Atomics-hub/agentk
AgentK is a user-space security kernel for AI agents: an MCP/tool boundary with typed syscalls, taint-aware policy, capability receipts, signed evidence, and replayable flight logs.
AgentK is a user-space security kernel for AI agents: an MCP/tool boundary with typed syscalls, taint-aware policy, capability receipts, signed evidence, and replayable flight logs.
npx add-skill Atomics-hub/agentkAgentK is a user-space security kernel for AI agents: an MCP/tool boundary with typed syscalls, taint-aware policy, capability receipts, signed evidence, and replayable flight logs.
University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning required.
Content ops Claude Code skills (us-trend-scout, etc.) - 测试中
An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Reusable AI skills for Codex CLI, Claude Code, and OpenCode. Write once, deploy everywhere. Portable agent workflows and best practices.
Local semantic search for AI agents. 20+ document formats, hybrid search, agent memory, zero cloud dependencies. MCP server + CLI.
Codex skill for writing Chinese graduation design manuals from project facts, templates, and verified references.