Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

LangGraph Development Skill · majiayu000 | DecimalAI

agent toolingby majiayu000

LangGraph Development Skill

majiayu000/building-langgraph-agents

Source majiayu000/claude-skill-registry ↗License MIT

LangGraph development for stateful multi-agent applications, cyclic workflows, conditional routing, human-in-the-loop patterns, and persistent state management.

SkillScore100Maintained

Automatic

AI Engineer pack

Last verified 8/18/2026

What it changes

Passed 22 of 22 test cases with the skill, and 19 of 22 without it.

Without skill86%

With skill100%

Checks it passed that the model alone missed

Sets LANGSMITH_API_KEY environment variable.
States langchain-core>=0.3.0 as the compatibility requirement.
Notes that returning keys not declared in the state schema raises an InvalidUpdateError.

3 fixed19 passed either way0 still failing0 broke

Pass-rate lift: +14 pp
Tokens: +187%
Agent turns: 0%
Response time: -32%

Model gemini-3.6-flashMeasured 8/18/2026v122 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/majiayu000-building-langgraph-agents/SKILL.md https://app.decimal.ai/s/majiayu000-building-langgraph-agents/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-building-langgraph-agents, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/majiayu000-building-langgraph-agents/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-building-langgraph-agents

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/majiayu000-building-langgraph-agents/SKILL.md https://app.decimal.ai/s/majiayu000-building-langgraph-agents/SKILL.md

Raw file: /s/majiayu000-building-langgraph-agents/SKILL.md ↗ · machine-readable summary at /s/majiayu000-building-langgraph-agents.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

We are installing langgraph version 0.2.x in our Python backend repository. What minimum version of langchain-core is required for compatibility?

What was checked, without and with the skill
Checked	Without skill	With skill
States langchain-core>=0.3.0 as the compatibility requirement.	Missed	Passed

case-13 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md366 linessingle file

LangGraph Development Skill

Quick Reference

LangGraph is LangChain's framework for building stateful, multi-actor applications with LLMs. It enables cyclic graphs, conditional branching, persistent state management, and human-in-the-loop workflows.

Key capabilities: StateGraph for workflow orchestration, checkpointers for persistence, prebuilt ReAct agents, streaming at multiple granularities, and LangGraph Platform for managed deployment.

When to Use
Package Ecosystem
Quick Start - Python
Quick Start - TypeScript
Core Concepts
Prebuilt Components
Common Patterns
Quick Persistence Setup
CLI Commands
Error Quick Reference
When to Use REFERENCE.md
Agent Integration
See Also

When to Use

This skill is loaded by backend-developer when:

langgraph in requirements.txt, pyproject.toml, or setup.py
@langchain/langgraph in package.json dependencies
Python imports: from langgraph.graph import StateGraph
Environment variables LANGSMITH_API_KEY, LANGGRAPH_API_URL, or LANGCHAIN_API_KEY present
User mentions "LangGraph", "StateGraph", "agent workflow", "cyclic agent", or "multi-agent graph"

Package Ecosystem

Track record

Benchmark

22 / 22

test cases passed, vs 19 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

majiayu000 / claude-skill-registry

skills/agent/building-langgraph-agents/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

LangGraph Development Skill

Quick Reference

Table of Contents

When to Use

Package Ecosystem

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills