[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-langchain-ai-deep-agents-core-en":3,"guides-for-langchain-ai-deep-agents-core":254,"similar-k17b4azxqtakm78mxatx1sst0d867h79":255},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":21,"identity":182,"isFallback":178,"parentExtension":187,"providers":232,"relations":235,"repo":236,"workflow":253},1778053782268.1968,"k17b4azxqtakm78mxatx1sst0d867h79",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.",{},"Deep Agents Core","https://github.com/langchain-ai/langchain-skills/tree/HEAD/config/skills/deep-agents-core",[15,16,17,18,19,20],"deep-agents","langchain","langgraph","agent-framework","python","typescript",{"_creationTime":22,"_id":23,"extensionId":5,"locale":24,"result":25,"trustSignals":171,"workflow":180},1778053822111.3508,"kn73zskrb3y621q96b3vw09cqn86703p","en",{"checks":26,"evaluatedAt":161,"extensionSummary":162,"promptVersionExtension":163,"promptVersionScoring":164,"rationale":165,"score":166,"summary":167,"tags":168,"targetMarket":169,"tier":170},[27,32,35,39,43,47,51,54,58,62,66,69,72,75,79,82,85,88,91,94,98,102,106,109,112,115,118,121,124,127,130,134,139,142,145,148,151,155,158],{"category":28,"check":29,"severity":30,"summary":31},"Invocation","Precise Purpose","pass","The description clearly states the purpose of the skill: building Deep Agents applications, and lists specific areas covered: create_deep_agent(), harness architecture, SKILL.md format, and configuration options. It also provides a 'when-to-use' table differentiating it from simpler LangChain agents.",{"category":28,"check":33,"severity":30,"summary":34},"Concise Frontmatter","The frontmatter is concise and self-contained, providing a clear summary of the core capability and listing specific areas covered within the initial ~160 characters.",{"category":36,"check":37,"severity":30,"summary":38},"Documentation","Concise Body","The main SKILL.md file is under 500 lines and delegates deeper material to separate files like examples and configuration sections, adhering to progressive disclosure.",{"category":40,"check":41,"severity":30,"summary":42},"Context","Progressive Disclosure","The SKILL.md outlines the Deep Agents flow and links to separate sections for specific configurations and examples, demonstrating progressive disclosure.",{"category":40,"check":44,"severity":45,"summary":46},"Forked exploration","not_applicable","This skill focuses on core architecture and setup rather than deep exploration or code review, so the `context: fork` setting is not applicable.",{"category":48,"check":49,"severity":30,"summary":50},"Practical Utility","Usage examples","The SKILL.md includes comprehensive, ready-to-use examples for both Python and TypeScript, demonstrating basic agent creation and full configuration, with clear inputs and expected outcomes.",{"category":48,"check":52,"severity":30,"summary":53},"Edge cases","The documentation covers edge cases and limitations, such as the requirement for a checkpointer with interrupts and the need for a Store instance with StoreBackend, providing clear recovery steps.",{"category":55,"check":56,"severity":45,"summary":57},"Code Execution","Tool Fallback","This skill does not appear to rely on external tools like MCP servers that would require a fallback mechanism; it focuses on the Deep Agents framework itself.",{"category":59,"check":60,"severity":30,"summary":61},"Safety","Halt on unexpected state","The documentation implicitly covers expected states by showing correct setup for checkpointers and stores, and the examples demonstrate how to properly configure the agent, implying a halt on unexpected states.",{"category":63,"check":64,"severity":30,"summary":65},"Portability","Cross-skill coupling","The skill is self-contained and focuses on the core Deep Agents framework, without implicit reliance on other skills. It clearly defines its scope.",{"category":48,"check":67,"severity":30,"summary":68},"Problem relevance","The description explicitly names the user problem: building ANY Deep Agents application, and covers key aspects like create_deep_agent(), harness architecture, and SKILL.md format.",{"category":48,"check":70,"severity":30,"summary":71},"Unique selling proposition","The skill offers significant value over a simple prompt by providing a structured framework (Deep Agents) with built-in middleware for task planning, context management, delegation, memory, and human-in-the-loop workflows, which is beyond default LangChain capabilities.",{"category":48,"check":73,"severity":30,"summary":74},"Production readiness","The skill provides comprehensive setup instructions and examples for Python and TypeScript, covering a full configuration with persistence and skills, indicating it's ready for use in production workflows.",{"category":76,"check":77,"severity":30,"summary":78},"Scope","Single responsibility principle","The skill focuses solely on the Deep Agents core architecture, its harness setup, and SKILL.md format, without extending into unrelated domains like testing or deployment.",{"category":76,"check":80,"severity":30,"summary":81},"Description quality","The description is accurate, concise, readable, and directly reflects the skill's documented purpose and capabilities.",{"category":28,"check":83,"severity":30,"summary":84},"Scoped tools","The skill describes built-in tools like `write_todos`, `ls`, `read_file`, `write_file`, `edit_file`, `glob`, `grep`, and `task`, which are narrow verb-noun specialists.",{"category":36,"check":86,"severity":30,"summary":87},"Configuration & parameter reference","The examples clearly demonstrate configuration options for models, tools, system prompts, backends, interrupts, skills, checkpointers, and stores, implicitly covering all necessary parameters.",{"category":76,"check":89,"severity":30,"summary":90},"Tool naming","The built-in tools (`write_todos`, `ls`, `read_file`, `write_file`, `edit_file`, `glob`, `grep`, `task`) are descriptive and follow a consistent verb-noun naming convention.",{"category":76,"check":92,"severity":30,"summary":93},"Minimal I/O surface","The tool descriptions and examples imply that inputs are structured (e.g., city name for get_weather, directory paths for filesystem tools) and outputs are task-specific, without excessive diagnostic dumps.",{"category":95,"check":96,"severity":45,"summary":97},"License","License usability","No explicit license file or SPDX identifier was found in the repository files provided. The README mentions a 'langchain-ai' GitHub organization which typically uses permissive licenses, but this cannot be confirmed without a LICENSE file.",{"category":99,"check":100,"severity":45,"summary":101},"Maintenance","Commit recency","No commit date information was provided for the repository.",{"category":103,"check":104,"severity":30,"summary":105},"Security","Secret Management","The documentation does not show any examples of secrets being hardcoded or echoed to stdout. It mentions API keys should be set as environment variables, which is standard practice.",{"category":103,"check":107,"severity":30,"summary":108},"Injection","The skill's focus on framework setup and its use of structured tools and configurations suggest it does not load or execute untrusted external data as instructions.",{"category":103,"check":110,"severity":30,"summary":111},"Transitive Supply-Chain Grenades","The skill does not appear to fetch remote content at runtime or execute arbitrary commands, and all its components seem to be bundled within the repository.",{"category":103,"check":113,"severity":30,"summary":114},"Sandbox Isolation","The skill's operations are confined to framework configuration and tool definitions; it does not appear to interact with or modify files outside its defined scope.",{"category":103,"check":116,"severity":30,"summary":117},"Sandbox escape primitives","There are no indications of detached process spawns or retry loops around denied tool calls in the provided documentation or examples.",{"category":103,"check":119,"severity":30,"summary":120},"Data Exfiltration","The skill's purpose is framework setup, and there are no outbound calls to undocumented destinations or any mechanisms for exfiltrating confidential data.",{"category":103,"check":122,"severity":30,"summary":123},"Hidden Text Tricks","The bundled content appears to be free of hidden steering tricks, invisible Unicode characters, or other obfuscation methods.",{"category":103,"check":125,"severity":30,"summary":126},"Opaque code execution","The provided code examples for Python and TypeScript are clear and readable, with no signs of obfuscation, base64-encoded payloads, or runtime code fetching.",{"category":63,"check":128,"severity":30,"summary":129},"Structural Assumption","The skill demonstrates code examples that are either self-contained or use standard path conventions (`./skills/`, `~/my-project/`), avoiding assumptions about specific user project layouts.",{"category":131,"check":132,"severity":45,"summary":133},"Trust","Issues Attention","No issue tracking data was provided.",{"category":135,"check":136,"severity":137,"summary":138},"Versioning","Release Management","warning","No manifest version, GitHub release tags, or CHANGELOG were found. The installation instructions reference `main` or specific branches, preventing precise version pinning.",{"category":55,"check":140,"severity":30,"summary":141},"Validation","The skill's examples implicitly show validation through typed function signatures and schema definitions (e.g., `zod` in TypeScript) for tool inputs, and the framework itself likely handles internal validation.",{"category":103,"check":143,"severity":30,"summary":144},"Unguarded Destructive Operations","The skill focuses on framework configuration and does not expose or use primitives for destructive operations without guards.",{"category":55,"check":146,"severity":30,"summary":147},"Error Handling","The examples and documentation suggest that the Deep Agents framework handles errors robustly, with explicit mention of checkpointers for interrupts and structured storage for memory, implying proper error categorization and reporting.",{"category":55,"check":149,"severity":45,"summary":150},"Logging","This skill primarily deals with configuration and framework setup, not destructive actions or outbound calls that would necessitate local audit logging.",{"category":152,"check":153,"severity":30,"summary":154},"Compliance","GDPR","The skill's purpose is framework configuration, and it does not appear to operate on or submit personal data.",{"category":152,"check":156,"severity":30,"summary":157},"Target market","The skill is designed as a general agent framework with examples in both Python and TypeScript, and there are no regional signals indicating it is restricted to a specific market.",{"category":63,"check":159,"severity":30,"summary":160},"Runtime stability","The skill provides examples for both Python and TypeScript and mentions compatibility with various agents (Claude Code, Cursor, Windsurf), indicating good cross-platform stability.",1778053796077,"This skill provides the core architecture for Deep Agents, including harness setup, SKILL.md formatting, and configuration options for middleware like task planning, context management, and sub-agent delegation. It includes ready-to-use examples for Python and TypeScript.","2.0.0","3.4.0","The 'deep-agents-core' skill is well-documented, production-ready, and adheres to best practices for scope and security. Its primary weakness is the lack of clear versioning information, which impacts reproducibility. Despite this, its strong adherence to other quality checks warrants a high score and 'verified' tier.",93,"A foundational skill for setting up Deep Agents applications with comprehensive documentation and examples.",[15,16,17,18,19,20],"global","verified",{"codeQuality":172,"collectedAt":173,"documentation":174,"maintenance":176,"security":177,"testCoverage":179},{},1778053784682,{"descriptionLength":175,"readmeSize":8},154,{},{"hasNpmPackage":178,"smitheryVerified":178},false,{"hasCi":178,"hasTests":178},{"updatedAt":181},1778053822111,{"githubOwner":183,"githubRepo":184,"locale":24,"slug":185,"type":186},"langchain-ai","langchain-skills","deep-agents-core","skill",{"_creationTime":188,"_id":189,"community":190,"display":191,"identity":201,"parentExtension":203,"providers":226,"relations":230,"workflow":231},1778053782268.1963,"k1710b29xhgdykchws1tmnjrnx866nxv",{"reviewCount":8},{"description":192,"installMethods":193,"name":194,"sourceUrl":195,"tags":196},"Agent skills for building agents with LangChain, LangGraph, and Deep Agents",{},"LangChain Skills","https://github.com/langchain-ai/langchain-skills",[16,17,15,197,198,199,200],"ai-agents","rag","skills","plugins",{"githubOwner":183,"githubRepo":184,"locale":24,"slug":184,"type":202},"plugin",{"_creationTime":204,"_id":205,"community":206,"display":207,"identity":210,"providers":212,"relations":221,"workflow":223},1778053782268.1958,"k1787v8f6tx7dxy8c4xfz7hk2h867f5j",{"reviewCount":8},{"description":192,"installMethods":208,"name":194,"sourceUrl":195,"tags":209},{},[16,17,15,197,198],{"githubOwner":183,"githubRepo":184,"locale":24,"slug":184,"type":211},"marketplace",{"extract":213,"llm":218},{"commitSha":214,"license":215,"marketplace":216},"648df5daa32ef7a742a07740d9c5d13e3b8229c4","MIT",{"name":184,"pluginCount":217},1,{"promptVersionExtension":163,"promptVersionScoring":164,"score":219,"targetMarket":169,"tier":220},70,"evaluated",{"repoId":222},"kd74nzm561ws7px2qx08z27fad864yft",{"anyEnrichmentAt":224,"extractAt":225,"githubAt":224,"llmAt":181,"updatedAt":181},1778053782949,1778053782268,{"extract":227,"llm":228},{"commitSha":214,"license":215},{"promptVersionExtension":163,"promptVersionScoring":164,"score":229,"targetMarket":169,"tier":220},75,{"parentExtensionId":205,"repoId":222},{"anyEnrichmentAt":224,"extractAt":225,"githubAt":224,"llmAt":181,"updatedAt":181},{"extract":233,"llm":234},{"commitSha":214,"license":45},{"promptVersionExtension":163,"promptVersionScoring":164,"score":166,"targetMarket":169,"tier":170},{"parentExtensionId":189,"repoId":222},{"_creationTime":237,"_id":222,"identity":238,"providers":239,"workflow":250},1777995558409.8423,{"githubOwner":183,"githubRepo":184,"sourceUrl":195},{"discover":240,"github":243},{"sources":241},[242],"skills-sh",{"closedIssues90d":244,"forks":245,"openIssues90d":8,"pushedAt":246,"readmeSize":247,"stars":248,"topics":249},2,58,1777486877000,3660,651,[],{"discoverAt":251,"extractAt":252,"githubAt":252,"updatedAt":252},1777995558409,1778053783581,{"anyEnrichmentAt":224,"extractAt":225,"githubAt":224,"llmAt":181,"updatedAt":181},[],[256,275,296,329,356,385],{"_creationTime":257,"_id":258,"community":259,"display":260,"identity":268,"providers":269,"relations":273,"workflow":274},1778053782268.1982,"k17c7a6x1535rf64abc4aj73d18673he",{"reviewCount":8},{"description":261,"installMethods":262,"name":263,"sourceUrl":264,"tags":265},"INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.",{},"Framework Selection","https://github.com/langchain-ai/langchain-skills/tree/HEAD/config/skills/framework-selection",[16,17,15,266,267],"framework-selection","documentation",{"githubOwner":183,"githubRepo":184,"locale":24,"slug":266,"type":186},{"extract":270,"llm":271},{"commitSha":214,"license":215},{"promptVersionExtension":163,"promptVersionScoring":164,"score":272,"targetMarket":169,"tier":170},95,{"parentExtensionId":189,"repoId":222},{"anyEnrichmentAt":224,"extractAt":225,"githubAt":224,"llmAt":181,"updatedAt":181},{"_creationTime":276,"_id":277,"community":278,"display":279,"identity":289,"providers":291,"relations":294,"workflow":295},1778053782268.1978,"k17e86mrthw9p3ka6b379d4nfs867gae",{"reviewCount":8},{"description":280,"installMethods":281,"name":282,"sourceUrl":283,"tags":284},"INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.",{},"Deep Agents Orchestration","https://github.com/langchain-ai/langchain-skills/tree/HEAD/config/skills/deep-agents-orchestration",[15,285,286,287,288,16,17],"orchestration","subagents","task-planning","human-in-the-loop",{"githubOwner":183,"githubRepo":184,"locale":24,"slug":290,"type":186},"deep-agents-orchestration",{"extract":292,"llm":293},{"commitSha":214,"license":215},{"promptVersionExtension":163,"promptVersionScoring":164,"score":272,"targetMarket":169,"tier":170},{"parentExtensionId":189,"repoId":222},{"anyEnrichmentAt":224,"extractAt":225,"githubAt":224,"llmAt":181,"updatedAt":181},{"_creationTime":297,"_id":298,"community":299,"display":300,"identity":311,"providers":315,"relations":322,"workflow":324},1777995614337.9844,"k17f0xfg2pkfqd1p5jjzh8sswh8645px",{"reviewCount":8},{"description":301,"installMethods":302,"name":303,"sourceUrl":304,"tags":305},"Scaffold an editable Tandem control panel app",{},"Tandem Panel Scaffold","https://github.com/frumu-ai/tandem/tree/HEAD/packages/create-tandem-panel",[306,307,308,20,309,310],"scaffolding","cli","react","vite","ui",{"githubOwner":312,"githubRepo":313,"locale":24,"slug":314,"type":186},"frumu-ai","tandem","create-tandem-panel",{"extract":316,"llm":319,"smithery":321},{"commitSha":317,"license":318},"25c8ae7c2f8b20d576a2b8d44946ac2e0ff9408d","MIT OR Apache-2.0",{"promptVersionExtension":163,"promptVersionScoring":164,"score":320,"targetMarket":169,"tier":170},100,{"qualityScore":8,"totalActivations":8,"uniqueUsers":8,"useCount":8,"verified":178},{"repoId":323},"kd72pd305er4m7vecv9p6mnd4s865kea",{"anyEnrichmentAt":325,"extractAt":326,"githubAt":327,"llmAt":328,"smitheryAt":325,"updatedAt":328},1777995723550,1777995614338,1777995614791,1777995897177,{"_creationTime":330,"_id":331,"community":332,"display":333,"identity":342,"providers":345,"relations":350,"workflow":352},1778054425877.1958,"k171ck7gyw157xcvkrk6k0r9y1866w01",{"reviewCount":8},{"description":334,"name":335,"sourceUrl":336,"tags":337},"ESLint rules for React Hooks","ESLint Plugin React Hooks","https://github.com/facebook/react/tree/HEAD/packages/eslint-plugin-react-hooks",[308,338,339,340,341,20],"eslint","linting","hooks","javascript",{"githubOwner":343,"githubRepo":308,"locale":24,"slug":344,"type":186},"facebook","eslint-plugin-react-hooks",{"extract":346,"llm":348},{"commitSha":347,"license":215},"9635257c1b557acc81f95b1e974a54c752e703a2",{"promptVersionExtension":163,"promptVersionScoring":164,"score":349,"targetMarket":169,"tier":170},99,{"repoId":351},"kd73v9dy7vwq94hgzc7eh43b9s865rhq",{"anyEnrichmentAt":353,"extractAt":354,"githubAt":353,"llmAt":355,"updatedAt":355},1778054428301,1778054425877,1778054588390,{"_creationTime":357,"_id":358,"community":359,"display":360,"identity":373,"providers":375,"relations":379,"workflow":381},1778053689272.9238,"k17a5hw81fhwybk1wxavs6mvjs8676ca",{"reviewCount":8},{"description":361,"installMethods":362,"name":363,"sourceUrl":364,"tags":365},"Set up a new Prisma Postgres database and connect it to a local project using the Management API. Use when asked to \"set up a database\", \"create a Prisma Postgres project\", \"get a connection string\", \"connect my app to Prisma Postgres\", or \"provision a database\".",{},"Prisma Postgres Setup","https://github.com/prisma/skills/tree/HEAD/prisma-postgres-setup",[366,367,368,369,370,371,20,372],"prisma","postgres","database","setup","connection","api","node-js",{"githubOwner":366,"githubRepo":199,"locale":24,"slug":374,"type":186},"prisma-postgres-setup",{"extract":376,"llm":378},{"commitSha":377,"license":215},"741a74fdafc1bf61fa208c2f73878be688cba263",{"promptVersionExtension":163,"promptVersionScoring":164,"score":349,"targetMarket":169,"tier":170},{"repoId":380},"kd76h7swxyhk8405svecsqq7gh864y5s",{"anyEnrichmentAt":382,"extractAt":383,"githubAt":382,"llmAt":384,"updatedAt":384},1778053689723,1778053689272,1778053716548,{"_creationTime":386,"_id":387,"community":388,"display":389,"identity":401,"providers":404,"relations":410,"workflow":412},1777995645703.244,"k174tj4zmxrkh9kz1sgs8w3ts9865y61",{"reviewCount":8},{"description":390,"installMethods":391,"name":392,"sourceUrl":393,"tags":394},"BuyWhere tools for LangChain - product search, price comparison, and deals as LangChain tools",{},"BuyWhere LangChain Tools","https://github.com/BuyWhere/buywhere/tree/HEAD/packages/buywhere-langchain",[395,16,396,397,398,399,400,20],"buywhere","ecommerce","product-search","price-comparison","deals","sdk",{"githubOwner":402,"githubRepo":395,"locale":24,"slug":403,"type":186},"BuyWhere","buywhere-langchain",{"extract":405,"llm":407,"smithery":409},{"commitSha":406,"license":215},"2083d92e71185b754d867eae453dc21e471f33d2",{"promptVersionExtension":163,"promptVersionScoring":164,"score":408,"targetMarket":169,"tier":170},98,{"qualityScore":8,"totalActivations":8,"uniqueUsers":8,"useCount":8,"verified":178},{"repoId":411},"kd76sh9s8596jy0g347p8xyj6d865494",{"anyEnrichmentAt":325,"extractAt":413,"githubAt":414,"llmAt":328,"smitheryAt":325,"updatedAt":328},1777995645703,1777995646287]