langgraph-multiagent
LangGraph Multi-Agent
What this skill does
Build, review, and modernize production-grade multi-agent systems with LangGraph/LangChain while staying version-accurate by default: always resolve the current APIs from docs + installed versions, and fall back to opensrc/ source snapshots for under-the-hood edge cases.
Default operating rules (do these every time)
- Treat all LangGraph/LangChain APIs as versioned; never “code from memory” for any API surface that might have changed.
- Establish ground truth before coding:
- Determine installed/pinned versions (repo lockfiles +
importlib.metadata). - Query official docs via
langchain-docs.SearchDocsByLangChain. - Use Context7 for canonical API references and examples.
- Determine installed/pinned versions (repo lockfiles +
- When docs are ambiguous or behavior is subtle, inspect dependency internals via
opensrc/(read-only):- Run
npx opensrc pypi:<package>@<version> --modify=false - Check
opensrc/sources.jsonand cite exactopensrc/...paths + versions in your writeup.
- Run
Use references/research_playbook.md when you need a rigorous doc-sweep, including llms.txt-driven crawling of LangGraph docs.
More from bjornmelin/dev-skills
streamdown
|
13zod-v4
Expert guidance for Zod v4 schema validation in TypeScript. Use when designing schemas, migrating from Zod 3, handling validation errors, generating JSON Schema/OpenAPI, using codecs/transforms, or integrating with React Hook Form, tRPC, Hono, or Next.js. Covers all Zod v4 APIs including top-level string formats, strictObject/looseObject, metadata, registries, branded types, and recursive schemas.
9vitest-dev
World-class Vitest QA/test engineer for TypeScript + Next.js (local + CI performance focused)
8docker-architect
SOTA Docker/Compose architecture, implementation, refactor, and security hardening. Use when working on containerization tasks such as creating or rewriting Dockerfiles, docker-compose files, buildx/bake configs, .dockerignore, and CI pipelines for build/test/scan/publish; auditing existing container setups for security, correctness, size/perf, and best practices (least privilege, non-root, minimal images, pinned base images, BuildKit secrets, healthchecks); debugging Docker build/run issues; or designing dev vs prod compose workflows across services (DB/cache/queues) with correct networking, volumes, secrets, and resource limits.
7pytest-dev
World-class pytest engineer for Python: write/refactor tests, fix flakiness, design fixtures/markers, add coverage, speed up suites (collection/runtime), and optimize CI (GitHub Actions sharding, xdist parallelism, caching). Use when asked about pytest best practices, pytest 9.x features (subtests, strict mode, TOML config), pytest plugins (xdist/cov/asyncio/mock/httpx), or test performance/CI tuning.
6notebook-ml-architect
>
5