Labsco
langchain-ai logo

langchain-ai / skills-benchmarks

★ 108

A skill package that teaches your agent 15 capabilities — every one documented and browsable below, no GitHub required · by langchain-ai.

Each skill below is one capability this package teaches your agent. Install the whole package, or open a skill to install just that one.

deep-agents-core🔥🔥🔥🔥✓ VerifiedFreeQuick setup

INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.

1 file — installable on its own

→
deep-agents-memory🔥🔥🔥🔥✓ VerifiedFreeQuick setup

INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent),…

1 file — installable on its own

→
deep-agents-orchestration🔥🔥🔥🔥✓ VerifiedFreeQuick setup

INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.

1 file — installable on its own

→
framework-selection🔥🔥🔥🔥✓ VerifiedFreeQuick setup

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…

1 file — installable on its own

→
langchain-dependencies🔥🔥🔥🔥✓ VerifiedFreeQuick setup

INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph,…

1 file — installable on its own

→
langchain-fundamentals🔥🔥🔥🔥✓ VerifiedFreeQuick setup

Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.

1 file — installable on its own

→
langchain-middleware🔥🔥🔥🔥✓ VerifiedFreeQuick setup

INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of…

1 file — installable on its own

→
langchain-oss-primer🔥🔥🔥✓ VerifiedFreeQuick setup

ALWAYS START HERE for any LangChain, Deep Agents, or LangGraph agent building project. Required starting point before choosing other skills or writing any…

1 file — installable on its own

→
langchain-rag🔥🔥FreeQuick setup

langchain-rag — an installable skill for AI agents, published by langchain-ai/skills-benchmarks.

1 file — installable on its own

→
langgraph-fundamentals🔥🔥🔥🔥✓ VerifiedFreeQuick setup

INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.

1 file — installable on its own

→
langgraph-human-in-the-loop🔥🔥🔥🔥✓ VerifiedFreeQuick setup

INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...),…

1 file — installable on its own

→
langgraph-persistence🔥🔥🔥🔥✓ VerifiedFreeQuick setup

INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping.…

1 file — installable on its own

→
langsmith-dataset🔥🔥🔥✓ VerifiedFreeQuick setup

INVOKE THIS SKILL when creating evaluation datasets, uploading datasets to LangSmith, or managing existing datasets. Covers dataset types (final_response,…

1 file — installable on its own

→
langsmith-evaluator🔥🔥🔥✓ VerifiedFreeQuick setup

INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2)…

1 file — installable on its own

→
langsmith-trace🔥🔥🔥✓ VerifiedFreeQuick setup

INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the…

24 files — installable on its own

→