Human-in-the-loop approval, custom middleware, and structured output patterns for LangChain agents.
Automate repetitive workflows and reduce manual effort
Example: Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example: Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example: Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
Time estimate: 15-45 minutes depending on use case complexity
Prerequisites
Submit your Claude Code skill and start earning
epx add langchain-ai/langchain-skills --skill langchain-middlewareCompatible with
Supported agents
HumanInTheLoopMiddleware pauses execution before dangerous tool calls, allowing humans to approve, edit arguments, or reject with feedback
Per-tool interrupt policies let you configure different approval rules based on risk level; requires a checkpointer and thread_id for state persistence
Command resume pattern continues execution after human decisions, with support for editing tool a
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionlangchain-middlewareExecute the skills CLI command in your project's root directory to begin installation:
epx add langchain-ai/langchain-skills --skill langchain-middlewareFetches langchain-middleware from langchain-ai/langchain-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
.cursor/skills/langchain-middleware
Restart Cursor to activate langchain-middleware. Access via /langchain-middlewarein your agent's command palette.
Learn more:View source on GitHubSkills CLI docsAbout CursorWhat are agent skills?
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
langgraph-fundamentals
langchain-ai/langchain-skills · Productivity · same repo
llm-council
am-will/codex-skills · AI/ML · same category
brainstorm
buiducnhat/agent-skills · AI/ML · same category
openai-docs
openai/skills · AI/ML · same category
frontend-design
anthropics/skills · AI/ML · same category
ml-paper-writing
orchestra-research/ai-research-skills · AI/ML · same category
Solid pick for teams standardizing on skills: langchain-middleware is focused, and the summary matches what you get after install.
We added langchain-middleware from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
I recommend langchain-middleware for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
langchain-middleware reduced setup friction for our internal harness; good balance of opinion and flexibility.
langchain-middleware fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Registry listing for langchain-middleware matched our evaluation — installs cleanly and behaves as described in the markdown.
Useful defaults in langchain-middleware — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
langchain-middleware is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
langchain-middleware reduced setup friction for our internal harness; good balance of opinion and flexibility.
We added langchain-middleware from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
showing 1-10 of 62