LangChain's skills help AI agents build and try LangGraph agents in Python, write StateGraph code with nodes, edges and streaming, and build and deploy Managed Deep Agents in LangSmith. Other skills cover LangSmith online evaluators for production traces, extracting text and tables from large PDFs into chunks and embeddings for Milvus or ChromaDB, and writing structured, SEO-optimized blog posts. Much of the catalogue centres on LangChain's own agent framework and tooling, with a few general-purpose skills such as skill creation alongside it.
Deepagents
26 skills · 31,043 stars · MIT
Analyze Market Perform a market analysis for a product category or segment.
Arxiv Search Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic.
Blog Post Write structured long-form blog posts with research, SEO optimization, and cover image generation.
Blog Post Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for…
Code Review Perform a structured code review of changes, checking for correctness, style, tests, and potentia…
Coding Prefs Read the user's coding preferences from /memory/coding-prefs.md before making non-trivial style d…
Competitor Analysis Analyze competitors in a given market segment.
Configuration Hardening Review Talon tool placement and defensive prompts when requested or when adding or changing tools…
Cudf Analytics Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF.
Cuml Machine Learning Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML.
Data Visualization Use for creating publication-quality charts and multi-panel analysis summaries.
Deepagents Plugin Discovery Discover plugins from configured dcode marketplaces when a capability is missing or the user asks…
Deepagents Thread Inspector Inspect and explain conversations in the local Deep Agents Code SQLite session store.
Extract text and tables from large PDFs in Adobe Acrobat and PdfCraft GPU-accelerated PDF text and table extraction, chunking and embeddings for large document sets
Langgraph Docs Fetches and references LangGraph Python documentation to build stateful agents, create multi-agen…
Planning Break down a coding task into a structured implementation plan with clear steps, file identificat…
Query Writing Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, a…
Remember Review the current conversation and capture valuable knowledge — best practices, coding conventio…
Safety Check secret handling, staged changes and push targets, destructive Git operations, Docker image…
Schema Exploration Lists tables, describes columns and data types, identifies foreign key relationships, and maps en…
Skill Creator Guide for creating effective skills that extend agent capabilities with specialized knowledge, wo…
Skill Creator Guide for creating effective skills that extend agent capabilities with specialized knowledge, wo…
Social Media Create social media content including Twitter/X threads, LinkedIn posts, and short-form updates.
Social Media Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, a…
Textual Screenshot Capture a Textual terminal UI as an SVG using its headless test harness.
Web Research Searches multiple web sources, synthesizes findings, and produces cited research reports using de…
Langchain Skills
22 skills · 1,324 stars · MIT
Deep Agents Core INVOKE THIS SKILL when building ANY Deep Agents application.
Deep Agents Memory INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access.
Deep Agents Orchestration INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents.
Deepagents Python Quickstart Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provide…
Deepagents Typescript Quickstart Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using pro…
Ecosystem Primer INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting…
Eval Engineering Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, b…
Langchain Dependencies INVOKE THIS SKILL when setting up a new project or when asked about package versions, installatio…
Langchain Fundamentals Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop…
Langchain Middleware INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output.
Langchain Python Quickstart Scaffold a minimal local LangChain agent in Python by following the official quickstart.
Langchain Rag INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system.
Langchain Typescript Quickstart Scaffold a minimal local LangChain agent in TypeScript by following the official quickstart.
Langgraph Cli INVOKE THIS SKILL when using the langgraph CLI to scaffold, develop, build, or deploy LangGraph a…
Langgraph Decision Models INVOKE THIS SKILL when routing a LangGraph agent with a decision model (TypeSafe Jev, SemIf) inst…
Langgraph Fundamentals INVOKE THIS SKILL when writing ANY LangGraph code.
Langgraph Human In The Loop INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling…
Langgraph Persistence INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel thro…
Langgraph Python Quickstart Scaffold a minimal local LangGraph agent in Python by following the official quickstart.
Langgraph Typescript Quickstart Scaffold a minimal local LangGraph agent in TypeScript by following the official quickstart.
Managed Deep Agents INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith.
Swarm Dispatches many independent items in parallel: create a table, fan out to subagents, aggregate re…
Langsmith Skills
5 skills · 165 stars · MIT
Langsmith Custom Apps INVOKE THIS SKILL when building, iterating on, copying, or sharing a LangSmith Custom App — a Rea…
Langsmith Dataset INVOKE THIS SKILL when creating evaluation datasets, uploading datasets to LangSmith, or managing…
Langsmith Evaluator INVOKE THIS SKILL when building evaluation pipelines for LangSmith.
Langsmith Online Eval Engineering Design, test, create, and attach LangSmith online evaluators for production traces or conversatio…
Langsmith Trace INVOKE THIS SKILL when working with LangSmith tracing OR querying traces.
Lca Tutors
1 skills · 22 stars
Lca Deepagents Active, Socratic teacher for the LangChain Academy Deep Agents course — drives the student throug…
Lca Skills
2 skills · 3 stars
Langsmith Code Eval Creates code-based evaluators for LangSmith-traced agents.
Langsmith Fetch Fetches LangSmith traces for debugging agent behavior.