SKILL-warehouse

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.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

Best practices and comprehensive guide for Remotion - programmatic video creation in React with animations, compositions, and media handling

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

指导学术论文Introduction与Conclusion的差异化撰写策略。使用此技能：1)撰写论文引言(Introduction)时采用沙漏模型倒三角结构；2)撰写论文结论(Conclusion)时采用正三角结构；3)需要理解Introduction与Conclusion的差异化对比时；4)需要5W1H研究方法框架指导时。

综合性英文学术写作助手，集成论文撰写、翻译、润色、AI痕迹检测与降AI率功能。用于：1)撰写学术论文Introduction/Conclusion；2)中英互译；3)中英文润色、缩写/扩写；4)检测并移除AI写作痕迹；5)逻辑检查与审稿。

面向 OpenClaw 的子 agent 生命周期设计与审计技能。用于设计或检查 sessions_spawn、subagents、隔离 session、上下文继承、进度回传、恢复与清理逻辑。

AI 学术论文写作 Prompt 模板库。用于：论文翻译（中英互译）、润色（英文/中文）、缩写/扩写、去 AI 味、逻辑检查、图表标题生成、实验分析、审稿等场景。

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。

获取 B 站 up 主所有视频的字幕并生成逐字稿。当用户想要获取某个 B 站 up 主的全部视频字幕内容时使用。

面向 OpenClaw 的风险半径权限设计技能。用于设计或审计删除、执行 shell、改配置、外部发送、子 agent 派生等高风险动作的权限与确认逻辑。

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

智能文献引用检索工具。根据用户输入的学术文本（如论文Introduction、Discussion等），自动识别需要引用的陈述，并检索相关真实文献提供引用建议。

Delegate coding tasks to Codex CLI for execution, or discuss implementation approaches with it. CodeX is a cost-effective, strong coder — great for batch refactoring, code generation, multi-file changes, test writing, and multi-turn implementation tasks. Use when the plan is clear and needs hands-on coding. Claude handles architecture, strategy, copywriting, and ambiguous problems better.

Consensus-powered NIH grant research skill. Use when someone wants to find grants for their research idea. Runs a 5-facet positioning analysis via Consensus (with draft Significance/Innovation language), maps the research to the right NIH institutes and study sections, finds NOSIs and funded overlap, and produces an editable Word document (.docx) with budget/scope guidance, submission timelines, and program officer recommendations. Trigger on: 'find grants for my research idea', 'what grants match my research', 'help me find NIH funding', 'grant opportunities for my research', or any grant-related request where speed and clarity matter.

面向 OpenClaw 的长上下文卫生系统技能。用于设计或审计 memory、skill 注入、工具输出预算、压缩、去重、恢复与长会话稳定性。

钉钉/飞书集成 - 企业通讯、机器人、自动化工作流（Slack 中国版）

CLI download tools for YouTube and WeChat

撰写优秀教案（课程思政教案）的助手。根据提供的课程信息、案例背景和思政元素，自动生成符合八大模块标准框架的优秀教案。适用于各类课程的教案比赛、课程思政示范课申报等场景。

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Create and populate Feishu (Lark) Bitable (multidimensional tables) with automated cleanup. Use when the user needs to: 1. Create a new Bitable from scratch with clean structure (no placeholder rows/columns) 2. Batch create fields and records in a Bitable 3. Convert structured data into a Bitable format 4. Create data tables for research, comparison, or tracking purposes Automatically handles: empty placeholder row cleanup, default column removal, intelligent primary field naming, and batch record creation.

Delegate design tasks to Gemini (gemini-2.5-flash-preview) via aicodemirror API. Use when you need UI/web design (single-page HTML), SVG icons/illustrations, color palettes, typography suggestions, layout advice, or any visual design reference. Gemini acts as your designer friend — ask it to create HTML page mockups, design SVG icons, suggest design systems, or give design feedback. Triggers on design-related requests like "design a page", "create an icon", "suggest colors", "make a logo", "UI mockup", "design reference".

面向 OpenClaw 的 Hook 治理层技能。用于设计或审计工具前后置 hook、策略注入、附加上下文、阻断与非致命错误处理。

移除文本中AI生成写作的痕迹。在编辑或审阅文本时使用，让内容听起来更自然、更具人情味。本工具基于维基百科全面的《AI写作痕迹识别》指南，可检测并修正多种AI写作模式，包括：夸张的象征手法、宣传性语言、表面化的-ing形式分析、模糊的归因、破折号滥用、三段式结构、AI常用词汇、否定平行结构以及过多的连接短语。致谢：原技能由@blader开发 - https://github.com/blader/humanizer

Use when Codex needs to obtain a literature PDF and normal routes failed: Open Access/full-text links are unavailable, AI4Scholar cannot download it, or an authorized institutional/source workflow is needed as a last resort. Uses the JLYL literature delivery site through the Browser Use plugin with user-provided credentials or an existing logged-in session.

专门针对Journal of Thoracic Oncology (JTO) 杂志的学术论文写作助手。遵循JTO官方投稿指南，支持Original Articles、Brief Reports、Rapid Communications等文章类型的撰写，确保符合格式要求、引用规范（AMA第11版）、伦理声明等投稿标准。

Automated literature review assistant that searches academic papers, builds a strategic search plan, and synthesizes findings into a professionally formatted Word document (.docx) research guide. Trigger this skill when the user expresses intent to explore a research topic, including casual phrasing like: "I'm starting a literature review on X", "I'm writing a paper on X", "help me research X", "I'm doing research on X", "can you help me research X". Do NOT trigger for single one-off paper searches where the user just wants a quick list of papers — that is a simple Consensus search. This skill is for when the user wants depth, strategy, and synthesis.

面向 OpenClaw 的 MCP 集成平面技能。用于设计或审计 MCP 连接、认证、工具发现、资源发现、超时、会话失效恢复与大结果持久化策略。

面向 OpenClaw 的多 agent 编排技能。用于设计或审计多个 session / subagent / ACP agent 之间的任务拆分、上下文裁剪、权限隔离、并行策略与结果回收。

Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level orientation to opencli, see opencli-usage.

Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing adapters — see opencli-adapter-author for that.

Use at the start of any OpenCLI session — this is the top-level map of what `opencli` can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".