langchain-ai

Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.

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.

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.

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".

Take a note.

Summarise text into a one-paragraph summary.

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.

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".

INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses the langsmith CLI tool.

INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the langsmith CLI tool.

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.

INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.

ALWAYS START HERE for any LangChain, Deep Agents, or LangGraph agent building project. Required starting point before choosing other skills or writing any code. Covers framework selection (LangChain vs LangGraph vs Deep Agents), agent archetypes, dependency setup, and which skills to load next based on your decisions.

INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.

INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.

INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.

INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith with the mda CLI. Covers the code-first, file-based project layout; define_deep_agent / defineDeepAgent; authored tools and middleware; MCP connectors; cron schedules; skills; sandboxes; mda init/dev/deploy; Context Hub; and human-in-the-loop interrupts in Python and TypeScript.

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.

Dispatches many independent items in parallel: create a table, fan out to subagents, aggregate results. One row = one unit of work.

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.

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.

INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.

INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.

INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: create a skill, make a skill, build a skill, set up a skill, initialize a skill, scaffold a skill, update or modify an existing skill, validate a skill, learn about skill structure, understand how skills work, or get guidance on skill design patterns.

Create new eval suites for the deepagentsjs monorepo. Handles dataset design, test case scaffolding, scoring logic, vitest configuration, and LangSmith integration. Use when the user asks to: (1) create an eval, (2) write an evaluation, (3) add a benchmark, (4) build an eval suite, (5) evaluate agent behaviour, (6) add test cases for a capability, or (7) implement an existing benchmark (e.g. oolong, AgentBench, SWE-bench). Trigger on phrases like 'create eval', 'new eval', 'add eval', 'benchmark', 'evaluate', 'eval suite', 'write evals for'.

INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the langsmith CLI tool.

Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.

Use this skill for requests related to LangGraph in order to fetch relevant documentation to provide accurate, up-to-date guidance.

Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research

Use this skill when migrating inline code samples from LangChain docs (MDX files) into external, testable code files that are extracted by this repo’s snippet scripts and used as Mintlify snippets. Applies when extracting code blocks from documentation, creating runnable code samples, using snippet delineators, or wiring snippet output into MDX includes.

Build batteries-included agents with planning, context management, subagent delegation, and sandboxed execution. Use for complex, multi-step tasks that need built-in capabilities.

Build agents with a prebuilt architecture and integrations for any model or tool. Use when creating tool-calling agents, switching model providers, or adding structured output.

Build stateful, durable agent workflows with LangGraph. Use when you need custom graph-based control flow, human-in-the-loop, persistence, or multi-agent orchestration.

Common pandas and matplotlib patterns for data analysis and visualization

Trace, evaluate, and deploy AI agents and LLM applications with LangSmith. Use when adding observability, running evaluations, engineering prompts, or deploying agents to production.

Use when the user wants the current date and time written to a file via the bundled script inside the sandbox.

Teaching instructions for Module 5 (Authentication and Authorization) — use when module_id is module-5

Teaching instructions for Module 3 (Dashboard) — use when module_id is module-3

Teaching instructions for Module 4 (Storage) — use when module_id is module-4

Teaching instructions for Module 6 (Deepagents CLI) — use when module_id is module-6

Teaching instructions for Module 2 (Using your deployment) — use when module_id is module-2

Teaching instructions for Module 1 (LangGraph Deployment Architecture) — use when module_id is module-1

Teaching instructions for Module 1 (LangGraph Deployment Architecture) — use when module_id is module-1

Build a report on the rep's sales territory — revenue, top customers, top genres, and trends for Jane's book of business — with a chart. Use when asked for a territory report, sales summary, performance numbers, or 'how is my book doing'.

Produce the weekly 'This Week in Music' customer newsletter by researching the distributor's top genres in parallel and assembling a styled HTML page. Use when asked to create, write, or send the weekly newsletter or a music-news roundup.

Use when the user wants to write a sales pitch or outreach message for a prospect.

Use when the user wants to qualify a sales lead or prospect.

Process an incoming request for quote (RFQ) from a customer: read the email, look up the customer and catalogue prices, compute a quote, have it reviewed, draft the reply, and log it. Use whenever a customer asks for a price, a quote, or to license/buy a batch of tracks.

INVOKE THIS SKILL when creating evaluation datasets, uploading datasets to LangSmith, or managing existing datasets. Covers dataset types (final_response, single_step, trajectory, RAG), CLI management commands, SDK-based creation, and example management. Uses the langsmith CLI tool.

INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses the langsmith CLI tool.

INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the langsmith CLI tool.

First-time analysis of a repository with no prior reviewer outcomes. Crawl historical merged-PR review feedback with the gh CLI (plus any preloaded samples), extract the team's review norms, and synthesize the initial per-repo review-style prompt. Use this for a cold-start repo; use continual-learning instead once the reviewer has accumulated finding outcomes.

Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt, and save the refined version. Use this once outcomes exist; use bootstrap-repo-analysis for a cold-start repo.

Write a LinkedIn post based on research findings or a given topic. Use this skill when asked to create LinkedIn content, professional posts, or thought leadership pieces.

Write a Twitter/X post or thread based on research findings or a given topic. Use this skill when asked to create tweets, X posts, or social media threads.

Creates code-based evaluators for LangSmith-traced agents. Use when building custom evaluation logic, testing tool usage patterns, or scoring agent outputs programmatically. Triggers on requests to evaluate agents, create evaluators, or run experiments against LangSmith datasets.

Fetches LangSmith traces for debugging agent behavior. Use when troubleshooting agent issues, reviewing conversation history, or investigating tool calls.

Skill for compiling and writing release notes for langchain-azure packages. Use when a new version of a package is being released and the README.md changelog section needs to be updated with a summary of merged PRs.