{"path":401,"priority":284},"README.md",{"path":403,"priority":404},"src/index.ts","low","mcp",{"sources":407},[408],"manual",{"closedIssues90d":242,"description":410,"forks":243,"homepage":411,"license":249,"openIssues90d":8,"pushedAt":245,"readmeSize":240,"stars":246,"topics":412},"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",[413,414,415,416,417,418,419,405,420,421,422,423,424,425,426,427,428,429,430,431],"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":433,"discoverAt":434,"extractAt":435,"githubAt":435,"updatedAt":433},1778698837409,1778698831609,1778698835357,[221,219,222,216,220,218,217],{"evaluatedAt":438,"extractAt":439,"updatedAt":252},1778698975269,1778698837670,[],[442,471,501,527,546,577],{"_creationTime":443,"_id":444,"community":445,"display":446,"identity":452,"providers":457,"relations":465,"tags":467,"workflow":468},1778691799740.4976,"k1719vgzsxtv8exr684y5ww47s86mzqh",{"reviewCount":8},{"description":447,"installMethods":448,"name":450,"sourceUrl":451},"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":449},"K-Dense-AI/claude-scientific-skills","TimesFM Forecasting","https://github.com/K-Dense-AI/claude-scientific-skills",{"basePath":453,"githubOwner":454,"githubRepo":455,"locale":286,"slug":456,"type":258},"scientific-skills/timesfm-forecasting","K-Dense-AI","claude-scientific-skills","timesfm-forecasting",{"evaluate":458,"extract":464},{"promptVersionExtension":209,"promptVersionScoring":210,"score":213,"tags":459,"targetMarket":263,"tier":223},[217,216,460,461,462,419,463],"univariate","foundation-model","timesfm","python",{"commitSha":265,"license":249},{"repoId":466},"kd79rphh5gexy91xmpxc05h5mh86mm9r",[216,461,419,463,217,462,460],{"evaluatedAt":469,"extractAt":470,"updatedAt":469},1778694590335,1778691799740,{"_creationTime":472,"_id":473,"community":474,"display":475,"identity":481,"providers":485,"relations":495,"tags":497,"workflow":498},1778675145461.8716,"k173knhqazsd87a0kmz3jp3tmn86nty4",{"reviewCount":8},{"description":476,"installMethods":477,"name":479,"sourceUrl":480},"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":478},"AlterLab-IEU/AlterLab-Academic-Skills","alterlab-aeon","https://github.com/AlterLab-IEU/AlterLab-Academic-Skills",{"basePath":482,"githubOwner":483,"githubRepo":484,"locale":286,"slug":479,"type":258},"skills/domain-specific/alterlab-aeon","AlterLab-IEU","AlterLab-Academic-Skills",{"evaluate":486,"extract":494},{"promptVersionExtension":209,"promptVersionScoring":210,"score":487,"tags":488,"targetMarket":263,"tier":223},98,[217,419,489,490,216,491,492,493],"classification","regression","anomaly-detection","clustering","scikit-learn",{"commitSha":265},{"repoId":496},"kd7fqvj70pvyn4r3q9kctpnd7d86mfqd",[491,489,492,216,419,490,493,217],{"evaluatedAt":499,"extractAt":500,"updatedAt":499},1778678143254,1778675145461,{"_creationTime":502,"_id":503,"community":504,"display":505,"identity":508,"providers":509,"relations":521,"tags":523,"workflow":524},1778699103065.3374,"k17ewgytf02f6ehg37exgsxh7h86n9nc",{"reviewCount":8},{"description":506,"installMethods":507,"name":306,"sourceUrl":14},"Bewertung der Vorhersagequalität für KI-Agenten. Brier-Score, Log-Score und Konvergenzanalyse mehrerer Quellen. Wissen Sie, ob Ihre Prognosen korrekt sind und ob Ihre Datenquellen übereinstimmen.",{"claudeCode":12},{"basePath":304,"githubOwner":255,"githubRepo":256,"locale":18,"slug":306,"type":258},{"evaluate":510,"extract":520},{"promptVersionExtension":209,"promptVersionScoring":210,"score":511,"tags":512,"targetMarket":263,"tier":223},97,[513,216,218,514,515,516,517,518,519],"calibration","accuracy","scoring","convergence","brier-score","statistics","analysis",{"commitSha":265},{"repoId":267,"translatedFrom":522},"k177gnp7tvr9phd9psfw21zgcs86ndx2",[514,519,517,513,516,216,218,515,518],{"evaluatedAt":525,"extractAt":439,"updatedAt":526},1778698906461,1778699103065,{"_creationTime":528,"_id":529,"community":530,"display":531,"identity":534,"providers":537,"relations":542,"tags":543,"workflow":544},1778675145461.859,"k17bkmbgyytbmdsdn8rfyyzwwd86n5h5",{"reviewCount":8},{"description":532,"installMethods":533,"name":450,"sourceUrl":480},"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":478},{"basePath":535,"githubOwner":483,"githubRepo":484,"locale":286,"slug":536,"type":258},"skills/data-science/alterlab-timesfm","alterlab-timesfm",{"evaluate":538,"extract":541},{"promptVersionExtension":209,"promptVersionScoring":210,"score":539,"tags":540,"targetMarket":263,"tier":223},96,[216,217,461,463,222],{"commitSha":265,"license":249},{"repoId":496},[222,216,461,463,217],{"evaluatedAt":545,"extractAt":500,"updatedAt":545},1778676882391,{"_creationTime":547,"_id":548,"community":549,"display":550,"identity":556,"providers":560,"relations":570,"tags":573,"workflow":574},1778695548458.3625,"k17d4591dpyfqfybnac81wp9y586nh7n",{"reviewCount":8},{"description":551,"installMethods":552,"name":554,"sourceUrl":555},"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":553},"pjt222/agent-almanac","forecast-operational-metrics","https://github.com/pjt222/agent-almanac",{"basePath":557,"githubOwner":558,"githubRepo":559,"locale":286,"slug":554,"type":258},"skills/forecast-operational-metrics","pjt222","agent-almanac",{"evaluate":561,"extract":569},{"promptVersionExtension":209,"promptVersionScoring":210,"score":562,"tags":563,"targetMarket":263,"tier":223},95,[216,217,564,565,566,567,568],"prophet","statsmodels","capacity-planning","grafana","mlops",{"commitSha":265},{"parentExtensionId":571,"repoId":572},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[566,216,567,568,564,565,217],{"evaluatedAt":575,"extractAt":576,"updatedAt":575},1778698282903,1778695548458,{"_creationTime":578,"_id":579,"community":580,"display":581,"identity":585,"providers":588,"relations":594,"tags":595,"workflow":596},1778691799740.4673,"k178b4tn4gxjqbpqfzkces5qm186m0z3",{"reviewCount":8},{"description":582,"installMethods":583,"name":584,"sourceUrl":451},"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":449},"Aeon Time Series Machine Learning",{"basePath":586,"githubOwner":454,"githubRepo":455,"locale":286,"slug":587,"type":258},"scientific-skills/aeon","aeon",{"evaluate":589,"extract":592},{"promptVersionExtension":209,"promptVersionScoring":210,"score":562,"tags":590,"targetMarket":263,"tier":223},[217,419,216,489,490,463,591],"data-analysis",{"commitSha":265,"license":593},"BSD-3-Clause",{"repoId":466},[489,591,216,419,463,490,217],{"evaluatedAt":597,"extractAt":470,"updatedAt":597},1778691874025]