Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Covers StateGraph, state schemas, nodes, and edges for LangGraph development. Includes Command, Send, invocation, streaming, and error handling.
Covers human-in-the-loop workflows with interrupt() and Command(resume=...). Includes approval and validation patterns plus a four-tier error handling strategy.
Covers checkpointers, thread_id, Store, and time travel for persistent LangGraph applications. Includes subgraph persistence modes and checkpointer scoping.
Follows the official quickstart to scaffold a minimal LangGraph agent in Python. Supports quickly building or trying an agent locally.
Follows the official quickstart to scaffold a minimal LangGraph agent in TypeScript. Supports quickly building or trying an agent locally.
Covers final_response, single_step, trajectory, and RAG evaluation datasets. Supports CLI management, SDK-based creation, uploading, and example management using LangSmith tooling.
Creates LLM-as-judge and custom code evaluators and defines run functions that capture agent outputs and trajectories. Runs evaluations locally with evaluate() or automatically through LangSmith, using its CLI tooling.
Retrieves recent execution traces from LangSmith Studio and analyzes execution patterns. Supports investigating agent errors, tool calls, memory operations, and performance, and requires the langsmith-fetch CLI.
Iteratively inspects traces, interviews users, and creates online evaluators one at a time for LangSmith. Its scope is LangSmith evaluators; Harbor-style evaluations are handled by eval-engineering.
Covers instrumenting applications with LangSmith tracing. Uses the LangSmith CLI to query and export trace data.
Translates speech into another language and returns a synchronized dubbed video while preserving each speaker's voice. Lip sync is enabled by default, with bilingual subtitles supported for dubbed output. It excludes caption-only, transcription-only, and on-screen text translation tasks.
Defines language-specific standards for strict, type-safe TypeScript and fully typed Python. Python guidance includes uv, Pydantic, and Ruff as part of broader code-quality guidelines.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name