QMAI
AGENTS.md827 starsChanged 2 months agoLicence not identifiedView on GitHub
QMAI 是长篇小说记忆型 AI 写作桌面系统（Tauri 2 + React 19 + TypeScript），不是普通聊天写作工具。目标场景：200 万～300 万字连载，解决 AI 遗忘前文、人设崩坏、时间线混乱、伏笔丢失。 核心理念：写前自动提取上下文 → 写后自动沉淀章节记忆 → 图谱追踪关系变化 → 审查防崩坏 → 人工确认定稿。 修改上下文逻辑时，保持 SECTION_PRIORITY 顺序，并考虑 token 预算二次裁剪。 小说相关逻辑优先放 src/lib/novel/，通过…
- Reads credentials
In this repository56 other files it gives its agents.
- AGENTS.mdAGENTS.md
- qmai-releaseSkill
- de-AI-writingSkill
- good-writingSkill
- andrej-karpathy-perspectiveSkill
- bi-bi-dong-perspectiveSkill
- bi-yao-perspectiveSkill
- cao-cao-perspectiveSkill
- catherine-great-perspectiveSkill
- charlie-munger-perspectiveSkill
- chen-pingan-perspectiveSkill
- elon-musk-perspectiveSkill
- er-lang-shen-perspectiveSkill
- fan-xian-perspectiveSkill
- feynman-perspectiveSkill
- han-fei-perspectiveSkill
- hua-mulan-perspectiveSkill
- huang-rong-perspectiveSkill
- ilya-sutskever-perspectiveSkill
- jane-austen-perspectiveSkill
- li-bai-perspectiveSkill
- lin-daiyu-perspectiveSkill
- li-qingzhao-perspectiveSkill
- li-shimin-perspectiveSkill
- li-si-perspectiveSkill
- lu-xueqi-perspectiveSkill
- lu-xun-perspectiveSkill
- lv-shu-perspectiveSkill
- marie-curie-perspectiveSkill
- mei-du-sha-perspectiveSkill
- mrbeast-perspectiveSkill
- munger-perspectiveSkill
- naval-perspectiveSkill
- nezha-perspectiveSkill
- paul-graham-perspectiveSkill
- qin-shihuang-perspectiveSkill
- steve-jobs-perspectiveSkill
- sun-wukong-perspectiveSkill
- sun-yuchen-perspectiveSkill
- su-shi-perspectiveSkill
- taleb-perspectiveSkill
- trump-perspectiveSkill
- wang-xifeng-perspectiveSkill
- wang-yangming-perspectiveSkill
- wu-zetian-perspectiveSkill
- xiao-feng-perspectiveSkill
- xiao-wu-perspectiveSkill
- xiao-xuner-perspectiveSkill
- x-mastery-mentorSkill
- zhang-liang-perspectiveSkill
- zhang-xiaofan-perspectiveSkill
- zhangxuefeng-perspectiveSkill
- zhang-yiming-perspectiveSkill
- zhao-gao-perspectiveSkill
- zhuang-zi-perspectiveSkill
- zhuge-liang-perspectiveSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.