Public Agent Skills by langchain-ai on Lightlines.
Finds relevant arXiv papers and retrieves their titles and abstracts.
Configures Deep Agents with ephemeral, persistent, hybrid, or filesystem-backed memory and file operations.
Selects the appropriate agent-building layer and directs the agent to current setup guidance, documentation, and follow-on skills.
Build production LangChain agents with create_agent(), tools, and middleware.
Builds retrieval-augmented generation systems that fetch relevant context for LLM responses.
Manages the lifecycle of LangGraph applications from project scaffolding through local development and platform deployment.
Builds LangGraph applications with stateful nodes, routing, execution, streaming, and error handling.
Configure LangGraph persistence for checkpointed state, thread-scoped conversations, cross-thread memory, time travel, and subgraph scoping.
Creates, uploads, and manages evaluation datasets in LangSmith for testing and validation.
Builds LangSmith evaluation pipelines with evaluators, run functions, and local or uploaded evaluation runs.
Creates and verifies one LangSmith online evaluator at a time through trace inspection and user-guided iteration.
Adds tracing to applications and queries or exports LangSmith trace data.
Builds, tests, and deploys a code-first Managed Deep Agent after matching the user's requirements to supported capabilities.
Writes and executes SQL queries to retrieve, filter, aggregate, and report database data.
Processes independent work items in parallel and merges their structured results into a table.
Produces a cited research synthesis by dividing an online question among delegated researchers.