[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-Whatsonyourmind-oraclaw-bandit-de":3,"guides-for-Whatsonyourmind-oraclaw-bandit":436,"similar-k17bmad8esdm244kq3rwtmm9ms86nnyc-de":437},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":252,"isFallback":247,"parentExtension":258,"providers":259,"relations":265,"repo":268,"tags":432,"workflow":433},1778699093242.588,"k17bmad8esdm244kq3rwtmm9ms86nnyc",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"A/B-Tests und Funktionsoptimierung für KI-Agenten. Wählen Sie automatisch die beste Option mit Multi-Armed Bandits und kontextbezogenen Bandits (LinUCB). Kein Data Warehouse erforderlich – funktioniert ab der Anfrage.",{"claudeCode":12},"Whatsonyourmind/oraclaw","OraClaw Bandit","https://github.com/Whatsonyourmind/oraclaw",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":233,"workflow":250},1778699093242.5881,"kn7frz5fza70x5h2g3vqvdt7kh86na0c","de",{"checks":20,"evaluatedAt":195,"extensionSummary":196,"features":197,"nonGoals":203,"practices":207,"prerequisites":211,"promptVersionExtension":214,"promptVersionScoring":215,"purpose":216,"rationale":217,"score":218,"summary":219,"tags":220,"tier":227,"useCases":228},[21,26,29,33,37,41,45,48,52,56,60,63,66,69,72,76,79,82,85,88,91,95,99,102,106,109,112,115,118,121,124,128,131,135,139,142,145,148,151,155,158,161,164,167,170,173,177,181,185,188,192],{"category":22,"check":23,"severity":24,"summary":25},"Invocation","Precise Purpose","pass","Die Beschreibung gibt den Zweck der Fähigkeit (A/B-Tests und Funktionsoptimierung mit Bandits) und den Anwendungszeitpunkt klar an, benennt das Artefakt (Optionen/Varianten) und die Benutzerabsicht (die beste Option auswählen, Tests durchführen, Funktionen optimieren).",{"category":22,"check":27,"severity":24,"summary":28},"Concise Frontmatter","Das Frontmatter ist prägnant, in sich geschlossen und fasst die Kernfunktionalität und Anwendungsfälle innerhalb der ersten ca. 160 Zeichen klar zusammen.",{"category":30,"check":31,"severity":24,"summary":32},"Documentation","Concise Body","Die SKILL.md ist prägnant und lagert tiefere Materialien in separate Dateien aus, wodurch der Hauptteil unter einer angemessenen Länge gehalten wird.",{"category":34,"check":35,"severity":24,"summary":36},"Context","Progressive Disclosure","Die SKILL.md skizziert den Ablauf und verweist bei Bedarf auf externe Details, wobei übermäßige Inline-Daten vermieden werden.",{"category":34,"check":38,"severity":39,"summary":40},"Forked exploration","not_applicable","Diese Fähigkeit ist nicht für tiefe Erkundungen oder Recherchen konzipiert, die die Konversation überfluten würden, daher ist 'context: fork' nicht anwendbar.",{"category":42,"check":43,"severity":24,"summary":44},"Practical Utility","Usage examples","Es werden ausreichende End-to-End-Beispiele für die wichtigsten Funktionen bereitgestellt, die Eingabe, Aufruf und beobachtbare Ergebnisse demonstrieren, und sie erscheinen plausibel.",{"category":42,"check":46,"severity":24,"summary":47},"Edge cases","Die Fähigkeit behandelt Randfälle und Einschränkungen und dokumentiert Fehlerfälle mit beobachtbaren Symptomen und Wiederherstellungsschritten.",{"category":49,"check":50,"severity":24,"summary":51},"Code Execution","Tool Fallback","Die Fähigkeit listet die erforderliche MCP auf und merkt an, dass sie optional mit einem Fallback ist, was bewährten Praktiken in der Dokumentation entspricht.",{"category":53,"check":54,"severity":24,"summary":55},"Portability","Stack assumptions","Die Fähigkeit gibt ihre Stack-Annahmen klar an, einschließlich der Laufzeitumgebung (Node.js über npx) und minimaler Versionen, falls zutreffend, und Abhängigkeiten werden deklariert.",{"category":57,"check":58,"severity":24,"summary":59},"Safety","Halt on unexpected state","Die Fähigkeit listet Vorbedingungen auf und impliziert ein Anhalten bei unerwartetem Zustand, um einen sicheren Arbeitsablauf zu gewährleisten.",{"category":53,"check":61,"severity":24,"summary":62},"Cross-skill coupling","Die Fähigkeit ist in sich geschlossen und verlässt sich nicht implizit auf andere Fähigkeiten, mit expliziter Verknüpfung für verwandte Funktionalität.",{"category":42,"check":64,"severity":24,"summary":65},"Problem relevance","Die Beschreibung nennt klar das Problem des Benutzers, KI-gesteuerte Optimierung für Entscheidungen und A/B-Tests ohne komplexe Daten-Warehousing-Lösungen zu benötigen.",{"category":42,"check":67,"severity":24,"summary":68},"Unique selling proposition","Die Erweiterung bietet ein einzigartiges Verkaufsargument, indem sie deterministische mathematische Optimierungsalgorithmen (Bandits, LinUCB) für KI-Agenten bereitstellt, die über einfaches Prompting hinausgehen und eine latenzarme, tokenfreie Berechnung ermöglichen.",{"category":42,"check":70,"severity":24,"summary":71},"Production readiness","Die Erweiterung ist produktionsreif, bietet mehrere Integrationsmethoden (MCP-Server, REST-API, SDK) und deckt den vollständigen Lebenszyklus von Optimierungsaufgaben ab.",{"category":73,"check":74,"severity":24,"summary":75},"Scope","Single responsibility principle","Die Erweiterung konzentriert sich auf Optimierungsaufgaben mit Bandit-Algorithmen und hält sich an eine einzige, gut definierte Verantwortung.",{"category":73,"check":77,"severity":24,"summary":78},"Description quality","Die Beschreibung ist korrekt, prägnant, lesbar und spiegelt das Verhalten und die Fähigkeiten der Fähigkeit genau wider.",{"category":22,"check":80,"severity":24,"summary":81},"Scoped tools","Die Erweiterung stellt eng gefasste, spezifische Werkzeuge wie `optimize_bandit` und `optimize_contextual` bereit.",{"category":30,"check":83,"severity":24,"summary":84},"Configuration & parameter reference","Alle Parameter für die Bandit- und kontextbezogenen Werkzeuge sind dokumentiert, einschließlich der Konsistenz des Kontextvektors und der Belohnungsnormalisierung.",{"category":73,"check":86,"severity":24,"summary":87},"Tool naming","Werkzeugnamen wie `optimize_bandit` und `optimize_contextual` sind beschreibend und folgen einer klaren Konvention.",{"category":73,"check":89,"severity":24,"summary":90},"Minimal I/O surface","Werkzeugeingaben sind strukturiert (JSON-Objekte mit definierten Feldern) und Ausgaben sind minimal, geben nur den ausgewählten Arm und relevante Scores zurück.",{"category":92,"check":93,"severity":24,"summary":94},"License","License usability","Die Erweiterung wird unter der MIT-Lizenz vertrieben, die freizügig ist und sowohl in der README- als auch in der LICENSE-Datei klar angegeben ist.",{"category":96,"check":97,"severity":24,"summary":98},"Maintenance","Commit recency","Der letzte Commit war am 2. Mai 2026, also deutlich innerhalb der letzten 90 Tage, was auf eine aktive Wartung hindeutet.",{"category":96,"check":100,"severity":24,"summary":101},"Dependency Management","Das Projekt nutzt npm und listet Abhängigkeiten klar auf. Der `mcp-server` wird wahrscheinlich über npm verwaltet, was auf gute Praktiken im Abhängigkeitsmanagement hindeutet.",{"category":103,"check":104,"severity":24,"summary":105},"Security","Secret Management","Geheimnisse wie `ORACLAW_API_KEY` werden über Umgebungsvariablen gehandhabt und nicht in der Ausgabe wiedergegeben, mit entsprechenden Maßnahmen.",{"category":103,"check":107,"severity":24,"summary":108},"Injection","Die Erweiterung scheint keine unzuverlässigen Daten von Drittanbietern als Anweisungen zu laden oder auszuführen und ruft keine externen Inhalte als ausführbaren Code ab.",{"category":103,"check":110,"severity":24,"summary":111},"Transitive Supply-Chain Grenades","Die Erweiterung ruft zur Laufzeit keine externen Dateien ab oder verwendet Remote-Pipe-to-Shell-Muster; alle Abhängigkeiten werden verwaltet und committet.",{"category":103,"check":113,"severity":24,"summary":114},"Sandbox Isolation","Die Erweiterung operiert innerhalb des definierten Projektordners und modifiziert keine Dateien außerhalb ihres Geltungsbereichs, wodurch die Sandbox-Isolation respektiert wird.",{"category":103,"check":116,"severity":24,"summary":117},"Sandbox escape primitives","Es wurden keine getrennten Prozess-Spawns oder Deny-Retry-Schleifen in den bereitgestellten Skripten gefunden, was auf keine Sandbox-Escape-Primitive hindeutet.",{"category":103,"check":119,"severity":24,"summary":120},"Data Exfiltration","Die Erweiterung weist den Agenten nicht an, vertrauliche Daten zu lesen oder an Dritte zu übermitteln. Ausgehende Aufrufe sind dokumentiert und für bekannte Dienste.",{"category":103,"check":122,"severity":24,"summary":123},"Hidden Text Tricks","Der gebündelte Inhalt scheint frei von versteckten Lenkungstricks zu sein, und Beschreibungen verwenden sauberes, druckbares ASCII.",{"category":125,"check":126,"severity":24,"summary":127},"Hooks","Opaque code execution","Die bereitgestellten Skripte und der Code sind einfach und lesbar, ohne Obfuskation wie Base64-Payloads oder das Abrufen von Code zur Laufzeit.",{"category":53,"check":129,"severity":24,"summary":130},"Structural Assumption","Die Fähigkeit trifft keine strukturellen Annahmen über benutzerspezifische Projektorganisationen außerhalb ihres Bundles und gibt ihre Anforderungen klar an.",{"category":132,"check":133,"severity":24,"summary":134},"Trust","Issues Attention","Bei 0 geöffneten und 44 geschlossenen Problemen in den letzten 90 Tagen ist die Abschlussrate hoch und das Engagement der Maintainer stark.",{"category":136,"check":137,"severity":24,"summary":138},"Versioning","Release Management","Die Erweiterung hat eine klare Version (`1.0.0`) im SKILL.md Frontmatter und CHANGELOG.md, was auf ein ordnungsgemäßes Release-Management hinweist.",{"category":49,"check":140,"severity":24,"summary":141},"Validation","Eingabeargumente für die Werkzeuge sind in Schemata klar definiert und validiert, was eine robuste Ausführung gewährleistet.",{"category":103,"check":143,"severity":24,"summary":144},"Unguarded Destructive Operations","Diese Erweiterung ist nur lesbar und führt keine zerstörerischen Operationen durch.",{"category":49,"check":146,"severity":24,"summary":147},"Error Handling","Fehler werden abgefangen und aussagekräftig gemeldet, wobei strukturierte Felder für die Entscheidungsfindung des Agenten bereitgestellt werden und keine stillen Wiederholungen zerstörerischer Aktionen erfolgen.",{"category":49,"check":149,"severity":39,"summary":150},"Logging","Die Fähigkeit führt keine destruktiven Aktionen oder ausgehenden Aufrufe durch, die eine lokale Audit-Protokollierung erfordern.",{"category":152,"check":153,"severity":39,"summary":154},"Compliance","GDPR","Die Erweiterung verarbeitet keine personenbezogenen Daten und erfordert daher keine spezifischen GDPR-Bereinigungsmaßnahmen.",{"category":152,"check":156,"severity":24,"summary":157},"Target market","Die Algorithmen der Erweiterung sind global anwendbar, und es werden keine regionalen oder standortspezifischen Einschränkungen angegeben.",{"category":53,"check":159,"severity":24,"summary":160},"Runtime stability","Die Erweiterung ist für die Ausführung in Standardumgebungen (Node.js über npx) konzipiert und trifft keine Annahmen über spezifische Editoren oder OS-spezifische Funktionen.",{"category":30,"check":162,"severity":24,"summary":163},"README","Die README existiert, ist umfassend und gibt den Zweck und die Fähigkeiten der Erweiterung klar an.",{"category":73,"check":165,"severity":24,"summary":166},"Tool surface size","Die Erweiterung stellt 17 Werkzeuge bereit, was im gewünschten Bereich für einen umfassenden MCP-Server liegt.",{"category":22,"check":168,"severity":24,"summary":169},"Overlapping near-synonym tools","Werkzeugnamen sind eindeutig und decken spezifische Optimierungsaufgaben ohne signifikante Überschneidungen oder Redundanzen durch nahezu synonyme Begriffe ab.",{"category":30,"check":171,"severity":24,"summary":172},"Phantom features","Jede im README und in der SKILL.md beworbene Funktion hat eine entsprechende Implementierung in den bereitgestellten Werkzeugen.",{"category":174,"check":175,"severity":24,"summary":176},"Install","Installation instruction","Klare Installationsanweisungen für die MCP-Server-Einrichtung, die REST-API-Nutzung und das npm-SDK werden mit Copy-Paste-Beispielen bereitgestellt.",{"category":178,"check":179,"severity":24,"summary":180},"Errors","Actionable error messages","Fehlerpfade sind gut definiert, mit klaren Meldungen, die angeben, was fehlgeschlagen ist, warum, und Korrekturschritte oder Links enthalten.",{"category":182,"check":183,"severity":24,"summary":184},"Execution","Pinned dependencies","Abhängigkeiten werden über npm verwaltet und die MCP-Server-Einrichtung impliziert angepinnte Versionen, was reproduzierbare Builds sicherstellt.",{"category":73,"check":186,"severity":39,"summary":187},"Dry-run preview","Die Erweiterung ist primär analytisch und führt keine zustandsändernden Operationen durch, die eine Trockenlauf-Vorschau erfordern würden.",{"category":189,"check":190,"severity":24,"summary":191},"Protocol","Idempotent retry & timeouts","Die Operationen der Erweiterung sind, wo immer möglich, idempotent, und der MCP-Server und die API sind für Zustandsunabhängigkeit mit Timeouts ausgelegt.",{"category":152,"check":193,"severity":24,"summary":194},"Telemetry opt-in","Telemetrie wird nicht als gesammelt erwähnt, was keine Opt-out-Telemetrie impliziert, und jede potenzielle Sammlung wäre nach Standardpraktiken Opt-in.",1778698869231,"Diese Fähigkeit bietet KI-Agenten fortschrittliche Optimierungsfunktionen mit Multi-Armed Bandits und kontextbezogenen Bandits (LinUCB). Sie bietet deterministische mathematische Lösungen zur Auswahl zwischen Optionen, zur Durchführung von A/B-Tests und zur Personalisierung von Auswahlen basierend auf dem Kontext, ohne dass ein Data Warehouse erforderlich ist.",[198,199,200,201,202],"Automatische Auswahl der besten Varianten mittels Bandits","Kontextbezogene Optimierung mit LinUCB","Latenzarme (\u003C25ms) und tokenfreie Berechnungen","Mehrere Integrationsmethoden (MCP-Server, REST-API, SDK)","Unterstützung für verschiedene Optimierungsalgorithmen",[204,205,206],"Durchführung beliebiger mathematischer Berechnungen über die Optimierung hinaus","Als allgemeines Werkzeug für Datenanalyse oder Data Warehousing fungieren","Ersetzung von LLM-Argumentation für Aufgaben, die keine deterministischen mathematischen Lösungen erfordern",[208,209,210],"Optimierung","Experimentelles Design","Machine Learning Operations",[212,213],"ORACLAW_API_KEY Umgebungsvariable für Premium-Funktionen","Node.js/npm für lokale MCP-Server-Einrichtung","3.0.0","4.4.0","KI-Agenten mit präzisen, deterministischen Optimierungsalgorithmen für die Entscheidungsfindung auszustatten, damit sie die besten Optionen auswählen, effektive A/B-Tests durchführen und Funktionen optimieren können, ohne auf potenziell fehleranfällige LLM-Heuristiken angewiesen zu sein.","Hohe Qualität bei allen Prüfpunkten, besonders stark in praktischem Nutzen, Dokumentation und Sicherheit. Der einzige bemerkenswerte Bereich ist das Fehlen einer Trockenlauf-Funktion, die angesichts der analytischen Natur der Erweiterung nicht zutreffend ist.",99,"Eine robuste und produktionsreife Fähigkeit für KI-gestützte A/B-Tests und Optimierung.",[221,222,223,224,225,226],"optimization","ab-testing","feature-flags","experimentation","machine-learning","mcp","verified",[229,230,231,232],"Auswahl der besten Variante aus mehreren Optionen für A/B-Tests","Optimierung von Feature-Flags, Prompts, E-Mail-Betreffzeilen oder beliebigen Auswahlmöglichkeiten","Kontextbezogene Auswahl basierend auf Benutzer, Zeit oder Situation","Durchführung adaptiver Experimente ohne vordefinierte Stichprobengrößen",{"codeQuality":234,"collectedAt":236,"documentation":237,"maintenance":240,"security":246,"testCoverage":249},{"hasLockfile":235},true,1778698853904,{"descriptionLength":238,"readmeSize":239},191,9472,{"closedIssues90d":241,"forks":242,"hasChangelog":235,"manifestVersion":243,"openIssues90d":8,"pushedAt":244,"stars":245},44,2,"1.0.0",1777714123000,8,{"hasNpmPackage":247,"license":248,"smitheryVerified":247},false,"MIT",{"hasCi":235,"hasTests":235},{"updatedAt":251},1778699093242,{"basePath":253,"githubOwner":254,"githubRepo":255,"locale":18,"slug":256,"type":257},"mission-control/packages/clawhub-skills/oraclaw-bandit","Whatsonyourmind","oraclaw","oraclaw-bandit","skill",null,{"evaluate":260,"extract":263},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":261,"targetMarket":262,"tier":227},[221,222,223,224,225,226],"global",{"commitSha":264,"license":248},"HEAD",{"repoId":266,"translatedFrom":267},"kd76fmxm1ng903s4fmj0p7hxxs86ndkg","k17ewnzxwqzf8m1b1t3c7srke186nx9a",{"_creationTime":269,"_id":266,"identity":270,"providers":271,"workflow":428},1778698831609.0093,{"githubOwner":254,"githubRepo":255,"sourceUrl":14},{"classify":272,"discover":404,"github":407},{"commitSha":264,"extensions":273},[274,286,292,300,308,316,324,332,340,348,356,364,372,380,388],{"basePath":275,"description":276,"displayName":277,"installMethods":278,"rationale":279,"selectedPaths":280,"source":284,"sourceLanguage":285,"type":257},"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",[281],{"path":282,"priority":283},"SKILL.md","mandatory","rule","en",{"basePath":253,"description":287,"displayName":256,"installMethods":288,"rationale":289,"selectedPaths":290,"source":284,"sourceLanguage":285,"type":257},"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",{"claudeCode":12},"SKILL.md frontmatter at mission-control/packages/clawhub-skills/oraclaw-bandit/SKILL.md",[291],{"path":282,"priority":283},{"basePath":293,"description":294,"displayName":295,"installMethods":296,"rationale":297,"selectedPaths":298,"source":284,"sourceLanguage":285,"type":257},"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",[299],{"path":282,"priority":283},{"basePath":301,"description":302,"displayName":303,"installMethods":304,"rationale":305,"selectedPaths":306,"source":284,"sourceLanguage":285,"type":257},"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",[307],{"path":282,"priority":283},{"basePath":309,"description":310,"displayName":311,"installMethods":312,"rationale":313,"selectedPaths":314,"source":284,"sourceLanguage":285,"type":257},"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",[315],{"path":282,"priority":283},{"basePath":317,"description":318,"displayName":319,"installMethods":320,"rationale":321,"selectedPaths":322,"source":284,"sourceLanguage":285,"type":257},"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",[323],{"path":282,"priority":283},{"basePath":325,"description":326,"displayName":327,"installMethods":328,"rationale":329,"selectedPaths":330,"source":284,"sourceLanguage":285,"type":257},"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",[331],{"path":282,"priority":283},{"basePath":333,"description":334,"displayName":335,"installMethods":336,"rationale":337,"selectedPaths":338,"source":284,"sourceLanguage":285,"type":257},"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",[339],{"path":282,"priority":283},{"basePath":341,"description":342,"displayName":343,"installMethods":344,"rationale":345,"selectedPaths":346,"source":284,"sourceLanguage":285,"type":257},"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",[347],{"path":282,"priority":283},{"basePath":349,"description":350,"displayName":351,"installMethods":352,"rationale":353,"selectedPaths":354,"source":284,"sourceLanguage":285,"type":257},"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",[355],{"path":282,"priority":283},{"basePath":357,"description":358,"displayName":359,"installMethods":360,"rationale":361,"selectedPaths":362,"source":284,"sourceLanguage":285,"type":257},"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",[363],{"path":282,"priority":283},{"basePath":365,"description":366,"displayName":367,"installMethods":368,"rationale":369,"selectedPaths":370,"source":284,"sourceLanguage":285,"type":257},"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",[371],{"path":282,"priority":283},{"basePath":373,"description":374,"displayName":375,"installMethods":376,"rationale":377,"selectedPaths":378,"source":284,"sourceLanguage":285,"type":257},"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",[379],{"path":282,"priority":283},{"basePath":381,"description":382,"displayName":383,"installMethods":384,"rationale":385,"selectedPaths":386,"source":284,"sourceLanguage":285,"type":257},"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",[387],{"path":282,"priority":283},{"basePath":389,"description":390,"displayName":391,"installMethods":392,"license":248,"rationale":393,"selectedPaths":394,"source":284,"sourceLanguage":285,"type":226},"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":391},"server.json with namespace/server name at mission-control/packages/mcp-server/server.json",[395,397,399,401],{"path":396,"priority":283},"server.json",{"path":398,"priority":283},"package.json",{"path":400,"priority":283},"README.md",{"path":402,"priority":403},"src/index.ts","low",{"sources":405},[406],"manual",{"closedIssues90d":241,"description":408,"forks":242,"homepage":409,"license":248,"openIssues90d":8,"pushedAt":244,"readmeSize":239,"stars":245,"topics":410},"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",[411,412,413,414,415,416,225,226,221,417,418,419,420,421,422,423,424,425,426,427],"ai-agents","algorithms","api","bandits","decision-intelligence","fastify","typescript","agent-tools","anthropic","claude-mcp","contextual-bandit","deterministic-tools","linear-programming","llm-tools","model-context-protocol","monte-carlo","pagerank",{"classifiedAt":429,"discoverAt":430,"extractAt":431,"githubAt":431,"updatedAt":429},1778698837409,1778698831609,1778698835357,[222,224,223,225,226,221],{"evaluatedAt":434,"extractAt":435,"updatedAt":251},1778698869396,1778698837670,[],[438,467,496,523,545,573],{"_creationTime":439,"_id":440,"community":441,"display":442,"identity":448,"providers":452,"relations":460,"tags":463,"workflow":464},1778695720086.7703,"k176r34g5a5fjn1z1a4gq6v88186nje0",{"reviewCount":8},{"description":443,"installMethods":444,"name":446,"sourceUrl":447},"Designs an A/B test or experiment with clear hypothesis, variants, success metrics, sample size, and duration. Use when planning experiments to validate product changes or test hypotheses.",{"claudeCode":445},"product-on-purpose/pm-skills","measure-experiment-design","https://github.com/product-on-purpose/pm-skills",{"basePath":449,"githubOwner":450,"githubRepo":451,"locale":285,"slug":446,"type":257},"skills/measure-experiment-design","product-on-purpose","pm-skills",{"evaluate":453,"extract":459},{"promptVersionExtension":214,"promptVersionScoring":215,"score":454,"tags":455,"targetMarket":262,"tier":227},100,[222,224,456,457,458],"product-management","a-b-testing","data-analysis",{"commitSha":264},{"parentExtensionId":461,"repoId":462},"k1721116hsfj7zg78w03432n8986n6y8","kd78ksv1wjj826ds5j1sh2kqnx86mhqf",[457,222,458,224,456],{"evaluatedAt":465,"extractAt":466,"updatedAt":465},1778696438706,1778695720086,{"_creationTime":468,"_id":469,"community":470,"display":471,"identity":477,"providers":482,"relations":489,"tags":492,"workflow":493},1778686640222.7952,"k178bs4zybvyebq2gnym4jazch86np03",{"reviewCount":8},{"description":472,"installMethods":473,"name":475,"sourceUrl":476},"Run metric-driven iterative optimization loops -- define a measurable goal, run parallel experiments, measure each against hard gates or LLM-as-judge scores, keep improvements, and converge on the best solution. Use when optimizing clustering quality, search relevance, build performance, prompt quality, or any measurable outcome that benefits from systematic experimentation.",{"claudeCode":474},"EveryInc/compound-engineering-plugin","CE Optimize","https://github.com/EveryInc/compound-engineering-plugin",{"basePath":478,"githubOwner":479,"githubRepo":480,"locale":285,"slug":481,"type":257},"plugins/compound-engineering/skills/ce-optimize","EveryInc","compound-engineering-plugin","ce-optimize",{"evaluate":483,"extract":488},{"promptVersionExtension":214,"promptVersionScoring":215,"score":454,"tags":484,"targetMarket":262,"tier":227},[221,224,485,486,487],"mlops","code-quality","prompt-engineering",{"commitSha":264,"license":248},{"parentExtensionId":490,"repoId":491},"k17d893df4em0e3pn8f55h1dxn86n09e","kd7e40my1b5g70tg0f60qg85ch86nn08",[486,224,485,221,487],{"evaluatedAt":494,"extractAt":495,"updatedAt":494},1778687141592,1778686640222,{"_creationTime":497,"_id":498,"community":499,"display":500,"identity":506,"providers":510,"relations":516,"tags":519,"workflow":520},1778675056600.2664,"k173ggr45da0wr1c32bva99bvh86nj5a",{"reviewCount":8},{"description":501,"installMethods":502,"name":504,"sourceUrl":505},"Use when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes with practical statistical rigor.",{"claudeCode":503},"alirezarezvani/claude-skills","experiment-designer","https://github.com/alirezarezvani/claude-skills",{"basePath":507,"githubOwner":508,"githubRepo":509,"locale":285,"slug":504,"type":257},"product-team/skills/experiment-designer","alirezarezvani","claude-skills",{"evaluate":511,"extract":515},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":512,"targetMarket":262,"tier":227},[224,222,456,513,458,514],"statistics","hypothesis-testing",{"commitSha":264},{"parentExtensionId":517,"repoId":518},"k17104ysr0smp7vvp26mnn1fzh86nynm","kd7ff9s1w43mfyy1n7hf87816186m6px",[222,458,224,514,456,513],{"evaluatedAt":521,"extractAt":522,"updatedAt":521},1778685452060,1778675056600,{"_creationTime":524,"_id":525,"community":526,"display":527,"identity":531,"providers":533,"relations":540,"tags":542,"workflow":543},1778675056600.2542,"k17d6x2qxdeyeegtqjtkz3myqx86mq6m",{"reviewCount":8},{"description":528,"installMethods":529,"name":530,"sourceUrl":505},"When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions \"A/B test,\" \"split test,\" \"experiment,\" \"test this change,\" \"variant copy,\" \"multivariate test,\" \"hypothesis,\" \"conversion experiment,\" \"statistical significance,\" or \"test this.\" For tracking implementation, see analytics-tracking.",{"claudeCode":503},"ab-test-setup",{"basePath":532,"githubOwner":508,"githubRepo":509,"locale":285,"slug":530,"type":257},"marketing-skill/skills/ab-test-setup",{"evaluate":534,"extract":539},{"promptVersionExtension":214,"promptVersionScoring":215,"score":535,"tags":536,"targetMarket":262,"tier":227},98,[222,224,537,538,458],"conversion-optimization","marketing",{"commitSha":264},{"parentExtensionId":541,"repoId":518},"k170sws65f0ebecn36z3q8c2z186m477",[222,537,458,224,538],{"evaluatedAt":544,"extractAt":522,"updatedAt":544},1778684020423,{"_creationTime":546,"_id":547,"community":548,"display":549,"identity":555,"providers":559,"relations":566,"tags":569,"workflow":570},1778695548458.3943,"k170qwsw3sjhsnm2r2nyz0j7jd86n1s7",{"reviewCount":8},{"description":550,"installMethods":551,"name":553,"sourceUrl":554},"Design and execute A/B tests for ML models in production using traffic splitting, statistical significance testing, and canary/shadow deployment strategies. Measure performance differences and make data-driven decisions about model rollout. Use when validating a new model version before full rollout, comparing candidate models trained with different algorithms, measuring business metric impact of model changes, or when regulatory requirements mandate gradual rollout.\n",{"claudeCode":552},"pjt222/agent-almanac","run-ab-test-models","https://github.com/pjt222/agent-almanac",{"basePath":556,"githubOwner":557,"githubRepo":558,"locale":285,"slug":553,"type":257},"skills/run-ab-test-models","pjt222","agent-almanac",{"evaluate":560,"extract":565},{"promptVersionExtension":214,"promptVersionScoring":215,"score":561,"tags":562,"targetMarket":262,"tier":227},95,[485,222,563,564,224],"canary-deployment","statistical-testing",{"commitSha":264},{"parentExtensionId":567,"repoId":568},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[222,563,224,485,564],{"evaluatedAt":571,"extractAt":572,"updatedAt":571},1778700953339,1778695548458,{"_creationTime":574,"_id":575,"community":576,"display":577,"identity":583,"providers":587,"relations":595,"tags":597,"workflow":598},1778695660274.5056,"k17erc36epeh2pmf9zgrfhe19s86ne9f",{"reviewCount":8},{"description":578,"installMethods":579,"name":581,"sourceUrl":582},"Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions to configuring-experiment-rollout and metric setup to configuring-experiment-analytics.\nTRIGGER when: user asks to create a new experiment or A/B test, OR when you are about to call experiment-create.\nDO NOT TRIGGER when: user is updating an existing experiment, managing lifecycle, or only browsing experiments.",{"claudeCode":580},"PostHog/posthog","creating-experiments","https://github.com/PostHog/posthog",{"basePath":584,"githubOwner":585,"githubRepo":586,"locale":285,"slug":581,"type":257},"products/experiments/skills/creating-experiments","PostHog","posthog",{"evaluate":588,"extract":594},{"promptVersionExtension":214,"promptVersionScoring":215,"score":589,"tags":590,"targetMarket":262,"tier":593},79,[591,222,592,586,223],"experiments","product-analytics","community",{"commitSha":264},{"repoId":596},"kd7f22zf7qb3eschtk9s2qdv4586mfts",[222,591,223,586,592],{"evaluatedAt":599,"extractAt":600,"updatedAt":599},1778697075518,1778695660274]