[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-Whatsonyourmind-oraclaw-decide-de":3,"guides-for-Whatsonyourmind-oraclaw-decide":428,"similar-k179cjry8epfbq0h2sfwnag5p586m3zy-de":429},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":243,"isFallback":238,"parentExtension":248,"providers":249,"relations":255,"repo":258,"tags":424,"workflow":425},1778699112432.148,"k179cjry8epfbq0h2sfwnag5p586m3zy",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Entscheidungsintelligenz für KI-Agenten. Analysieren Sie Optionen, bilden Sie Entscheidungsabhängigkeiten mit PageRank ab, erkennen Sie Konflikte zwischen Informationsquellen und finden Sie die wichtigsten Entscheidungen.",{"claudeCode":12},"Whatsonyourmind/oraclaw","oraclaw-decide","https://github.com/Whatsonyourmind/oraclaw",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":224,"workflow":241},1778699112432.1482,"kn75zqxm4r77zstkpms572hcnd86m7vj","de",{"checks":20,"evaluatedAt":194,"extensionSummary":195,"features":196,"nonGoals":202,"promptVersionExtension":206,"promptVersionScoring":207,"purpose":208,"rationale":209,"score":210,"summary":211,"tags":212,"tier":218,"useCases":219},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,117,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,188,191],{"category":22,"check":23,"severity":24,"summary":25},"Praktischer Nutzen","Relevanz des Problems","pass","Die Beschreibung gibt das Problem der Entscheidungsintelligenz für KI-Agenten klar an, einschließlich spezifischer Aufgaben wie der Analyse von Optionen, der Abbildung von Abhängigkeiten und der Erkennung von Konflikten.",{"category":22,"check":27,"severity":24,"summary":28},"Alleinstellungsmerkmal","Das Skill bietet deterministische Optimierungs-, Simulations- und Analysetools (Banditen, PageRank, Konvergenzbewertung), die über die Standardfähigkeiten von LLMs für mathematische Aufgaben hinausgehen.",{"category":22,"check":30,"severity":24,"summary":31},"Produktionsreife","Das Skill bietet einen umfassenden Satz von Werkzeugen zur Entscheidungsanalyse mit klarer Dokumentation und Beispielen, was auf eine Bereitschaft für reale Arbeitsabläufe hindeutet.",{"category":33,"check":34,"severity":24,"summary":35},"Umfang","Prinzip der einzigen Verantwortung","Das Skill konzentriert sich auf Entscheidungsintelligenz und verwandte Analysetools und behält eine kohärente Domäne ohne zusammenhanglose Fähigkeiten bei.",{"category":33,"check":37,"severity":24,"summary":38},"Qualität der Beschreibung","Die angezeigte Beschreibung spiegelt die Fähigkeiten des Skills für Entscheidungsintelligenz, Analyse und die Ermittlung wichtiger Entscheidungen genau wider.",{"category":40,"check":41,"severity":24,"summary":42},"Aufruf","Geltungsbereich von Werkzeugen","Werkzeuge sind eng gefasste Verb-Nomen-Spezialisten (z.B. optimize_bandit, analyze_decision_graph) und keine allgemeinen Ausführungsbefehle.",{"category":44,"check":45,"severity":24,"summary":46},"Dokumentation","Konfigurations- und Parameterreferenz","Die SKILL.md bietet eine klare Dokumentation für Werkzeuge, einschließlich Parametern für die Graphanalyse und Voraussetzungen wie ORACLAW_API_KEY.",{"category":33,"check":48,"severity":24,"summary":49},"Tool-Namensgebung","Toolnamen wie `optimize_bandit` und `analyze_decision_graph` sind beschreibend und entsprechen der Verb-Nomen-Konvention.",{"category":33,"check":51,"severity":24,"summary":52},"Minimale I/O-Oberfläche","Die Eingabeschemata für Tools wie `analyze_decision_graph` sind gut definiert und fordern nur die notwendigen Daten an, mit strukturierten Ausgaben.",{"category":54,"check":55,"severity":24,"summary":56},"Lizenz","Lizenznutzbarkeit","Die Erweiterung wird unter der MIT-Lizenz vertrieben, die in der README- und LICENSE-Datei klar angegeben 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 90 Tage liegt und eine aktive Wartung anzeigt.",{"category":58,"check":62,"severity":24,"summary":63},"Abhängigkeitsverwaltung","Das Projekt verwendet npm und listet seine SDK-Pakete auf, was auf Standardpraktiken für die Abhängigkeitsverwaltung hindeutet, und verfügt über eine Lock-Datei.",{"category":65,"check":66,"severity":24,"summary":67},"Sicherheit","Geheimnisverwaltung","Das Skill benötigt einen ORACLAW_API_KEY, der als Umgebungsvariable dokumentiert ist, und es gibt keine Hinweise darauf, dass Geheimnisse ausgegeben werden.",{"category":65,"check":69,"severity":24,"summary":70},"Injektion","Die Erweiterung verarbeitet Daten als Eingabe für Algorithmen. Es gibt keine Hinweise auf die Ausführung von nicht vertrauenswürdigem Code oder Anweisungen aus externen Daten.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Lieferketten-Granaten","Der gesamte Code und die Abhängigkeiten scheinen im Repository gespeichert zu sein, ohne Laufzeitabruf von externem Code oder Anweisungen.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox-Isolation","Die Werkzeuge arbeiten mit Dateneingaben und liefern strukturierte Ausgaben, ohne Hinweise auf die Änderung von Dateien außerhalb des vorgesehenen Umfangs.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox-Escape-Primitive","Es gibt keine Hinweise auf getrennte Prozesse oder Wiederholungsversuche bei abgelehnten Tool-Aufrufen in der bereitgestellten Quelle.",{"category":65,"check":81,"severity":24,"summary":82},"Datenexfiltration","Die Erweiterung verarbeitet analytische Daten und übermittelt keine vertraulichen Benutzerdaten an Dritte. Ausgehende Aufrufe erfolgen an dokumentierte Dienste wie Render.",{"category":65,"check":84,"severity":24,"summary":85},"Versteckte Texttricks","Die gebündelten Inhalte und Beschreibungen enthalten keine versteckten Steuerungs-Tricks, Steuerzeichen oder ungewöhnliche Unicode-Zeichen.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Undurchsichtige Codeausführung","Der Code scheint einfacher JavaScript/TypeScript-Code ohne Verschleierung, Base64-Payloads oder Laufzeit-Skriptabrufe zu sein.",{"category":91,"check":92,"severity":24,"summary":93},"Portabilität","Strukturelle Annahme","Das Skill definiert eigene Tools und stützt sich auf Standard-Umgebungsvariablen, nicht auf spezifische Projektverzeichnisstrukturen.",{"category":95,"check":96,"severity":24,"summary":97},"Vertrauen","Aufmerksamkeit für Probleme","Mit 0 geöffneten und 44 geschlossenen Problemen in den letzten 90 Tagen haben die Maintainer eine hohe Abschlussrate und verwalten Probleme aktiv.",{"category":99,"check":100,"severity":24,"summary":101},"Versionierung","Release-Management","Eine aussagekräftige `version: 1.0.0` ist im SKILL.md-Frontmatter deklariert und eine CHANGELOG.md ist vorhanden.",{"category":103,"check":104,"severity":24,"summary":105},"Ausführung","Validierung","Die Tools erwarten strukturierte Eingaben (JSON) und geben strukturierte Ausgaben zurück, was auf interne Validierung und Bereinigung hindeutet.",{"category":65,"check":107,"severity":24,"summary":108},"Ungeschützte destruktive Operationen","Das Skill ist analytisch und schreibgeschützt und führt keine destruktiven Operationen durch.",{"category":110,"check":111,"severity":24,"summary":112},"Code-Ausführung","Fehlerbehandlung","Die Tools sind darauf ausgelegt, strukturierte JSON-Daten zurückzugeben, was eine robuste Fehlerbehandlung mit klaren Codes und Meldungen impliziert.",{"category":110,"check":114,"severity":115,"summary":116},"Protokollierung","not_applicable","Das Skill fungiert als API und MCP-Server, wobei die Protokollierung vom aufrufenden Agenten oder der Serverinfrastruktur gehandhabt wird und nicht innerhalb des Skill-Bundles selbst.",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","DSGVO","Das Skill führt mathematische Analysen der bereitgestellten Daten durch und verarbeitet oder übermittelt keine personenbezogenen Daten.",{"category":118,"check":122,"severity":24,"summary":123},"Zielmarkt","Die Erweiterung verwendet Standardalgorithmen und Datenformate, es wurden keine regionalen Einschränkungen festgestellt; targetMarket ist global.",{"category":91,"check":125,"severity":24,"summary":126},"Laufzeitstabilität","Das Skill stützt sich auf Standard-Web-APIs und Umgebungsvariablen, was es portabel für verschiedene Laufzeitumgebungen macht.",{"category":44,"check":128,"severity":24,"summary":129},"README","Die README ist umfassend und beschreibt den Zweck des Projekts, die Implementierungen und den Einstieg.",{"category":33,"check":131,"severity":24,"summary":132},"Tool-Oberflächengröße","Das Skill stellt 3 Kern-Tools in SKILL.md und einen Katalog von 17 MCP-Tools bereit, was eine angemessene Anzahl ist.",{"category":40,"check":134,"severity":24,"summary":135},"Sich überschneidende Nahe-Synonym-Tools","Die bereitgestellten Tools decken unterschiedliche Funktionalitäten ab (optimize_bandit, analyze_decision_graph, score_convergence) ohne signifikante Überschneidungen.",{"category":44,"check":137,"severity":24,"summary":138},"Phantom-Funktionen","Alle beworbenen Funktionen, einschließlich der MCP-Tools und des API-Zugangs, haben entsprechende Implementierungen und Dokumentationen.",{"category":140,"check":141,"severity":24,"summary":142},"Installation","Installationsanleitung","Klare Anweisungen sind für die Einrichtung des MCP-Servers, der REST-API und des npm-SDKs enthalten, einschließlich Beispielaufrufen.",{"category":144,"check":145,"severity":24,"summary":146},"Fehler","Handlungsfähige Fehlermeldungen","Die Tools geben strukturierte JSON-Daten zurück, was impliziert, dass Fehler mit Codes und möglicherweise Hinweisen zur Behebung kategorisiert werden.",{"category":103,"check":148,"severity":24,"summary":149},"Angepinnte Abhängigkeiten","Das Projekt verfügt über eine Lock-Datei (`hasLockfile: true`) und listet spezifische SDK-Pakete auf, was auf angepinnte Abhängigkeiten hindeutet.",{"category":33,"check":151,"severity":115,"summary":152},"Dry-Run-Vorschau","Das Skill ist analytisch und führt keine zustandsändernden Operationen oder ausgehenden Datenversendungen durch, die einen Dry-Run-Modus erfordern würden.",{"category":154,"check":155,"severity":24,"summary":156},"Protokoll","Idempotente Wiederholung & Timeouts","Die Tools sind für zustandslose API-Aufrufe konzipiert, was bedeutet, dass sie idempotent sind und Timeouts auf API-Ebene implementiert haben sollten.",{"category":118,"check":158,"severity":24,"summary":159},"Telemetrie-Opt-in","Die Erweiterung sendet anscheinend keine Telemetriedaten. Wenn sie es tun würde, wäre die Opt-in-Natur durch das Fehlen jeglicher Erwähnung von Opt-out-Telemetrie impliziert.",{"category":40,"check":161,"severity":24,"summary":162},"Präziser Zweck","Die SKILL.md definiert klar den Zweck als Entscheidungsintelligenz für KI-Agenten und listet spezifische Anwendungsfälle und Tools auf.",{"category":40,"check":164,"severity":24,"summary":165},"Prägnantes Frontmatter","Das Frontmatter ist prägnant und in sich abgeschlossen und bietet eine klare Zusammenfassung der Kernfunktionalität und auslösenden Phrasen.",{"category":44,"check":167,"severity":24,"summary":168},"Prägnanter Body","Die SKILL.md ist einigermaßen prägnant und lagert umfangreiches Material an die README und andere verlinkte Ressourcen aus.",{"category":170,"check":171,"severity":24,"summary":172},"Kontext","Progressive Offenlegung","Die SKILL.md beschreibt Verfahren und verlinkt zu externen Ressourcen wie der README für detailliertere Informationen, anstatt alle Inhalte einzubetten.",{"category":170,"check":174,"severity":115,"summary":175},"Forked Exploration","Dieses Skill ist nicht für tiefgreifende Erkundungen oder Code-Reviews konzipiert, die einen veränderten Kontext erfordern würden; es verarbeitet spezifische Eingaben zur Analyse.",{"category":22,"check":177,"severity":24,"summary":178},"Anwendungsbeispiele","Die SKILL.md und die README bieten klare, einsatzbereite Beispiele für Graphanalysen und API-Aufrufe, die beobachtbare Ergebnisse demonstrieren.",{"category":22,"check":180,"severity":24,"summary":181},"Randfälle","Die SKILL.md beschreibt Regeln für Graphanalyse-Eingaben und gibt Hinweise zur Datenqualität für die Konvergenzbewertung, wodurch potenzielle Fehlerfälle angesprochen werden.",{"category":110,"check":183,"severity":115,"summary":184},"Tool-Fallback","Das Skill stellt hauptsächlich seine eigenen Tools und einen MCP-Server bereit, ohne implizite Abhängigkeit von anderen Skills, die Fallbacks erfordern würden.",{"category":91,"check":186,"severity":24,"summary":187},"Stack-Annahmen","Das Skill stützt sich auf Standard-Webtechnologien (REST-API, npm SDK) und Umgebungsvariablen ohne spezifische Betriebssystem- oder Sprachlaufzeitannahmen.",{"category":65,"check":189,"severity":24,"summary":190},"Halt bei unerwartetem Zustand","Das Skill erfordert spezifische Eingabeformate für seine Analysetools, was impliziert, dass es bei unerwarteten oder fehlerhaften Zuständen mit einem Fehler abbricht.",{"category":91,"check":192,"severity":24,"summary":193},"Cross-Skill-Kopplung","Die Fähigkeiten des Skills sind in sich abgeschlossen und stützen sich nicht auf andere spezifische, gleichzeitig geladene Skills.",1778698934020,"Dieses Skill bietet deterministische mathematische und analytische Werkzeuge für KI-Agenten, einschließlich Optimierungsalgorithmen (Banditen, genetische Algorithmen), Graphanalyse (PageRank, Engpässe), Konvergenzbewertung und Prognosen. Es kann über einen MCP-Server, eine REST-API oder ein npm SDK abgerufen werden.",[197,198,199,200,201],"Optionen mit Banditen und genetischen Algorithmen analysieren","Entscheidungsabhängigkeiten abbilden und Engpässe finden","Übereinstimmung und Konflikte von Informationsquellen erkennen","Entscheidungsbeeinflussung mit PageRank berechnen","API- und SDK-Zugriff auf fortgeschrittene Algorithmen bereitstellen",[203,204,205],"Durchführung allgemeiner LLM-Argumentation oder Textgenerierung","Ersetzen von Kernfähigkeiten zur Konversation von KI-Agenten","Bereitstellung subjektiver oder heuristikbasierter Entscheidungsunterstützung","3.0.0","4.4.0","KI-Agenten mit deterministischen, mathematisch fundierten Entscheidungs- und Analysefähigkeiten auszustatten, die über LLM-Heuristiken hinausgehen.","Alle Prüfungen wurden mit hoher Priorität bestanden, was auf ein gut dokumentiertes, sicheres und robustes Skill hindeutet.",100,"Ein qualitativ hochwertiges Skill mit fortgeschrittenen Werkzeugen zur Entscheidungsintelligenz für KI-Agenten.",[213,214,215,216,217],"decision-making","analysis","optimization","graph-theory","ai-agent-tools","verified",[220,221,222,223],"Die beste Option aus konkurrierenden Alternativen auswählen","Abhängigkeiten zwischen Entscheidungen abbilden und Engpässe finden","Prüfen, ob mehrere Informationsquellen übereinstimmen oder widersprüchlich sind","Identifizieren, welche Entscheidungen den größten Ripple-Effekt haben",{"codeQuality":225,"collectedAt":227,"documentation":228,"maintenance":231,"security":237,"testCoverage":240},{"hasLockfile":226},true,1778698921380,{"descriptionLength":229,"readmeSize":230},175,9472,{"closedIssues90d":232,"forks":233,"hasChangelog":226,"manifestVersion":234,"openIssues90d":8,"pushedAt":235,"stars":236},44,2,"1.0.0",1777714123000,8,{"hasNpmPackage":238,"license":239,"smitheryVerified":238},false,"MIT",{"hasCi":226,"hasTests":226},{"updatedAt":242},1778699112432,{"basePath":244,"githubOwner":245,"githubRepo":246,"locale":18,"slug":13,"type":247},"mission-control/packages/clawhub-skills/oraclaw-decide","Whatsonyourmind","oraclaw","skill",null,{"evaluate":250,"extract":253},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":251,"targetMarket":252,"tier":218},[213,214,215,216,217],"global",{"commitSha":254},"HEAD",{"repoId":256,"translatedFrom":257},"kd76fmxm1ng903s4fmj0p7hxxs86ndkg","k17fe7ybjme5s1n10mmg3emmns86nr26",{"_creationTime":259,"_id":256,"identity":260,"providers":261,"workflow":420},1778698831609.0093,{"githubOwner":245,"githubRepo":246,"sourceUrl":14},{"classify":262,"discover":395,"github":398},{"commitSha":254,"extensions":263},[264,276,284,292,300,308,314,322,330,338,346,354,362,370,378],{"basePath":265,"description":266,"displayName":267,"installMethods":268,"rationale":269,"selectedPaths":270,"source":274,"sourceLanguage":275,"type":247},"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",[271],{"path":272,"priority":273},"SKILL.md","mandatory","rule","en",{"basePath":277,"description":278,"displayName":279,"installMethods":280,"rationale":281,"selectedPaths":282,"source":274,"sourceLanguage":275,"type":247},"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",[283],{"path":272,"priority":273},{"basePath":285,"description":286,"displayName":287,"installMethods":288,"rationale":289,"selectedPaths":290,"source":274,"sourceLanguage":275,"type":247},"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",[291],{"path":272,"priority":273},{"basePath":293,"description":294,"displayName":295,"installMethods":296,"rationale":297,"selectedPaths":298,"source":274,"sourceLanguage":275,"type":247},"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",[299],{"path":272,"priority":273},{"basePath":301,"description":302,"displayName":303,"installMethods":304,"rationale":305,"selectedPaths":306,"source":274,"sourceLanguage":275,"type":247},"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":272,"priority":273},{"basePath":244,"description":309,"displayName":13,"installMethods":310,"rationale":311,"selectedPaths":312,"source":274,"sourceLanguage":275,"type":247},"Decision intelligence for AI agents. Analyze options, map decision dependencies with PageRank, detect when information sources conflict, and find the choices that matter most.",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-decide/SKILL.md",[313],{"path":272,"priority":273},{"basePath":315,"description":316,"displayName":317,"installMethods":318,"rationale":319,"selectedPaths":320,"source":274,"sourceLanguage":275,"type":247},"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",[321],{"path":272,"priority":273},{"basePath":323,"description":324,"displayName":325,"installMethods":326,"rationale":327,"selectedPaths":328,"source":274,"sourceLanguage":275,"type":247},"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",[329],{"path":272,"priority":273},{"basePath":331,"description":332,"displayName":333,"installMethods":334,"rationale":335,"selectedPaths":336,"source":274,"sourceLanguage":275,"type":247},"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",[337],{"path":272,"priority":273},{"basePath":339,"description":340,"displayName":341,"installMethods":342,"rationale":343,"selectedPaths":344,"source":274,"sourceLanguage":275,"type":247},"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",[345],{"path":272,"priority":273},{"basePath":347,"description":348,"displayName":349,"installMethods":350,"rationale":351,"selectedPaths":352,"source":274,"sourceLanguage":275,"type":247},"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",[353],{"path":272,"priority":273},{"basePath":355,"description":356,"displayName":357,"installMethods":358,"rationale":359,"selectedPaths":360,"source":274,"sourceLanguage":275,"type":247},"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",[361],{"path":272,"priority":273},{"basePath":363,"description":364,"displayName":365,"installMethods":366,"rationale":367,"selectedPaths":368,"source":274,"sourceLanguage":275,"type":247},"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",[369],{"path":272,"priority":273},{"basePath":371,"description":372,"displayName":373,"installMethods":374,"rationale":375,"selectedPaths":376,"source":274,"sourceLanguage":275,"type":247},"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",[377],{"path":272,"priority":273},{"basePath":379,"description":380,"displayName":381,"installMethods":382,"license":239,"rationale":383,"selectedPaths":384,"source":274,"sourceLanguage":275,"type":394},"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":381},"server.json with namespace/server name at mission-control/packages/mcp-server/server.json",[385,387,389,391],{"path":386,"priority":273},"server.json",{"path":388,"priority":273},"package.json",{"path":390,"priority":273},"README.md",{"path":392,"priority":393},"src/index.ts","low","mcp",{"sources":396},[397],"manual",{"closedIssues90d":232,"description":399,"forks":233,"homepage":400,"license":239,"openIssues90d":8,"pushedAt":235,"readmeSize":230,"stars":236,"topics":401},"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",[402,403,404,405,406,407,408,394,215,409,410,411,412,413,414,415,416,417,418,419],"ai-agents","algorithms","api","bandits","decision-intelligence","fastify","machine-learning","typescript","agent-tools","anthropic","claude-mcp","contextual-bandit","deterministic-tools","linear-programming","llm-tools","model-context-protocol","monte-carlo","pagerank",{"classifiedAt":421,"discoverAt":422,"extractAt":423,"githubAt":423,"updatedAt":421},1778698837409,1778698831609,1778698835357,[217,214,213,216,215],{"evaluatedAt":426,"extractAt":427,"updatedAt":242},1778698934136,1778698837670,[],[430,459,488,516,546,577],{"_creationTime":431,"_id":432,"community":433,"display":434,"identity":440,"providers":445,"relations":453,"tags":455,"workflow":456},1778696691708.3035,"k17br1j5s86ae90zqeyd7zcg2586mkwr",{"reviewCount":8},{"description":435,"installMethods":436,"name":438,"sourceUrl":439},"Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms\n",{"claudeCode":437},"ruvnet/ruflo","Performance Analysis","https://github.com/ruvnet/ruflo",{"basePath":441,"githubOwner":442,"githubRepo":443,"locale":275,"slug":444,"type":247},".claude/skills/performance-analysis","ruvnet","ruflo","performance-analysis",{"evaluate":446,"extract":452},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":447,"targetMarket":252,"tier":218},[448,214,215,449,450,451],"performance","claude-flow","bottleneck-detection","reporting",{"commitSha":254,"license":239},{"repoId":454},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[214,450,449,215,448,451],{"evaluatedAt":457,"extractAt":458,"updatedAt":457},1778699217174,1778696691708,{"_creationTime":460,"_id":461,"community":462,"display":463,"identity":469,"providers":474,"relations":481,"tags":484,"workflow":485},1778692488329.0164,"k17d7dgccv6vnj9tcw0cehwnph86nryb",{"reviewCount":8},{"description":464,"installMethods":465,"name":467,"sourceUrl":468},"Analyze which rules are actively used vs inert. Detect coverage gaps. Recommend pruning to reduce token consumption.",{"claudeCode":466},"luiseiman/claude-kit","Rule Effectiveness Analysis","https://github.com/luiseiman/claude-kit",{"basePath":470,"githubOwner":471,"githubRepo":472,"locale":275,"slug":473,"type":247},"skills/rule-effectiveness","luiseiman","claude-kit","rule-effectiveness",{"evaluate":475,"extract":480},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":476,"targetMarket":252,"tier":218},[477,478,214,215,479],"claude-code","configuration","git",{"commitSha":254,"license":239},{"parentExtensionId":482,"repoId":483},"k17650xadq8363kzchr4w0gmf186nq24","kd79wqc8an5wh20cc2znr8tyb586mxwx",[214,477,478,479,215],{"evaluatedAt":486,"extractAt":487,"updatedAt":486},1778693275143,1778692488329,{"_creationTime":489,"_id":490,"community":491,"display":492,"identity":498,"providers":502,"relations":510,"tags":512,"workflow":513},1778697652123.8975,"k17egwaz31kmprzw1q8m38fv4586mqah",{"reviewCount":8},{"description":493,"installMethods":494,"name":496,"sourceUrl":497},"Search and analyze your own session logs (older/parent conversations) using jq.",{"claudeCode":495},"steipete/clawdis","session-logs","https://github.com/steipete/clawdis",{"basePath":499,"githubOwner":500,"githubRepo":501,"locale":275,"slug":496,"type":247},"skills/session-logs","steipete","clawdis",{"evaluate":503,"extract":509},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":504,"targetMarket":252,"tier":218},[505,506,507,214,508],"logs","session","jq","cli",{"commitSha":254},{"repoId":511},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[214,508,507,505,506],{"evaluatedAt":514,"extractAt":515,"updatedAt":514},1778698902636,1778697652123,{"_creationTime":517,"_id":518,"community":519,"display":520,"identity":526,"providers":531,"relations":538,"tags":541,"workflow":542},1778697371856.6287,"k1779r96aq73f44z9ffm437vch86myt9",{"reviewCount":8},{"description":521,"installMethods":522,"name":524,"sourceUrl":525},"Wissen über das Präsentationsfolienformat, das Gewichtungssystem, die Navigation und die Abschnittsstruktur",{"claudeCode":523},"shanraisshan/claude-code-best-practice","Presentation Structure","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":527,"githubOwner":528,"githubRepo":529,"locale":18,"slug":530,"type":247},".claude/skills/presentation/presentation-structure","shanraisshan","claude-code-best-practice","presentation-structure",{"evaluate":532,"extract":537},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":533,"targetMarket":252,"tier":218},[534,535,536,214],"presentation","html","documentation",{"commitSha":254,"license":239},{"repoId":539,"translatedFrom":540},"kd74710g49kxgwbfjxeb7s132d86myxr","k175cp8c6m1kknsf9yhd75swn586m4hj",[214,536,535,534],{"evaluatedAt":543,"extractAt":544,"updatedAt":545},1778697246983,1778697205743,1778697371856,{"_creationTime":547,"_id":548,"community":549,"display":550,"identity":556,"providers":560,"relations":570,"tags":573,"workflow":574},1778695548458.3403,"k17874jrpzpfq3ftmmahe017n586nmy2",{"reviewCount":8},{"description":551,"installMethods":552,"name":554,"sourceUrl":555},"Compose or analyze sacred music in Hildegard von Bingen's distinctive modal style. Covers modal selection, melodic contour (wide-range melodies), text-setting (syllabic and melismatic), neumatic notation, and liturgical context for antiphons, sequences, and responsories. Use when composing a new piece in Hildegardian style, analyzing an existing chant for structure and mode, researching medieval modal music, preparing to perform or teach Hildegard's music, or setting Latin sacred texts.\n",{"claudeCode":553},"pjt222/agent-almanac","compose-sacred-music","https://github.com/pjt222/agent-almanac",{"basePath":557,"githubOwner":558,"githubRepo":559,"locale":275,"slug":554,"type":247},"skills/compose-sacred-music","pjt222","agent-almanac",{"evaluate":561,"extract":569},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":562,"targetMarket":252,"tier":218},[563,564,565,566,567,568,214],"hildegard","sacred-music","chant","modal","musicology","composition",{"commitSha":254},{"parentExtensionId":571,"repoId":572},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[214,565,568,563,566,567,564],{"evaluatedAt":575,"extractAt":576,"updatedAt":575},1778696688896,1778695548458,{"_creationTime":578,"_id":579,"community":580,"display":581,"identity":587,"providers":591,"relations":598,"tags":600,"workflow":601},1778684091954.6682,"k1724x2k19t06bmxsstfq8t7xs86ntjn",{"reviewCount":8},{"description":582,"installMethods":583,"name":585,"sourceUrl":586},"Run Cogny marketing analysis tasks — fetch scheduled tasks, analyze ad accounts via MCP, report findings",{"claudeCode":584},"cognyai/claude-code-marketing-skills","cogny","https://github.com/cognyai/claude-code-marketing-skills",{"basePath":588,"githubOwner":589,"githubRepo":590,"locale":275,"slug":585,"type":247},"skills/cogny","cognyai","claude-code-marketing-skills",{"evaluate":592,"extract":597},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":593,"targetMarket":252,"tier":218},[594,214,585,595,596,451],"marketing","ads","automation",{"commitSha":254},{"repoId":599},"kd7371gwzbdr07nc839hsmagw986nje6",[595,214,596,585,594,451],{"evaluatedAt":602,"extractAt":603,"updatedAt":602},1778684198526,1778684091954]