Pause your AI agent. Ask a human. Resume with their answer. Open source human-in-the-loop (HITL) library for production LLM agents: Slack, email, and web dashboard. Typed Pydantic and Zod responses. Durable Temporal and LangGraph adapters. AI verifier. Audit trail. Self-hosted, Apache 2.0. Python and TypeScript.
npx add-skill awaithumans/awaithumans-human-in-the-loop-ai-agentsPause your AI agent. Ask a human. Resume with their answer. Open source human-in-the-loop (HITL) library for production LLM agents: Slack, email, and web dashboard. Typed Pydantic and Zod responses. Durable Temporal and LangGraph adapters. AI verifier. Audit trail. Self-hosted, Apache 2.0. Python and TypeScript.
Agent Skill that writes honest, structured READMEs — classifies your project type, audience & distribution model instead │ │ │ of filling templates. Works with Claude Code, Cursor, Codex, Gemini CLI and more AI agents.
Keyword research that scores by estimated monthly revenue, not search volume. ORCAS CTR data, intent-based conversion rates, AI Visibility scoring, hyper-local long-tail generation. Installable skill for Claude Code, OpenClaw, Codex.
Review and maintain AI agent instruction documents (AGENTS.md, SKILL.md, MCP docs) to prevent quality degradation from incremental edits. Use when reviewing or refactoring these documents.
AI-powered course material generator for programming classes. AgentSkill for Claude Code, OpenClaw, and Codex.
Claude Code Skill - 小红书财经笔记写作系统，基于120+信息源深度调研，7个核心框架、10种标题模板、完整合规体系
An MCP tool that allows agents to orchestrate other agents with Claude skills, enabling pseudocode scripting over skill-based stateless workflows