@skills · Owner
Agent skills by langchain-ai
84 skills indexed from github.com/langchain-ai. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.
- analyze-market · Skill · 27,447 stars
Perform a market analysis for a product category or segment. Trigger on: market analysis, market size, TAM SAM SOM, market opportunity, industry analysis.
- arxiv-search · Skill · 27,447 stars
Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic. Use when the user asks to find research papers, search arXiv,
- blog-post · Skill · 27,447 stars
Write structured long-form blog posts with research, SEO optimization, and cover image generation.
- blog-post · Skill · 27,447 stars
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
- built_in_skills · Collection · 27,447 stars
- code · Collection · 27,447 stars
- code-review · Skill · 27,447 stars
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.
- coding-prefs · Skill · 27,447 stars
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 d
- competitor-analysis · Skill · 27,447 stars
Analyze competitors in a given market segment. Trigger on: competitive landscape, competitor analysis, market comparison, competitive positioning.
- content-builder-agent · Collection · 27,447 stars
- cudf-analytics · Skill · 27,447 stars
Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF. Triggers when tasks involve groupby aggregations, statistical s
- cuml-machine-learning · Skill · 27,447 stars
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensional
- data-visualization · Skill · 27,447 stars
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating ch
- deepagents · Collection · 27,447 stars
- deepagents_code · Collection · 27,447 stars
- deepagents-thread-inspector · Skill · 27,447 stars
Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for of
- deploy-coding-agent · Collection · 27,447 stars
- deploy-content-writer · Collection · 27,447 stars
- deploy-gtm-agent · Collection · 27,447 stars
- examples · Collection · 27,447 stars
- examples · Collection · 27,447 stars
- gpu-document-processing · Skill · 27,447 stars
Use when processing large PDFs, document collections, or bulk text extraction tasks that benefit from GPU-accelerated processing. Triggers when the user pr
- langgraph-docs · Skill · 27,447 stars
Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use
- libs · Collection · 27,447 stars
- market-researcher · Collection · 27,447 stars
- nvidia_deep_agent · Collection · 27,447 stars
- planning · Skill · 27,447 stars
Break down a coding task into a structured implementation plan with clear steps, file identification, and risk assessment.
- query-writing · Skill · 27,447 stars
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,
- remember · Skill · 27,447 stars
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback —
- schema-exploration · Skill · 27,447 stars
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks a
- skill-creator · Skill · 27,447 stars
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the use
- skill-creator · Skill · 27,447 stars
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the use
- skills · Collection · 27,447 stars
- skills · Collection · 27,447 stars
- skills · Collection · 27,447 stars
- skills · Collection · 27,447 stars
- skills · Collection · 27,447 stars
- skills · Collection · 27,447 stars
- skills · Collection · 27,447 stars
- skills · Collection · 27,447 stars
- social-media · Skill · 27,447 stars
Create social media content including Twitter/X threads, LinkedIn posts, and short-form updates.
- social-media · Skill · 27,447 stars
Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to w
- subagents · Collection · 27,447 stars
- text-to-sql-agent · Collection · 27,447 stars
- web-research · Skill · 27,447 stars
Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a to
- config · Collection · 1,107 stars
- deep-agents-core · Skill · 1,107 stars
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
- deep-agents-memory · Skill · 1,107 stars
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), Filesys
- deep-agents-orchestration · Skill · 1,107 stars
INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interru
- deepagents-python-quickstart · Skill · 1,107 stars
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 w
- deepagents-typescript-quickstart · Skill · 1,107 stars
Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. Use when the us
- ecosystem-primer · Skill · 1,107 stars
INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting
- eval-engineering · Skill · 1,107 stars
Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable projec
- langchain-dependencies · Skill · 1,107 stars
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, Lang
- langchain-fundamentals · Skill · 1,107 stars
Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.
- langchain-middleware · Skill · 1,107 stars
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of
- langchain-python-quickstart · Skill · 1,107 stars
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
- langchain-rag · Skill · 1,107 stars
INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenA
- langchain-skills · Collection · 1,107 stars
- langchain-typescript-quickstart · Skill · 1,107 stars
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 ag
- langgraph-cli · Skill · 1,107 stars
INVOKE THIS SKILL when using the langgraph CLI to scaffold, develop, build, or deploy LangGraph applications. Covers langgraph new, dev, build, up, deploy,
- langgraph-fundamentals · Skill · 1,107 stars
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
- langgraph-human-in-the-loop · Skill · 1,107 stars
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=.
- langgraph-persistence · Skill · 1,107 stars
INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. C
- langgraph-python-quickstart · Skill · 1,107 stars
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
- langgraph-typescript-quickstart · Skill · 1,107 stars
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 ag
- langsmith-online-eval-engineering · Skill · 1,107 stars
Iteratively inspect traces, interview the user, and create LangSmith online evaluators one at a time. Use specifically for creating online evaluators for u
- managed-deep-agents · Skill · 1,107 stars
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
- skills · Collection · 1,107 stars
- swarm · Skill · 1,107 stars
Dispatches many independent items in parallel: create a table, fan out to subagents, aggregate results. One row = one unit of work.
- config · Collection · 142 stars
- langsmith-dataset · Skill · 142 stars
INVOKE THIS SKILL when creating evaluation datasets, uploading datasets to LangSmith, or managing existing datasets. Covers dataset types (final_response,
- langsmith-evaluator · Skill · 142 stars
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2)
- langsmith-skills · Collection · 142 stars
- langsmith-trace · Skill · 142 stars
INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the
- skills · Collection · 142 stars
- .agents · Collection
- configuration-hardening · Skill
Review Talon tool placement and defensive prompts when requested or when adding or changing tools or subagents; apply confirmed changes and verify active c
- deepagents_talon · Collection
- defaults · Collection
- skills · Collection
- skills · Collection
- talon · Collection
- textual-screenshot · Skill
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 o