soba-labs

soba-labs/langchain-agent-skills

Plugin Claude Code

Plugin marketplace listing 3 plugins: langgraph-skills, langsmith-skills, deepagents-skills.

soba-labs/langchain-agent-skills

Instructions file CodexOpenCode

Instructions for soba-labs/langchain-agent-skills, covering repository guidelines, project overview, repository structure, marketplace configuration (claude code) and development environment.

soba-labs/langchain-agent-skills

Instructions file

Instructions for soba-labs/langchain-agent-skills: This repository uses AGENTS.md as the single source of truth for contributor and agent guidance.

soba-labs/langchain-agent-skills

Skill Claude CodeCodex

Use the writetodos tool effectively for task planning and decomposition in Deep Agents. Use when users want to (1) implement task planning with writetodos, (2) break down complex tasks into subtasks, (3) track agent progress through todos, (4) debug why todos aren't completing, (5) design todo structures for different…

soba-labs/langchain-agent-skills

Skill Claude CodeCodex

Initialize, validate, and troubleshoot Deep Agents projects in Python or JavaScript using the deepagents package. Use when users need to create agents with built-in planning/filesystem/subagents, configure middleware/backends/checkpointing/HITL, migrate from createreactagent or createagent, scaffold projects with repo…

soba-labs/langchain-agent-skills

Skill Claude CodeCodex

Implement multi-agent coordination patterns (supervisor-subagent, router, orchestrator-worker, handoffs) for LangGraph applications. Use when users want to (1) implement multi-agent systems, (2) coordinate multiple specialized agents, (3) choose between coordination patterns, (4) set up supervisor-subagent workflows…

soba-labs/langchain-agent-skills

Skill Claude CodeCodex

Implement LangGraph error handling with current v1 patterns. Use when users need to classify failures, add RetryPolicy for transient issues, build LLM recovery loops with Command routing, add human-in-the-loop with interrupt()/resume, handle ToolNode errors, or choose a safe strategy between retry, recovery, and…

soba-labs/langchain-agent-skills

Skill Claude CodeCodex

Initialize and configure LangGraph projects with proper structure, langgraph.json configuration, environment variables, and dependency management. Use when users want to (1) create a new LangGraph project, (2) set up langgraph.json for deployment, (3) configure environment variables for LLM providers, (4) initialize…

soba-labs/langchain-agent-skills

Skill Claude CodeCodex

Design state schemas, implement reducers, configure persistence, and debug state issues for LangGraph applications. Use when users want to (1) design or define state schemas for LangGraph graphs, (2) implement reducer functions for state accumulation, (3) configure persistence with checkpointers…

soba-labs/langchain-agent-skills

Skill Claude CodeCodex

Use this skill when you need to test or evaluate LangGraph/LangChain agents: writing unit or integration tests, generating test scaffolds, mocking LLM/tool behavior, running trajectory evaluation (match or LLM-as-judge), running LangSmith dataset evaluations, and comparing two agent versions with A/B-style offline…

soba-labs/langchain-agent-skills

Skill Claude CodeCodex

Deploy and operate production agent servers with LangSmith Deployment. Use when work involves choosing Cloud vs Hybrid/Self-hosted-with-control-plane vs Standalone, preparing/validating langgraph.json, creating deployments or revisions, rolling back revisions, wiring CI/CD to control-plane APIs, configuring…

soba-labs/langchain-agent-skills

Skill Claude CodeCodex

Fetch, organize, and analyze LangSmith traces for debugging and evaluation. Use when you need to: query traces/runs by project, metadata, status, or time window; download traces to JSON; organize outcomes into passed/failed/error buckets; analyze token/message/tool-call patterns; compare passed vs failed behavior; or…

soba-labs/langchain-agent-skills

Skill Claude CodeCodex

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.