z3z1ma/agent-loom
The missing middle between prompt and patch: a Markdown-native protocol that turns AI coding sessions into durable work products agents can continue, audit, and trust
The missing middle between prompt and patch: a Markdown-native protocol that turns AI coding sessions into durable work products agents can continue, audit, and trust
npx skills add z3z1ma/agent-loomThe missing middle between prompt and patch: a Markdown-native protocol that turns AI coding sessions into durable work products agents can continue, audit, and trust
Claude skill that translates a workflow use case into a Concord architecture design document via structured interview
Agent skills for Chinese, Japanese, and Korean text layout. 日本語組版 / 中文排版 / 한국어 텍스트 레이아웃 agent skills.
降低中文学术写作（本/专科毕业论文）AIGC检测率的专项 skill。 基于真实论文改写实验（AIGC率从 >50% 降至 11%）归纳的规律，并参考 Wikipedia「Signs of AI writing」项目的系统性模式分类。 检测并修复中文AI写作的典型模式；含中英术语与缩写规范、会话记忆库（避免 重复释义、滚动段落摘要防前后不一致）、LaTeX 源文件保护规则。支持：降低AI率、人工润色、降低AIGC、 humanize、去AI味、学术写作润色、论文降重、AIGC检测、AI痕迹消除、学术文本 人工化处理、AIGC检测报告。
Agent skill for writing prose based on https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
Native Word Track Changes for AI agents. An MCP server and Python SDK that translates LLM edits into safe DOCX redlines without breaking formatting.
Privacy-first agent skill for curated Obsidian memory closeouts, retrieval, Codex, and Claude