[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-BrainBlend-AI-create-atomic-schema-de":3,"guides-for-BrainBlend-AI-create-atomic-schema":518,"similar-k17febhm14mhrjy7wd99dp601s86njn0-de":519},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":249,"isFallback":244,"parentExtension":254,"providers":313,"relations":317,"repo":319,"tags":515,"workflow":516},1778683567301.4797,"k17febhm14mhrjy7wd99dp601s86njn0",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Entwerfen und schreiben Sie ein `BaseIOSchema`-Eingabe-/Ausgabepaar für einen Atomic Agents-Agenten oder ein Tool – Docstrings, Feld-Beschreibungen, Validatoren, Fehler-Varianten. Verwenden Sie dies, wenn der Benutzer nach \"Schema erstellen\", \"Eingabe-/Ausgabe-Schema entwerfen\", \"`IOSchema` definieren\", \"`BaseIOSchema` schreiben\", \"Modellieren der Agentenausgabe\" fragt oder `/atomic-agents:create-atomic-schema` ausführt.",{"claudeCode":12},"BrainBlend-AI/atomic-agents","Create Atomic Schema","https://github.com/BrainBlend-AI/atomic-agents",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":230,"workflow":247},1778683567301.48,"kn773kt4wd13w5vat5haj5c1ss86mk8q","de",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":199,"practices":203,"prerequisites":207,"promptVersionExtension":208,"promptVersionScoring":209,"purpose":210,"rationale":211,"score":212,"summary":213,"tags":214,"tier":220,"useCases":221,"workflow":225},[21,26,29,33,37,41,45,48,52,56,60,63,66,69,73,76,79,82,85,88,92,96,99,103,106,109,112,115,118,121,125,128,132,136,139,142,145,148,152,155,158,161,164,167,170,174,178,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Invocation","Precise Purpose","pass","Die Beschreibung gibt klar an, was die Fähigkeit tut (Entwurf und Schreiben von `BaseIOSchema`-Eingabe-/Ausgabepaarungen) und für wen (Entwickler von Atomic Agents-Agenten oder -Tools), einschließlich spezifischer Benutzerabsichten und eines negativen Auslösers für die übergreifende Framework-Fähigkeit.",{"category":22,"check":27,"severity":24,"summary":28},"Concise Frontmatter","Der Frontmatter ist prägnant und fasst die Kernfunktionalität effektiv zusammen und liefert klare Auslöserphrasen innerhalb des Zeichenlimits.",{"category":30,"check":31,"severity":24,"summary":32},"Documentation","Concise Body","Der SKILL.md-Body ist gut strukturiert und vermeidet übermäßige Länge, wobei tiefere Materialien nach Bedarf in Referenzdateien ausgelagert werden.",{"category":34,"check":35,"severity":24,"summary":36},"Context","Progressive Disclosure","Die SKILL.md skizziert den Workflow und verweist auf eine separate Referenzdatei für tiefere Materialien, was den Prinzipien der progressiven Offenlegung entspricht.",{"category":34,"check":38,"severity":39,"summary":40},"Forked exploration","not_applicable","Diese Fähigkeit konzentriert sich auf die Schemaerstellung und beinhaltet keine tiefe Erkundung oder Code-Überprüfung, die einen verzweigten Kontext erfordern würde.",{"category":42,"check":43,"severity":24,"summary":44},"Practical Utility","Usage examples","Die SKILL.md bietet eine minimale Vorlage und klare Verifizierungsschritte, die als illustrative Beispiele für die Schemaerstellung dienen.",{"category":42,"check":46,"severity":24,"summary":47},"Edge cases","Die SKILL.md beschreibt spezifische Antipatterns, die abgelehnt werden sollen, und dokumentiert effektiv Fehlerfälle und Wiederherstellungsschritte für das Schema-Design.",{"category":49,"check":50,"severity":39,"summary":51},"Code Execution","Tool Fallback","Diese Fähigkeit ist nicht auf externe Tools wie einen MCP-Server angewiesen, daher ist ein Fallback nicht anwendbar.",{"category":53,"check":54,"severity":24,"summary":55},"Safety","Halt on unexpected state","Die Fähigkeit weist klar an, bei unerwarteten Zuständen wie fehlenden Docstrings oder Feldern abzubrechen und zu berichten, die als Vorbedingungen fungieren.",{"category":57,"check":58,"severity":24,"summary":59},"Portability","Cross-skill coupling","Die Fähigkeit ist in sich geschlossen und grenzt ihren Umfang klar ab, indem sie ohne implizite Abhängigkeit auf eine gleichrangige Fähigkeit für verwandte, aber unterschiedliche Aufgaben verweist.",{"category":42,"check":61,"severity":24,"summary":62},"Problem relevance","Die Beschreibung benennt klar das Problem der Erstellung und des Schreibens von `BaseIOSchema`-Paaren für Atomic Agents und gibt an, wann sie verwendet werden soll.",{"category":42,"check":64,"severity":24,"summary":65},"Unique selling proposition","Die Fähigkeit bietet einen strukturierten Workflow zur Erstellung von Schemata, die Pydantic und Instructor für die LLM-Integration nutzen, und bietet einen Mehrwert über einfaches Prompting hinaus.",{"category":42,"check":67,"severity":24,"summary":68},"Production readiness","Die Fähigkeit bietet einen vollständigen Lebenszyklus für die Schemaerstellung, von der Klärung bis zur Verifizierung und Übergabe, und ist für den Produktionseinsatz bereit.",{"category":70,"check":71,"severity":24,"summary":72},"Scope","Single responsibility principle","Die Fähigkeit konzentriert sich ausschließlich auf die Erstellung und Validierung von Atomic Agents-Schemas und behält eine klare und einzige Verantwortung bei.",{"category":70,"check":74,"severity":24,"summary":75},"Description quality","Die Beschreibung ist prägnant, lesbar und spiegelt das Verhalten und den Zweck der Fähigkeit genau wider.",{"category":22,"check":77,"severity":39,"summary":78},"Scoped tools","Diese Fähigkeit gibt keine spezifischen Tools oder Befehle frei; sie fungiert als direkte, anweisungsbasierte Fähigkeit.",{"category":30,"check":80,"severity":39,"summary":81},"Configuration & parameter reference","Diese Fähigkeit hat keine konfigurierbaren Parameter oder Optionen, die über ihre Kernanweisungen hinaus dokumentiert werden müssten.",{"category":70,"check":83,"severity":39,"summary":84},"Tool naming","Diese Fähigkeit gibt keine Tools oder Befehle frei, daher ist die Benennung von Tools nicht anwendbar.",{"category":70,"check":86,"severity":39,"summary":87},"Minimal I/O surface","Da es sich um eine auf Prompts basierende Fähigkeit handelt, verfügt sie nicht über herkömmliche Tool-Parameter oder Antwortformen, die auf eine minimale I/O-Oberfläche hin untersucht werden könnten.",{"category":89,"check":90,"severity":24,"summary":91},"License","License usability","Die mitgelieferte LICENSE-Datei ist MIT, eine permissive Open-Source-Lizenz, und ist korrekt identifiziert.",{"category":93,"check":94,"severity":24,"summary":95},"Maintenance","Commit recency","Der letzte Commit war am 29. April 2026, was innerhalb der letzten 3 Monate liegt.",{"category":93,"check":97,"severity":24,"summary":98},"Dependency Management","Das Projekt verfügt über eine Lock-Datei und CI/CD-Pipelines für Codequalität, was auf gute Praktiken im Abhängigkeitsmanagement hindeutet.",{"category":100,"check":101,"severity":24,"summary":102},"Security","Secret Management","Die Fähigkeit verarbeitet oder exponiert keine Geheimnisse.",{"category":100,"check":104,"severity":24,"summary":105},"Injection","Die Fähigkeit lädt zur Laufzeit keine Daten oder Dateien von Drittanbietern, wodurch Injektionsrisiken gemindert werden.",{"category":100,"check":107,"severity":24,"summary":108},"Transitive Supply-Chain Grenades","Die Fähigkeit ruft zur Laufzeit keine externen Inhalte ab und verhindert so transitive Risiken in der Lieferkette.",{"category":100,"check":110,"severity":24,"summary":111},"Sandbox Isolation","Die Fähigkeit operiert innerhalb ihres definierten Umfangs und interagiert nicht mit Dateien außerhalb ihres Projektordners und modifiziert diese auch nicht.",{"category":100,"check":113,"severity":24,"summary":114},"Sandbox escape primitives","Es wurden keine abgekoppelten Prozess-Spawns oder deny-retry-Schleifen im Code der Fähigkeit erkannt.",{"category":100,"check":116,"severity":24,"summary":117},"Data Exfiltration","Die Fähigkeit liest oder übermittelt keine vertraulichen Daten an Dritte.",{"category":100,"check":119,"severity":24,"summary":120},"Hidden Text Tricks","Die mitgelieferten Inhalte sind frei von versteckten Steuerungs-Tricks und Beschreibungen verwenden sauberes, druckbares ASCII.",{"category":122,"check":123,"severity":24,"summary":124},"Hooks","Opaque code execution","Der Code der Fähigkeit ist klar und lesbar, ohne Verschleierung, Base64-Payloads oder zur Laufzeit abgerufene Skripte.",{"category":57,"check":126,"severity":24,"summary":127},"Structural Assumption","Die Fähigkeit trifft keine strukturellen Annahmen über Benutzerprojekte außerhalb ihres eigenen Bundles und stützt sich auf Standard-Python-Importe.",{"category":129,"check":130,"severity":24,"summary":131},"Trust","Issues Attention","Das Projekt zeigt ein gesundes Verhältnis von geschlossenen zu offenen Issues (7 geschlossen, 6 offen in 90 Tagen), was auf aktive Wartung hindeutet.",{"category":133,"check":134,"severity":24,"summary":135},"Versioning","Release Management","Das Projekt verwendet aussagekräftiges Semver in seiner package.json und verfügt über ein Changelog, was auf ein gutes Release-Management hindeutet.",{"category":49,"check":137,"severity":24,"summary":138},"Validation","Die Fähigkeit stützt sich auf Pydantic für die Schema-Validierung, um eine robuste Eingabeverarbeitung zu gewährleisten.",{"category":100,"check":140,"severity":24,"summary":141},"Unguarded Destructive Operations","Diese Fähigkeit ist nicht destruktiv; sie konzentriert sich auf die Schemaerstellung und -validierung.",{"category":49,"check":143,"severity":24,"summary":144},"Error Handling","Die Fähigkeit nutzt die ValidationError-Behandlung von Pydantic und weist Benutzer an, Schema-Beschränkungen zu korrigieren, was auf ein robustes Fehlermanagement hindeutet.",{"category":49,"check":146,"severity":39,"summary":147},"Logging","Da diese Fähigkeit rein instruktiv ist und keine destruktiven Aktionen oder ausgehenden Aufrufe durchführt, ist Logging nicht anwendbar.",{"category":149,"check":150,"severity":39,"summary":151},"Compliance","GDPR","Die Fähigkeit verarbeitet keine personenbezogenen Daten.",{"category":149,"check":153,"severity":24,"summary":154},"Target market","Die Fähigkeit ist sprachunabhängig und enthält keine regionale Logik, was sie global anwendbar macht.",{"category":57,"check":156,"severity":24,"summary":157},"Runtime stability","Die Fähigkeit stützt sich auf Standard-Python und Pydantic, ohne spezifische Betriebssystem- oder Shell-Annahmen, was eine breite Kompatibilität gewährleistet.",{"category":30,"check":159,"severity":24,"summary":160},"README","Die README-Datei existiert und beschreibt klar den Zweck des Projekts, die Funktionen und die Anleitung zur Inbetriebnahme.",{"category":70,"check":162,"severity":39,"summary":163},"Tool surface size","Dies ist eine Einzelfunktions-Fähigkeit und bietet keine mehreren Tools oder Befehle.",{"category":22,"check":165,"severity":39,"summary":166},"Overlapping near-synonym tools","Diese Fähigkeit gibt keine mehreren Tools frei, daher sind überlappende Synonyme nicht anwendbar.",{"category":30,"check":168,"severity":24,"summary":169},"Phantom features","Alle beworbenen Funktionen im Zusammenhang mit der Schemaerstellung sind implementiert und in der Fähigkeit und der README dokumentiert.",{"category":171,"check":172,"severity":24,"summary":173},"Install","Installation instruction","Die README bietet klare Installationsanweisungen mit pip und enthält ein ausführbares Python-Codebeispiel.",{"category":175,"check":176,"severity":24,"summary":177},"Errors","Actionable error messages","Die Fähigkeit dokumentiert Fehlerfälle und Wiederherstellungsschritte klar und stellt sicher, dass Benutzer auf Fehler reagieren können.",{"category":179,"check":180,"severity":24,"summary":181},"Execution","Pinned dependencies","Das Projekt enthält eine Lock-Datei und gibt Python-Versionsanforderungen an, was auf angeheftete Abhängigkeiten hindeutet.",{"category":70,"check":183,"severity":39,"summary":184},"Dry-run preview","Diese Fähigkeit ist nicht zustandsändernd und führt keine ausgehenden Operationen durch, wodurch eine Dry-Run-Funktion unzutreffend ist.",{"category":186,"check":187,"severity":39,"summary":188},"Protocol","Idempotent retry & timeouts","Diese Fähigkeit beinhaltet keine Fernaufrufe oder zustandsändernden Operationen, daher sind Idempotenz und Timeouts nicht anwendbar.",{"category":149,"check":190,"severity":24,"summary":191},"Telemetry opt-in","In der Dokumentation oder im Code gibt es keine Hinweise auf Telemetriesammlung.",1778683329664,"Diese Fähigkeit unterstützt Benutzer beim Entwerfen und Schreiben von `BaseIOSchema`-Eingabe-/Ausgabepaarungen für Atomic Agents, einschließlich Docstrings, Feld-Beschreibungen und Validatoren. Sie folgt einem strukturierten Prozess aus Klärung, Schreiben und Verifizierung.",[195,196,197,198],"Leitet das Schema-Design mit klaren Phasen (klären, schreiben, verifizieren).","Erzwingt Docstrings und Feld-Beschreibungen für die LLM-Integration.","Demonstriert diskriminierte Unions und die Verwendung von Validatoren.","Stellt eine minimale Vorlage für eine schnelle Schemaimplementierung bereit.",[200,201,202],"Bearbeitung allgemeiner Fragen zum Atomic Agents-Framework (verwenden Sie die übergreifende Fähigkeit).","Implementierung komplexer Validatoren oder fortgeschrittener Pydantic-Muster, die über den Bereich der Schema-Definition hinausgehen.","Schreiben der eigentlichen Agenten- oder Tool-Logik, die das Schema verwendet.",[204,205,206],"Schema-Design","Code-Dokumentation","Typsicherheit",[],"3.0.0","4.4.0","Zur Rationalisierung der Erstellung robuster und gut dokumentierter Eingabe-/Ausgabeschemata für Atomic Agents, um Konsistenz und Wartbarkeit bei der Entwicklung von KI-Anwendungen zu gewährleisten.","Die Erweiterung ist gut dokumentiert, folgt Best Practices für die Schemaerstellung im Atomic Agents-Framework und weist keine kritischen oder Warnmeldungen auf. Alle Prüfungen waren erfolgreich oder nicht zutreffend.",98,"Eine qualitativ hochwertige Fähigkeit zur Generierung von Atomic Agents-Schemas mit klaren Anweisungen und Beispielen.",[215,216,217,218,219],"schema","pydantic","instructor","atomic-agents","python","verified",[222,223,224],"Wenn ein Benutzer nach der Erstellung oder Definition eines Schemas für einen Agenten oder ein Tool fragt.","Beim Ändern eines vorhandenen Schemas mit neuen Feldern oder Fehler-Varianten.","Wenn sichergestellt wird, dass Schemata für die LLM-Interpretation ordnungsgemäß dokumentiert sind.",[226,227,228,229],"Klare den Aufrufer, die Richtung, die Felder und die Fehlerfälle.","Schreiben Sie Schemata an konventionellen Stellen unter Verwendung von `BaseIOSchema` und `Field` mit Beschreibungen.","Verifizieren Sie, dass Schema-Importe sauber sind und die Round-Trip-Überprüfung über `model_json_schema()` erfolgreich durchlaufen.","Übergabe an den Benutzer mit Importorten und nächsten Schritten (Agent, Tool, Anbieter).",{"codeQuality":231,"collectedAt":233,"documentation":234,"maintenance":237,"security":243,"testCoverage":246},{"hasLockfile":232},true,1778683313650,{"descriptionLength":235,"readmeSize":236},352,20431,{"closedIssues90d":238,"forks":239,"hasChangelog":232,"openIssues90d":240,"pushedAt":241,"stars":242},7,506,6,1777460217000,5909,{"hasNpmPackage":244,"license":245,"smitheryVerified":244},false,"MIT",{"hasCi":232,"hasTests":232},{"updatedAt":248},1778683567301,{"basePath":250,"githubOwner":251,"githubRepo":218,"locale":18,"slug":252,"type":253},"claude-plugin/atomic-agents/skills/create-atomic-schema","BrainBlend-AI","create-atomic-schema","skill",{"_creationTime":255,"_id":256,"community":257,"display":258,"identity":261,"parentExtension":265,"providers":299,"relations":308,"tags":309,"workflow":310},1778683220959.3245,"k17bm61p7zr993vt7thb45838h86mrjy",{"reviewCount":8},{"description":259,"installMethods":260,"name":218,"sourceUrl":14},"Skills plus explorer and reviewer subagents for building, scaffolding, understanding, and auditing applications with the Atomic Agents Python framework. Includes the umbrella `framework` skill, action-oriented `create-atomic-schema` / `create-atomic-agent` / `create-atomic-tool` / `create-atomic-context-provider` skills, the `new-app` scaffolder, progressive-disclosure reference material for prompts, orchestration, memory, hooks, providers, project structure, and testing, and isolated-context subagents for codebase mapping and code review.",{"claudeCode":218},{"basePath":262,"githubOwner":251,"githubRepo":218,"locale":263,"slug":218,"type":264},"claude-plugin/atomic-agents","en","plugin",{"_creationTime":266,"_id":267,"community":268,"display":269,"identity":273,"providers":276,"relations":292,"tags":294,"workflow":295},1778683220959.3242,"k173812k7d1b2wh2bze2r2cdjn86mzva",{"reviewCount":8},{"description":270,"installMethods":271,"name":272,"sourceUrl":14},"Official plugins for the Atomic Agents framework - a lightweight, modular system for building AI agents with Pydantic and Instructor",{"claudeCode":12},"Atomic Agents",{"basePath":274,"githubOwner":251,"githubRepo":218,"locale":263,"slug":218,"type":275},"","marketplace",{"evaluate":277,"extract":285},{"promptVersionExtension":278,"promptVersionScoring":209,"score":279,"tags":280,"targetMarket":284,"tier":220},"3.1.0",95,[281,282,216,217,219,283],"ai-agents","llm","framework","global",{"commitSha":286,"license":245,"marketplace":287,"plugin":290},"HEAD",{"name":288,"pluginCount":289},"brainblend-plugins",1,{"mcpCount":8,"provider":291,"skillCount":8},"classify",{"repoId":293},"kd7038dvhwk39adrnvedmx8x3s86mqpq",[281,283,217,282,216,219],{"evaluatedAt":296,"extractAt":297,"updatedAt":298},1778683239491,1778683220959,1778683666542,{"evaluate":300,"extract":306},{"promptVersionExtension":208,"promptVersionScoring":209,"score":212,"tags":301,"targetMarket":284,"tier":220},[219,302,283,303,304,305],"agent","code-generation","development-tools","llm-application-development",{"commitSha":286,"license":245,"plugin":307},{"mcpCount":8,"provider":291,"skillCount":240},{"parentExtensionId":267,"repoId":293},[302,303,304,283,305,219],{"evaluatedAt":311,"extractAt":297,"updatedAt":312},1778683257368,1778683666777,{"evaluate":314,"extract":316},{"promptVersionExtension":208,"promptVersionScoring":209,"score":212,"tags":315,"targetMarket":284,"tier":220},[215,216,217,218,219],{"commitSha":286,"license":245},{"parentExtensionId":256,"repoId":293,"translatedFrom":318},"k170nd3h8zeayffrxe6pscxyy986m7em",{"_creationTime":320,"_id":293,"identity":321,"providers":322,"workflow":511},1778683214161.1255,{"githubOwner":251,"githubRepo":218,"sourceUrl":14},{"classify":323,"discover":498,"github":501},{"commitSha":286,"extensions":324},[325,338,363,372,380,388,394,402,431,439,464,473,482,491],{"basePath":274,"description":270,"displayName":288,"installMethods":326,"rationale":327,"selectedPaths":328,"source":337,"sourceLanguage":263,"type":275},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[329,332,334],{"path":330,"priority":331},".claude-plugin/marketplace.json","mandatory",{"path":333,"priority":331},"README.md",{"path":335,"priority":336},"LICENSE","high","rule",{"basePath":262,"description":259,"displayName":218,"installMethods":339,"license":245,"rationale":340,"selectedPaths":341,"source":337,"sourceLanguage":263,"type":264},{"claudeCode":218},"plugin manifest at claude-plugin/atomic-agents/.claude-plugin/plugin.json",[342,344,345,346,349,351,353,355,357,359,361],{"path":343,"priority":331},".claude-plugin/plugin.json",{"path":333,"priority":331},{"path":335,"priority":336},{"path":347,"priority":348},"skills/create-atomic-agent/SKILL.md","medium",{"path":350,"priority":348},"skills/create-atomic-context-provider/SKILL.md",{"path":352,"priority":348},"skills/create-atomic-schema/SKILL.md",{"path":354,"priority":348},"skills/create-atomic-tool/SKILL.md",{"path":356,"priority":348},"skills/framework/SKILL.md",{"path":358,"priority":348},"skills/new-app/SKILL.md",{"path":360,"priority":336},"agents/atomic-explorer.md",{"path":362,"priority":336},"agents/atomic-reviewer.md",{"basePath":364,"description":365,"displayName":366,"installMethods":367,"rationale":368,"selectedPaths":369,"source":337,"sourceLanguage":263,"type":253},".claude/skills/release","Release a new version of atomic-agents to PyPI and GitHub. Use when the user asks to \"release\", \"publish\", \"deploy\", or \"bump version\" for atomic-agents.","release",{"claudeCode":12},"SKILL.md frontmatter at .claude/skills/release/SKILL.md",[370],{"path":371,"priority":331},"SKILL.md",{"basePath":373,"description":374,"displayName":375,"installMethods":376,"rationale":377,"selectedPaths":378,"source":337,"sourceLanguage":263,"type":253},"claude-plugin/atomic-agents/skills/create-atomic-agent","Build and wire an `AtomicAgent[InSchema, OutSchema]` — schemas, `AgentConfig`, `SystemPromptGenerator`, provider client, history, hooks, optional context providers. Use when the user asks to \"create an agent\", \"add another agent\", \"build an `AtomicAgent`\", \"wire up an agent\", \"make a planner/router/extractor agent\", or runs `/atomic-agents:create-atomic-agent`.","create-atomic-agent",{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/create-atomic-agent/SKILL.md",[379],{"path":371,"priority":331},{"basePath":381,"description":382,"displayName":383,"installMethods":384,"rationale":385,"selectedPaths":386,"source":337,"sourceLanguage":263,"type":253},"claude-plugin/atomic-agents/skills/create-atomic-context-provider","Build a `BaseDynamicContextProvider` that injects a named, titled block into an agent's system prompt at every `run()` — current time, user identity, retrieved RAG docs, session state, cached DB schema. Use when the user asks to \"add a context provider\", \"inject X into the prompt\", \"give the agent dynamic context\", \"wire up RAG\", \"make a `BaseDynamicContextProvider`\", or runs `/atomic-agents:create-atomic-context-provider`.","create-atomic-context-provider",{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/create-atomic-context-provider/SKILL.md",[387],{"path":371,"priority":331},{"basePath":250,"description":389,"displayName":252,"installMethods":390,"rationale":391,"selectedPaths":392,"source":337,"sourceLanguage":263,"type":253},"Design and write a `BaseIOSchema` input/output pair for an Atomic Agents agent or tool — docstrings, field descriptions, validators, error variants. Use when the user asks to \"create a schema\", \"design the input/output schema\", \"define an `IOSchema`\", \"write a `BaseIOSchema`\", \"model the agent's output\", or runs `/atomic-agents:create-atomic-schema`.",{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/create-atomic-schema/SKILL.md",[393],{"path":371,"priority":331},{"basePath":395,"description":396,"displayName":397,"installMethods":398,"rationale":399,"selectedPaths":400,"source":337,"sourceLanguage":263,"type":253},"claude-plugin/atomic-agents/skills/create-atomic-tool","Build a `BaseTool[InSchema, OutSchema]` subclass — input/output schemas, `BaseToolConfig`, `run()` (and optional `run_async()`), env-driven secrets, typed failure outputs. Use when the user asks to \"add a tool\", \"create a tool\", \"wrap an API as a tool\", \"build a `BaseTool`\", \"make a calculator/search/weather tool\", or runs `/atomic-agents:create-atomic-tool`.","create-atomic-tool",{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/create-atomic-tool/SKILL.md",[401],{"path":371,"priority":331},{"basePath":403,"description":404,"displayName":283,"installMethods":405,"rationale":406,"selectedPaths":407,"source":337,"sourceLanguage":263,"type":253},"claude-plugin/atomic-agents/skills/framework","Guide for the Atomic Agents Python framework — schemas, agents, tools, context providers, prompts, orchestration, and provider configuration. Use when code imports from `atomic_agents`, defines an `AtomicAgent`, `BaseTool`, or `BaseIOSchema`, or the user asks about multi-agent orchestration or LLM-provider wiring in an atomic-agents project.",{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/framework/SKILL.md",[408,409,411,413,415,417,419,421,423,425,427,429],{"path":371,"priority":331},{"path":410,"priority":348},"references/agents.md",{"path":412,"priority":348},"references/context-providers.md",{"path":414,"priority":348},"references/hooks.md",{"path":416,"priority":348},"references/memory.md",{"path":418,"priority":348},"references/orchestration.md",{"path":420,"priority":348},"references/project-structure.md",{"path":422,"priority":348},"references/prompts.md",{"path":424,"priority":348},"references/providers.md",{"path":426,"priority":348},"references/schemas.md",{"path":428,"priority":348},"references/testing.md",{"path":430,"priority":348},"references/tools.md",{"basePath":432,"description":433,"displayName":434,"installMethods":435,"rationale":436,"selectedPaths":437,"source":337,"sourceLanguage":263,"type":253},"claude-plugin/atomic-agents/skills/new-app","Scaffold a new Atomic Agents project from scratch — create the directory, `pyproject.toml`, env file, first agent, and a runnable entry point. Use when the user asks to start a new atomic-agents project from scratch, says \"scaffold\" / \"new project\" / \"start from zero\", or runs `/atomic-agents:new-app`.","new-app",{"claudeCode":12},"SKILL.md frontmatter at claude-plugin/atomic-agents/skills/new-app/SKILL.md",[438],{"path":371,"priority":331},{"basePath":440,"displayName":441,"installMethods":442,"rationale":443,"selectedPaths":444,"source":337,"sourceLanguage":263,"type":463},"atomic-examples/mcp-agent/example-mcp-server","example-mcp-server",{"pypi":441},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/mcp-agent/example-mcp-server/pyproject.toml",[445,447,448,450,453,455,457,459,461],{"path":446,"priority":331},"pyproject.toml",{"path":333,"priority":331},{"path":449,"priority":348},"example_mcp_server/server.py",{"path":451,"priority":452},"example_mcp_server/tools/__init__.py","low",{"path":454,"priority":452},"example_mcp_server/tools/add_numbers.py",{"path":456,"priority":452},"example_mcp_server/tools/batch_operations.py",{"path":458,"priority":452},"example_mcp_server/tools/divide_numbers.py",{"path":460,"priority":452},"example_mcp_server/tools/multiply_numbers.py",{"path":462,"priority":452},"example_mcp_server/tools/subtract_numbers.py","mcp",{"basePath":465,"displayName":466,"installMethods":467,"rationale":468,"selectedPaths":469,"source":337,"sourceLanguage":263,"type":463},"atomic-examples/progressive-disclosure/servers/data_server","pd-data-server",{"pypi":466},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/progressive-disclosure/servers/data_server/pyproject.toml",[470,471],{"path":446,"priority":331},{"path":472,"priority":348},"data_server/server.py",{"basePath":474,"displayName":475,"installMethods":476,"rationale":477,"selectedPaths":478,"source":337,"sourceLanguage":263,"type":463},"atomic-examples/progressive-disclosure/servers/math_server","pd-math-server",{"pypi":475},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/progressive-disclosure/servers/math_server/pyproject.toml",[479,480],{"path":446,"priority":331},{"path":481,"priority":348},"math_server/server.py",{"basePath":483,"displayName":484,"installMethods":485,"rationale":486,"selectedPaths":487,"source":337,"sourceLanguage":263,"type":463},"atomic-examples/progressive-disclosure/servers/text_server","pd-text-server",{"pypi":484},"pyproject.toml with mcp/fastmcp dependency + scripts at atomic-examples/progressive-disclosure/servers/text_server/pyproject.toml",[488,489],{"path":446,"priority":331},{"path":490,"priority":348},"text_server/server.py",{"basePath":274,"displayName":218,"installMethods":492,"rationale":493,"selectedPaths":494,"source":337,"sourceLanguage":263,"type":463},{"pypi":218},"pyproject.toml with mcp/fastmcp dependency + scripts at pyproject.toml",[495,496,497],{"path":446,"priority":331},{"path":333,"priority":331},{"path":335,"priority":336},{"sources":499},[500],"manual",{"closedIssues90d":238,"description":502,"forks":239,"license":245,"openIssues90d":240,"pushedAt":241,"readmeSize":236,"stars":242,"topics":503},"Building AI agents, atomically",[504,505,506,507,508,509,510],"ai","artificial-intelligence","large-language-model","large-language-models","llms","openai","openai-api",{"classifiedAt":512,"discoverAt":513,"extractAt":514,"githubAt":514,"updatedAt":512},1778683220596,1778683214161,1778683218333,[218,217,216,219,215],{"evaluatedAt":517,"extractAt":297,"updatedAt":248},1778683329867,[],[520,542,574,599,630,663],{"_creationTime":521,"_id":522,"community":523,"display":524,"identity":528,"providers":529,"relations":536,"tags":538,"workflow":539},1778683565597.3582,"k179v0t3brjq9ge89jt697x39186mwa2",{"reviewCount":8},{"description":525,"installMethods":526,"name":527,"sourceUrl":14},"Erstellen Sie eine `BaseTool[InSchema, OutSchema]`-Unterklasse — Eingabe-/Ausgabeschemata, `BaseToolConfig`, `run()` (und optional `run_async()`), umgebungsgesteuerte Geheimnisse, typisierte Fehler-Outputs. Verwenden Sie dies, wenn der Benutzer fragt, \"ein Werkzeug hinzuzufügen\", \"ein Werkzeug zu erstellen\", \"eine API als Werkzeug zu verpacken\", \"eine `BaseTool` zu bauen\", \"ein Werkzeug für Berechnungen/Suche/Wetter zu erstellen\" oder `/atomic-agents:create-atomic-tool` ausführt.",{"claudeCode":12},"Create Atomic Tool",{"basePath":395,"githubOwner":251,"githubRepo":218,"locale":18,"slug":397,"type":253},{"evaluate":530,"extract":535},{"promptVersionExtension":208,"promptVersionScoring":209,"score":531,"tags":532,"targetMarket":284,"tier":220},99,[219,303,533,534,216,217],"developer-tools","agent-framework",{"commitSha":286,"license":245},{"parentExtensionId":256,"repoId":293,"translatedFrom":537},"k17etfv7gy0r843nssf7yy7em586nxja",[534,303,533,217,216,219],{"evaluatedAt":540,"extractAt":297,"updatedAt":541},1778683348543,1778683565597,{"_creationTime":543,"_id":544,"community":545,"display":546,"identity":552,"providers":556,"relations":567,"tags":570,"workflow":571},1778695116697.1924,"k1714hg6p3104jz49mqr6yn47s86nz7n",{"reviewCount":8},{"description":547,"installMethods":548,"name":550,"sourceUrl":551},"Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library",{"claudeCode":549},"Orchestra-Research/AI-Research-SKILLs","Instructor","https://github.com/Orchestra-Research/AI-Research-SKILLs",{"basePath":553,"githubOwner":554,"githubRepo":555,"locale":263,"slug":217,"type":253},"16-prompt-engineering/instructor","Orchestra-Research","AI-Research-SKILLs",{"evaluate":557,"extract":566},{"promptVersionExtension":208,"promptVersionScoring":209,"score":212,"tags":558,"targetMarket":284,"tier":220},[559,217,560,216,561,562,563,564,565],"prompt-engineering","structured-output","data-extraction","json-parsing","type-safety","validation","streaming",{"commitSha":286,"license":245},{"parentExtensionId":568,"repoId":569},"k17155ws9qc0hw7a568bg79sfd86max8","kd70hj1y80mhra5xm5g188j5n586mg18",[561,217,562,559,216,565,560,563,564],{"evaluatedAt":572,"extractAt":573,"updatedAt":572},1778697010260,1778695116697,{"_creationTime":575,"_id":576,"community":577,"display":578,"identity":582,"providers":587,"relations":593,"tags":595,"workflow":596},1778685991755.7273,"k175b8b0kpk0gsz87sd34639z586nn67",{"reviewCount":8},{"description":547,"installMethods":579,"name":217,"sourceUrl":581},{"claudeCode":580},"davila7/claude-code-templates","https://github.com/davila7/claude-code-templates",{"basePath":583,"githubOwner":584,"githubRepo":585,"locale":263,"slug":586,"type":253},"cli-tool/components/skills/ai-research/prompt-engineering-instructor","davila7","claude-code-templates","prompt-engineering-instructor",{"evaluate":588,"extract":592},{"promptVersionExtension":208,"promptVersionScoring":209,"score":589,"tags":590,"targetMarket":284,"tier":591},75,[559,217,560,216,561,282],"community",{"commitSha":286},{"repoId":594},"kd71fzn4s7r0269fkw47wt670n86ndz0",[561,217,282,559,216,560],{"evaluatedAt":597,"extractAt":598,"updatedAt":597},1778688700350,1778685991755,{"_creationTime":600,"_id":601,"community":602,"display":603,"identity":609,"providers":613,"relations":623,"tags":626,"workflow":627},1778699018122.8064,"k178yxvt3g9djb8ph907q3tv1186n8ex",{"reviewCount":8},{"description":604,"installMethods":605,"name":607,"sourceUrl":608},"Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.",{"claudeCode":606},"wshobson/agents","embedding-strategies","https://github.com/wshobson/agents",{"basePath":610,"githubOwner":611,"githubRepo":612,"locale":263,"slug":607,"type":253},"plugins/llm-application-dev/skills/embedding-strategies","wshobson","agents",{"evaluate":614,"extract":622},{"promptVersionExtension":208,"promptVersionScoring":209,"score":615,"tags":616,"targetMarket":284,"tier":220},100,[617,618,619,620,621,219],"embeddings","rag","semantic-search","vector-databases","llm-applications",{"commitSha":286},{"parentExtensionId":624,"repoId":625},"k1719fyk9jrke6aq23wbyf8ej586n3af","kd74de64zj0axtg5b8t7eqqe2x86nske",[617,621,219,618,619,620],{"evaluatedAt":628,"extractAt":629,"updatedAt":628},1778701750946,1778699018122,{"_creationTime":631,"_id":632,"community":633,"display":634,"identity":640,"providers":644,"relations":654,"tags":658,"workflow":659},1778699877608.8755,"k1797ahn9dp86gj0yfve225q2n86mv13",{"reviewCount":8},{"description":635,"installMethods":636,"name":638,"sourceUrl":639},"AWS Cloud Development Kit (CDK) Experte für den Aufbau von Cloud-Infrastruktur mit TypeScript/Python. Verwenden Sie dies beim Erstellen von CDK-Stacks, Definieren von CDK-Konstrukten, Implementieren von Infrastructure as Code oder wenn der Benutzer CDK, CloudFormation, IaC, cdk synth, cdk deploy erwähnt oder AWS-Infrastruktur programmatisch definieren möchte. Behandelt CDK-App-Struktur, Konstruktmuster, Stack-Komposition und Bereitstellungs-Workflows.",{"claudeCode":637},"zxkane/aws-skills","aws-cdk-development","https://github.com/zxkane/aws-skills",{"basePath":641,"githubOwner":642,"githubRepo":643,"locale":18,"slug":638,"type":253},"plugins/aws-cdk/skills/aws-cdk-development","zxkane","aws-skills",{"evaluate":645,"extract":653},{"promptVersionExtension":208,"promptVersionScoring":209,"score":615,"tags":646,"targetMarket":284,"tier":220},[647,648,649,219,650,651,652],"aws","cdk","typescript","iac","cloudformation","infrastructure",{"commitSha":286},{"parentExtensionId":655,"repoId":656,"translatedFrom":657},"k177paz2fgaa1r1kfhgb2esr1n86my7m","kd7708aervxaq6vqq9tdf93s2586mcqy","k174bzyyax9v1t5bm0m98bfqyh86m8v8",[647,648,651,650,652,219,649],{"evaluatedAt":660,"extractAt":661,"updatedAt":662},1778699774404,1778699647844,1778699877608,{"_creationTime":664,"_id":665,"community":666,"display":667,"identity":673,"providers":677,"relations":685,"tags":688,"workflow":689},1778695548458.3613,"k17dx6tyy2yb3z5pp1vgmg46ad86nm18",{"reviewCount":8},{"description":668,"installMethods":669,"name":671,"sourceUrl":672},"Fit cognitive drift-diffusion models (Ratcliff DDM) to reaction time and accuracy data with parameter estimation (drift rate, boundary separation, non-decision time), model comparison, and parameter recovery validation. Use when modeling binary decision-making with reaction time data, estimating cognitive parameters from experimental data, comparing sequential sampling model variants, or decomposing speed-accuracy tradeoff effects into latent cognitive components.\n",{"claudeCode":670},"pjt222/agent-almanac","fit-drift-diffusion-model","https://github.com/pjt222/agent-almanac",{"basePath":674,"githubOwner":675,"githubRepo":676,"locale":263,"slug":671,"type":253},"skills/fit-drift-diffusion-model","pjt222","agent-almanac",{"evaluate":678,"extract":684},{"promptVersionExtension":208,"promptVersionScoring":209,"score":615,"tags":679,"targetMarket":284,"tier":220},[680,681,682,219,683],"cognitive-science","modeling","statistics","data-analysis",{"commitSha":286},{"parentExtensionId":686,"repoId":687},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[680,683,681,219,682],{"evaluatedAt":690,"extractAt":691,"updatedAt":690},1778698191612,1778695548458]