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 skills add 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.
Codex skill for SCI and IEEE paper writing workflows with literature reading, direction selection, LaTeX scaffolding, and MATLAB simulation loops.
Ten rules for writing a planning document — drop-in CLAUDE.md / AGENTS.md system prompt that turns any AI agent into a senior planner. KO/EN bilingual. GitHub Pages: https://cskwork.github.io/planning-doc-rules/
通过流程图来构建流水线提示词, 辅助Claude Code的Skill和Agent提示词编写; Flowcharts are used to construct pipeline prompts, assisting in the writing of Skill and Agent prompts for Claude Code.
Manage and optimize OpenClaw workspace markdown files to maintain agent identity, memory, and operational clarity across AI channels.
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex), backed by Markdown and Milvus.
Manage SEO tasks with 44 Claude Code commands for audits, backlink analysis, ranking tracking, SERP research, and content brief generation.