Back to Skills
Code

langchain-architecture

Craft LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration.

langchain-architecture is an Agent Skill — a folder with a SKILL.md and any helper scripts that a coding agent loads on demand. Drop it in your skills directory and the agent picks it up the next time the task matches.

Its source repo has about 39.3k stars, a rough proxy for how many people rely on it.

If something here is out of date, the source link below is always the canonical reference.

CategoryCode
GitHub stars39.3k
/skill add langchain-architecture

How to use it

  1. Copy the skill folder into your agent's skills directory, or run the add command above.
  2. Reload the agent so it re-scans available skills.
  3. Trigger it by describing the task — the agent loads the skill when it matches.
Compiled and written by HowToPrompts from public sources.

Related in Code

test-driven-developmentWrite the failing test first, then the code — enforced red-green-refactor.using-git-worktreesSpin up isolated git worktrees safely, with smart directory picks.claude-apiA working reference for the Claude API — models, pricing, streaming and tool use.discernment-nudgePrompt sharper judgment by flagging weak reasoning before it ships.mcp-builderScaffold a solid MCP server in Python or TypeScript with well-shaped tools from the start.skill-creatorDraft a new skill from scratch — scoped instructions, structure and metadata done right.webapp-testingDrive a real browser to exercise your web app and catch what unit tests miss.debug-skillGive your agent a real debugger — breakpoints, stepping and stack inspection.brainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or…dispatching-parallel-agentsFacing 2+ independent tasks that can be worked on without shared state or sequential dependencies.
← Back to Skills