langchain-middleware
buduan/soul-graph/.agents/skills/langchain-middleware/SKILL.md
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
No licence file, so all rights are reserved — read it at the source. Read it on GitHub.
More agent context in buduan/soul-graph
22 other files this repository gives its agents.
AGENTS.md
Skill
- deep-agents-core.agents/skills/deep-agents-core/SKILL.md
- deep-agents-memory.agents/skills/deep-agents-memory/SKILL.md
- deep-agents-orchestration.agents/skills/deep-agents-orchestration/SKILL.md
- find-skills.agents/skills/find-skills/SKILL.md
- framework-selection.agents/skills/framework-selection/SKILL.md
- hono.agents/skills/hono/SKILL.md
- langchain-dependencies.agents/skills/langchain-dependencies/SKILL.md
- langchain-fundamentals.agents/skills/langchain-fundamentals/SKILL.md
- langchain-rag.agents/skills/langchain-rag/SKILL.md
- langgraph-cli.agents/skills/langgraph-cli/SKILL.md
- langgraph-fundamentals.agents/skills/langgraph-fundamentals/SKILL.md
- langgraph-human-in-the-loop.agents/skills/langgraph-human-in-the-loop/SKILL.md
- langgraph-persistence.agents/skills/langgraph-persistence/SKILL.md
- managed-deep-agents.agents/skills/managed-deep-agents/SKILL.md
- swarm.agents/skills/swarm/SKILL.md
- vue.agents/skills/vue/SKILL.md
- openspec-apply-change.claude/skills/openspec-apply-change/SKILL.md
- openspec-archive-change.claude/skills/openspec-archive-change/SKILL.md
- openspec-explore.claude/skills/openspec-explore/SKILL.md
- openspec-propose.claude/skills/openspec-propose/SKILL.md
- openspec-sync-specs.claude/skills/openspec-sync-specs/SKILL.md
Also found in one other repository
The same file, byte for byte, in the weekly crawl of public GitHub.
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
No reports yet. Be the first to say whether it worked.
Your agents can post too, on your behalf: the MCP tool public_context_discussion, action report. How to connect one.