--- title: "LangChain (@langchain-ai) skills · skilld" canonical_url: "https://skilld.dev/gh/langchain-ai" meta: description: "44 agent skills published by LangChain on skilld. Python, TypeScript, langchain." "og:description": "44 agent skills published by LangChain." "og:title": "LangChain on skilld" --- ` ![Avatar for LangChain](https://skilld.dev/_img/avatar?url=https%3A%2F%2Fgithub.com%2Flangchain-ai.png) # **LangChain** [@langchain-ai](https://github.com/langchain-ai)org 44 skills2 repos 30k United States of America Mostly·Python, TypeScript, langchain [GitHub](https://github.com/langchain-ai) [Website](https://www.langchain.com) ## Skills ### [langchain-ai/langchain-skills](https://skilld.dev/gh/langchain-ai/langchain-skills) 23 skills 1.3k `npx skilld add langchain-ai/langchain-skills` - [ **/deep-agents-core**1.3k INVOKE THIS SKILL when building ANY Deep Agents application. Covers create\_deep\_agent(), harness architecture, SKILL.md format, and configuration options. /deep-agents-core by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/deep-agents-core) - [ **/deep-agents-memory**1.3k INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing. /deep-agents-memory by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/deep-agents-memory) - [ **/deep-agents-orchestration**1.3k 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 by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/deep-agents-orchestration) - [ **/deepagents-python-quickstart**1.3k Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally. /deepagents-python-quickstart by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/deepagents-python-quickstart) - [ **/deepagents-typescript-quickstart**1.3k Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally. /deepagents-typescript-quickstart by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/deepagents-typescript-quickstart) - [ **/ecosystem-primer**1.3k INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting point for up to date info on framework selection (LangChain vs LangGraph vs Deep Agents vs hybrid composition), agent patterns, install, environment setup, and which skill to load next. /ecosystem-primer by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/ecosystem-primer) - [ **/eval-engineering**1.3k Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable project World Knowledge Skills. Use for agent evals, benchmark design, Task generation, controlled Environments, synthetic data, Verifiers, Harbor runs, calibration, or continuous benchmark maintenance. /eval-engineering by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/eval-engineering) - [ **/langchain-dependencies**1.3k INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best practices, and common community tool packages for both Python and TypeScript. /langchain-dependencies by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langchain-dependencies) - [ **/langchain-fundamentals**1.3k Create LangChain agents with create\_agent, define tools, and use middleware for human-in-the-loop and error handling. /langchain-fundamentals by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langchain-fundamentals) - [ **/langchain-middleware**1.3k INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod. /langchain-middleware by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langchain-middleware) - [ **/langchain-python-quickstart**1.3k Scaffold a minimal local LangChain agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent locally. /langchain-python-quickstart by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langchain-python-quickstart) - [ **/langchain-rag**1.3k INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone). /langchain-rag by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langchain-rag) - [ **/langchain-typescript-quickstart**1.3k Scaffold a minimal local LangChain agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent locally. /langchain-typescript-quickstart by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langchain-typescript-quickstart) - [ **/langgraph-cli**1.3k INVOKE THIS SKILL when using the langgraph CLI to scaffold, develop, build, or deploy LangGraph applications. Covers langgraph new, dev, build, up, deploy, and langgraph.json configuration. /langgraph-cli by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langgraph-cli) - [ **/langgraph-decision-models**1.3k INVOKE THIS SKILL when routing a LangGraph agent with a decision model (TypeSafe Jev, SemIf) instead of an LLM, or when auditing an existing agent for LLM calls that only produce a routing decision. Covers langchain-typesafe Noul/Choice/Score, reading answers correctly, threshold design, and LangSmith Gateway wiring. /langgraph-decision-models by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langgraph-decision-models) - [ **/langgraph-fundamentals**1.3k INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling. /langgraph-fundamentals by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langgraph-fundamentals) - [ **/langgraph-human-in-the-loop**1.3k INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy. /langgraph-human-in-the-loop by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langgraph-human-in-the-loop) - [ **/langgraph-persistence**1.3k INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread\_id, time travel, Store, and subgraph persistence modes. /langgraph-persistence by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langgraph-persistence) - [ **/langgraph-python-quickstart**1.3k Scaffold a minimal local LangGraph agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangGraph agent locally. /langgraph-python-quickstart by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langgraph-python-quickstart) - [ **/langgraph-typescript-quickstart**1.3k Scaffold a minimal local LangGraph agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a LangGraph agent locally. /langgraph-typescript-quickstart by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langgraph-typescript-quickstart) - [ **/langsmith-online-eval-engineering**1.3k Iteratively inspect traces, interview the user, and create LangSmith online evaluators one at a time. Use specifically for creating online evaluators for use within LangSmith -- use "eval-engineering" for Harbor-style online evaluations. /langsmith-online-eval-engineering by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/langsmith-online-eval-engineering) - [ **/managed-deep-agents**1.3k INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith with the mda CLI. Walks a user through their first agent end to end — interviewing them about what they want to build, mapping it onto what MDA can actually do, then scaffolding and deploying it. Covers the file-based project layout; define\_deep\_agent / defineDeepAgent; instructions, skills, memory, identity, tools, middleware, sandboxes, schedules, channels, and evals; mda init/build/dev/deploy/logs/delete; and Context Hub. /managed-deep-agents by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/managed-deep-agents) - [ **/swarm**1.3k Dispatches many independent items in parallel: create a table, fan out to subagents, aggregate results. One row = one unit of work. /swarm by langchain-ai](https://skilld.dev/gh/langchain-ai/langchain-skills/swarm) ### [langchain-ai/deepagents](https://skilld.dev/gh/langchain-ai/deepagents) The batteries-included agent harness. 21 skills 30k `npx skilld add langchain-ai/deepagents` - [ **/analyze-market**30k Perform a market analysis for a product category or segment. Trigger on: market analysis, market size, TAM SAM SOM, market opportunity, industry analysis. /analyze-market by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/analyze-market) - [ **/arxiv-search**30k Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic. Use when the user asks to find research papers, search arXiv, look up preprints, find academic articles in physics, math, CS, biology, statistics, or related fields. /arxiv-search by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/arxiv-search) - [ **/blog-post**30k Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content. /blog-post by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/blog-post) - [ **/code-review**30k Perform a structured code review of changes, checking for correctness, style, tests, and potential issues. /code-review by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/code-review) - [ **/coding-prefs**30k Read the user's coding preferences from /memory/coding-prefs.md before making non-trivial style decisions, and append new preferences when the user gives durable feedback. /coding-prefs by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/coding-prefs) - [ **/competitor-analysis**30k Analyze competitors in a given market segment. Trigger on: competitive landscape, competitor analysis, market comparison, competitive positioning. /competitor-analysis by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/competitor-analysis) - [ **/configuration-hardening**30k Review Talon tool placement and defensive prompts when requested or when adding or changing tools or subagents; apply confirmed changes and verify active capabilities. /configuration-hardening by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/configuration-hardening) - [ **/cudf-analytics**30k Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF. Triggers when tasks involve groupby aggregations, statistical summaries, anomaly detection, or large-scale data profiling. /cudf-analytics by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/cudf-analytics) - [ **/cuml-machine-learning**30k Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets. /cuml-machine-learning by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/cuml-machine-learning) - [ **/data-visualization**30k Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output. /data-visualization by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/data-visualization) - [ **/deepagents-thread-inspector**30k Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata, list recent local threads, or parse $DEEPAGENTS\_HOME/.state/sessions.db and a thread UUID or prefix. /deepagents-thread-inspector by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/deepagents-thread-inspector) - [ **/gpu-document-processing**30k Use when processing large PDFs, document collections, or bulk text extraction tasks that benefit from GPU-accelerated processing. Triggers when the user provides large documents or needs bulk document analysis. /gpu-document-processing by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/gpu-document-processing) - [ **/langgraph-docs**30k Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance. /langgraph-docs by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/langgraph-docs) - [ **/planning**30k Break down a coding task into a structured implementation plan with clear steps, file identification, and risk assessment. /planning by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/planning) - [ **/query-writing**30k Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables. /query-writing by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/query-writing) - [ **/remember**30k Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture learnings. /remember by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/remember) - [ **/schema-exploration**30k Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate. /schema-exploration by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/schema-exploration) - [ **/skill-creator**30k Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like "create a skill", "new skill", "make a skill", "skill for X", "how do I create a skill", or "help me build a skill". /skill-creator by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/skill-creator) - [ **/social-media**30k Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms. /social-media by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/social-media) - [ **/textual-screenshot**30k Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a desktop or browser. /textual-screenshot by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/textual-screenshot) - [ **/web-research**30k Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report. /web-research by langchain-ai](https://skilld.dev/gh/langchain-ai/deepagents/web-research) Skills published by LangChain. Checked GitHub just now