메뉴
面向 OpenClaw 的行为制度化技能。用于把“诚实汇报、先验证再宣称、危险动作先确认、何时自主推进”等要求写成可执行规则，而不是空泛口号。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when the user wants academic literature search, paper discovery, citation graph lookup, PubMed or Google Scholar retrieval, arXiv or Rxiv preprint search, or AI4Scholar-powered citation insertion inside Codex. Prefer the bundled script over generic web search when the user explicitly wants AI4Scholar.
Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Academic literature review workflow for research topic selection. Use when user asks to do literature survey, research topic exploration, or systematic review for a specific field. Triggers include: "literature review for [field]", "research topic selection", "help me design a search strategy", "systematic literature search", or when user describes a multi-step research workflow involving database searching, relevance assessment, journal filtering, and topic analysis.
Use this skill when the user wants to work with Google NotebookLM from Codex through the `notebooklm-py` CLI, including logging in, listing notebooks, selecting a notebook, adding sources, asking questions, exporting metadata, or generating NotebookLM artifacts.
| name | behavior-institutionalization |
| description | 面向 OpenClaw 的行为制度化技能。用于把“诚实汇报、先验证再宣称、危险动作先确认、何时自主推进”等要求写成可执行规则，而不是空泛口号。 |
这个 skill 解决的是：怎么把 agent 的行为要求写成 长期稳定、可执行、可审计 的规则。
不是写“要专业”“要谨慎”，而是写成这种能落地的话：
把抽象要求改写成操作规则：
不要写：保持诚实
要写：
不要写：谨慎处理危险操作
要写：
不要写：自主完成任务
要写：
