Ask me what skills you need
What are you building?
Tell me what you're working on and I'll find the best agent skills for you.
把碎片化的信息变成持续积累、互相链接的知识库。你只需要提供素材,AI 做所有的整理工作。
llm-wiki 帮你构建一个持续增长的个人知识库。它不是传统的笔记软件,而是一个让 AI 帮你维护的 wiki 系统:
传统方式(RAG/聊天记录)的问题:每次问问题,AI 都要从头阅读原始文件,没有积累。知识库的价值在于知识被编译一次,然后持续维护,而不是每次重新推导。
告诉用户这两步就够了:
Scripts located in scripts/ subdirectory.
Path Resolution:
SKILL_DIR = this SKILL.md's directory${SKILL_DIR}/scripts/<script-name>核心主线(本地文件、纯文本、已有知识库操作)默认不需要这些提取依赖。
只有当用户给的是 URL 类来源,并且明确要自动提取网页 / X / 微信公众号 / YouTube / 知乎内容时,才检查以下可选依赖。
如果缺失,提示用户运行:
bash ${SKILL_DIR}/install.sh --platform <当前平台> --with-optional-adapters
可选依赖 skill / 工具:
baoyu-url-to-markdown — 普通网页、X/Twitter、部分知乎提取wechat-article-to-markdown — 微信公众号提取youtube-transcript — YouTube 字幕提取即使这些依赖缺失,skill 仍可工作(用户可以直接提供本地文件、粘贴文本,或改走手动入口)。
外挂失败统一分成 not_installed / env_unavailable / runtime_failed / unsupported / empty_result 五类。
npx skills add sdyckjq-lab/llm-wiki-skill --skill llm-wiki-skillHow clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
Mostly clear, but there are still a few confusing or poorly structured parts.
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
Partially actionable with several concrete steps, but still missing important details.