Tool Design
agentailor/fullstack-langgraph-nextjs-agent
Design and verify tools that AI agents can actually use — for any framework or language (MCP servers, LangChain/LangGraph, function-calling, raw JSON schema; TypeScript, Python, or otherwise).
A Chinese-language guide and reference for building agents with LangGraph 1.0, from a first ReAct agent through middleware, memory, MCP, RAG and web search.
SKILL.md written in Chinese; this summary is our English description.
Install Dive Into LangGraph
$ npx skills add luochang212/dive-into-langgraph --skill dive-into-langgraph -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install luochang212/dive-into-langgraph dive-into-langgraph --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/luochang212/dive-into-langgraph.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dive-into-langgraph .claude/skills/dive-into-langgraph && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "dive-into-langgraph" agent skill from https://github.com/luochang212/dive-into-langgraph/tree/main/skills/dive-into-langgraph into .claude/skills/dive-into-langgraph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dive-into-langgraph", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/luochang212/dive-into-langgraph/tree/main/skills/dive-into-langgraphType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add luochang212/dive-into-langgraph --skill dive-into-langgraph -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install luochang212/dive-into-langgraph dive-into-langgraph --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/luochang212/dive-into-langgraph.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/dive-into-langgraph .agents/skills/dive-into-langgraph && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dive-into-langgraph" agent skill from https://github.com/luochang212/dive-into-langgraph/tree/main/skills/dive-into-langgraph into .agents/skills/dive-into-langgraph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dive-into-langgraph", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add luochang212/dive-into-langgraph --skill dive-into-langgraph -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install luochang212/dive-into-langgraph dive-into-langgraph --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/luochang212/dive-into-langgraph.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/dive-into-langgraph .cursor/skills/dive-into-langgraph && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "dive-into-langgraph" agent skill from https://github.com/luochang212/dive-into-langgraph/tree/main/skills/dive-into-langgraph into .cursor/skills/dive-into-langgraph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dive-into-langgraph", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/luochang212/dive-into-langgraph.git --path skills/dive-into-langgraph--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add luochang212/dive-into-langgraph --skill dive-into-langgraph -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install luochang212/dive-into-langgraph dive-into-langgraph --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/luochang212/dive-into-langgraph.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/dive-into-langgraph .gemini/skills/dive-into-langgraph && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "dive-into-langgraph" agent skill from https://github.com/luochang212/dive-into-langgraph/tree/main/skills/dive-into-langgraph into .gemini/skills/dive-into-langgraph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dive-into-langgraph", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install luochang212/dive-into-langgraph dive-into-langgraphInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add luochang212/dive-into-langgraph --skill dive-into-langgraph -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/luochang212/dive-into-langgraph.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/dive-into-langgraph .github/skills/dive-into-langgraph && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "dive-into-langgraph" agent skill from https://github.com/luochang212/dive-into-langgraph/tree/main/skills/dive-into-langgraph into .github/skills/dive-into-langgraph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dive-into-langgraph", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add luochang212/dive-into-langgraph --skill dive-into-langgraph -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install luochang212/dive-into-langgraph dive-into-langgraph --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/luochang212/dive-into-langgraph.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/dive-into-langgraph .opencode/skills/dive-into-langgraph && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "dive-into-langgraph" agent skill from https://github.com/luochang212/dive-into-langgraph/tree/main/skills/dive-into-langgraph into .opencode/skills/dive-into-langgraph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dive-into-langgraph", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
dive-into-langgraph- GitHub stars
- 457
- Token cost
- ~837 tokens
- SKILL.md length
- 140 words
- Files
- 16 (incl. scripts, references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
A Chinese-language guide and reference for building agents with LangGraph 1.0, from a first ReAct agent through middleware, memory, MCP, RAG and web search.
- Building a first ReAct agent with LangGraph 1.0
- SKILL.md covers 安装依赖, 环境变量, 章节概览 and 官方资源
- Runs Python scripts from its folder; calls uv; reaches bailian.console.aliyun.com and dashscope.aliyuncs.com; needs DASHSCOPE_API_KEY and ARK_API_KEY
- Designing a workflow as a StateGraph
What it does
The skill draws on a LangGraph 1.0 guide and organizes it into eleven chapters with local reference files. They cover a first ReAct agent, StateGraph workflows, middleware (budget control, message truncation, sensitive-word filtering, PII detection), human-in-the-loop approval, short-term and long-term memory, and context engineering with State, Store and Runtime.
Later chapters cover building an MCP server and connecting it to LangGraph, the supervisor pattern with subagents as tools, parallelization (node concurrency, the @task decorator, map-reduce and sub-graphs), RAG with vector, keyword and hybrid retrieval, and web search through DashScope, Tavily, DDGS and Exa MCP. Python examples live in scripts/examples.py, with a sample math tool and utilities.
Setup is uv sync, with dependencies declared in pyproject.toml and pinned in uv.lock. MCP goes through the MCPAdapter in langchain[mcp], whose namespace is still beta, and the skill targets only the latest interface of the current stable package. Models need API keys in a .env file, and the guide recommends Alibaba Cloud Bailian (DashScope).
When your agent uses it
- Building a first ReAct agent with LangGraph 1.0
- Designing a workflow as a StateGraph
- Adding middleware such as PII detection or message truncation to an agent
- Setting up a supervisor agent that calls subagents as tools
- Adding RAG or web search to a LangGraph agent
Example prompts
- “Create a ReAct agent with LangGraph 1.0 that can call a math tool.”
- “Add human-in-the-loop approval to my agent's tool calls using the HITL middleware.”
- “Show me how to run two LangGraph nodes in parallel and merge the results.”
Requirements
- Python with uv to sync dependencies
- A model provider API key in a .env file, with DashScope recommended
What it can do on your machine
Read from SKILL.md and the folder at commit ab10e27. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 4 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
bailian.console.aliyun.comdashscope.aliyuncs.comconsole.volcengine.comark.cn-beijing.volces.com
Also links to:
luochang212.github.iodocs.langchain.comgithub.comlangchain-ai.github.io
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
DASHSCOPE_API_KEYARK_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Dive Into LangGraph loads about 837 tokens when it runs, and up to ~37k if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 140 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:45
请将环境变量添加到 `.env` 文件，并填入你的 API key。
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 140 words (~837 tokens).
“LangGraph 是由 LangChain 团队开发的开源 Agent 框架。v1.0 是稳定版本，框架能力全面升级，支持中间件、状态图、多智能体等高级功能。本 skill 内容由《LangGraph 1.0 完全指南》提供。”
- name
- dive-into-langgraph
Files
SKILL.md and 15 other files (scripts, references) in skills/dive-into-langgraph of luochang212/dive-into-langgraph.
- SKILL.md
- references/1.quickstart.md
- references/10.rag.md
- references/11.web_search.md
- references/2.stategraph.md
- references/3.middleware.md
- references/4.human_in_the_loop.md
- references/5.memory.md
- references/6.context.md
- references/7.mcp_server.md
- references/8.supervisor.md
- references/9.parallelization.md
- scripts/examples.py
- scripts/tools/__init__.py
- scripts/tools/tool_math.py
- scripts/utils.py
Open the folder on GitHubat commit ab10e27
Compare with similar skills
Dive Into LangGraph next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Dive Into LangGraph this skillluochang212/dive-into-langgraph | 457 | — | ~837 | Automated safety check: Notes | Custom licence | |
| Tool Designagentailor/fullstack-langgraph-nextjs-agent | 132 | — | ~3.2k | Automated safety check: Pass | MIT | |
| Chemgraphargonne-lcf/ChemGraph | 162 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Agent Eval Casesagentailor/fullstack-langgraph-nextjs-agent | 132 | — | ~5.3k | Automated safety check: Pass | MIT | |
| Deep Agents Corelangchain-ai/langchain-skills | 1.3k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Langgraphmagnus919/agent-skills | 116 | — | ~2.8k | Automated safety check: Pass | MIT |
Similar skills
Chemgraph
argonne-lcf/ChemGraph
Develop, test, and extend ChemGraph -- an agentic framework for automated molecular simulations using LLMs, LangGraph, ASE, and MCP servers
Agent Eval Cases
agentailor/fullstack-langgraph-nextjs-agent
Decide which AI agent behaviors are worth an eval case, then write those cases — harness-, framework-, and language-agnostic.
- Official
Deep Agents Core
langchain-ai/langchain-skills
Explains how to build agents with the Deep Agents framework: create_deep_agent, the built-in middleware, the harness, SKILL.md format and configuration options.
Langgraph
magnus919/agent-skills
Build multi-agent AI systems with LangGraph — the low-level orchestration framework for stateful, graph-based agent workflows.
Magic Resume
Magic-Resume/Magic-Resume
How AI agents integrate with Magic Resume — read and safely edit a user's resumes through the native MCP server (@magic-resume/mcp).
Related
Categories
Questions about Dive Into LangGraph
What does Dive Into LangGraph do?
A Chinese-language guide and reference for building agents with LangGraph 1.0, from a first ReAct agent through middleware, memory, MCP, RAG and web search. 0 guide and organizes it into eleven chapters with local reference files. They cover a first ReAct agent, StateGraph workflows, middleware (budget control, message truncation, sensitive-word filtering, PII detection), human-in-the-loop approval, short-term and long-term memory, and context engineering with State, Store and Runtime.
When should I use Dive Into LangGraph?
Dive Into LangGraph fits situations like: building a first ReAct agent with LangGraph 1.0; designing a workflow as a StateGraph; adding middleware such as PII detection or message truncation to an agent; setting up a supervisor agent that calls subagents as tools.
How do I install Dive Into LangGraph in Claude Code?
Run `npx skills add luochang212/dive-into-langgraph --skill dive-into-langgraph -a claude-code`. Or copy the skill folder (skills/dive-into-langgraph in luochang212/dive-into-langgraph) into .claude/skills/dive-into-langgraph in your project. Claude Code loads it when a task matches its description.
How do I install Dive Into LangGraph in Codex?
Run `npx skills add luochang212/dive-into-langgraph --skill dive-into-langgraph -a codex`. Or copy the skill folder (skills/dive-into-langgraph in luochang212/dive-into-langgraph) into .agents/skills/dive-into-langgraph in your project. Codex loads it when a task matches its description.
Can I use Dive Into LangGraph in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add luochang212/dive-into-langgraph --skill dive-into-langgraph -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dive-into-langgraph, .gemini/skills/dive-into-langgraph, .github/skills/dive-into-langgraph and .opencode/skills/dive-into-langgraph in your project.
What does Dive Into LangGraph need to run?
Going by SKILL.md and its folder, Dive Into LangGraph needs Python for the scripts in its folder, the command-line tools its instructions call (uv) and credentials named DASHSCOPE_API_KEY and ARK_API_KEY. Our summary lists: Python with uv to sync dependencies; A model provider API key in a .env file, with DashScope recommended.
Does Dive Into LangGraph access the network?
SKILL.md names 8 domains. In commands or code: bailian.console.aliyun.com, dashscope.aliyuncs.com, console.volcengine.com and ark.cn-beijing.volces.com; the agent is likely to contact these when it follows the instructions. As links in the text: luochang212.github.io, docs.langchain.com, github.com and langchain-ai.github.io. This is read from the text; nothing was executed.
Is Dive Into LangGraph safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Dive Into LangGraph use?
Dive Into LangGraph has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Dive Into LangGraph use?
About 837 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 37k tokens, read only when the agent opens those files.
What are the alternatives to Dive Into LangGraph?
Skills that share tags, products or a category with Dive Into LangGraph: Tool Design (agentailor/fullstack-langgraph-nextjs-agent, 132 stars), Chemgraph (argonne-lcf/ChemGraph, 162 stars), Agent Eval Cases (agentailor/fullstack-langgraph-nextjs-agent, 132 stars) and Deep Agents Core (langchain-ai/langchain-skills, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dive Into LangGraph?
luochang212 (a GitHub user) maintains it in luochang212/dive-into-langgraph, which has 457 GitHub stars. The repository was last updated on September 11, 2026.
Source: luochang212/dive-into-langgraph on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.