Helps design, implement, evaluate, debug, and deploy stateful multi-agent workflows with LangGraph, including supervisor, swarm, hierarchical, persistence, subgraph, and human-in-the-loop patterns.
Build multi-agent AI systems with LangGraph — the low-level orchestration framework for stateful, graph-based agent workflows. Covers supervisor, swarm, and hierarchical multi-agent patterns; subgraph composition; state management (checkpointers/stores); persistence; evals; and production debugging. Reach for this when designing agent architectures that need cycles, conditional branching, parallel execution, or human-in-the-loop patterns. Do not use this skill for unrelated requests; route to the nearest named specialist.
assets/templates/subgraph-agent.py
Python
Asset
assets/templates/supervisor-graph.py
Python
Asset
assets/templates/swarm-graph.py
Python
Other
evals/evals.json
JSON
Other
README.md
Markdown
Reference
references/architecture.md
Markdown
Reference
references/evals.md
Markdown
Reference
references/multi-agent-hierarchical.md
Markdown
Reference
references/multi-agent-supervisor.md
Markdown
Reference
references/multi-agent-swarm.md
Markdown
Reference
references/persistence.md
Markdown
Reference
references/production.md
Markdown
Reference
references/troubleshooting.md
Markdown
Script
scripts/lg-eval-generator.py
Python
Script
scripts/lg-supervisor-scaffold.py
Python
Script
scripts/lg-swarm-scaffold.py
Python
SKILL.md
SKILL.md
Markdown
Guides agents through safe cross-system migrations involving data, schemas, interfaces, infrastructure, and service ownership, using compatibility windows, dual-running, reconcili…
Guides agents in developing, testing, deploying, and administering managed or self-hosted Supabase projects, including migrations, RLS, client types, services, backups, upgrades, …
Guides agents in designing, evaluating, governing, operating, evolving, and retiring digital twins and federated twin universes with synchronization, simulation, authority, and li…
Guides agents in designing, reviewing, prototyping, measuring, and troubleshooting electronic circuits using component evidence, worst-case analysis, interface contracts, and stag…
Guides system-level architecture decisions from business drivers through boundaries, tradeoffs, runtime behavior, evolution, evidence, and architecture reviews.
Guides agents in designing and reviewing multi-tenant SaaS architectures, covering tenant semantics, system planes, isolation choices, onboarding, entitlements, billing handoffs, …
Helps agents build, customize, and debug Hugo themes, including templates, asset pipelines, shortcodes, render hooks, content organization, performance, SEO, accessibility, and CI…
Helps build type-safe Python AI agents and graph-based workflows with PydanticAI and PydanticGraph, including tools, dependency injection, structured output, streaming, multi-agen…