Claude Skills by luokai0

Web scraping and content comprehension agent — multi-strategy extraction with cascade fallback, news detection, boilerplate removal, structured metadata, and LLM entity extraction

Extract structured information from websites using web_fetch for simple pages and browser automation for dynamic sites, login-gated flows, pagination, infinite scroll, or pages that require clicking/searching/filtering. Use when the user asks to scrape a site, collect listings, gather fields from many pages, monitor website changes, or turn webpage content into structured summaries/JSON/CSV.

🖼️ 任意URL全页面截图 + PDF导出工具。当用户要求截取网页、保存网页快照、截图存档、做QA对比、导出PDF时使用。支持百度/知乎/微信公众号/小红书等中文网站，自动等待JS渲染交付PNG/JPG/PDF。

Retrieve search results from web search engines.

通用网络搜索技能，支持多引擎搜索（百度、必应、DuckDuckGo），无需API密钥即可获取实时信息

Neural web search, content extraction, company and people research, code search, and deep research via the Exa MCP server. Use when you need to: (1) search the web with semantic understanding — not just keywords, (2) find research papers, news, tweets, companies, or people, (3) extract clean content from URLs, (4) find semantically similar pages to a known URL, (5) get code examples and documentation, (6) run deep multi-step research with a report, (7) get a quick synthesized answer with cita...

Use this skill when users need to search the web for information, news, images, or videos. Triggers include: requests to \"search for\", \"find information about\", \"look up\", \"what's the latest on\", or any request requiring current web content. Also use for research tasks, fact-checking, finding visual resources, or gathering recent news. Requires OpenClawCLI installation from clawhub.ai. Do NOT use when Claude's built-in web_search tool is more appropriate for simple queries.

Web search using DuckDuckGo Instant Answer API (no API key required). Use when you need to search the web for information, definitions, calculations, conversions, or quick facts. Also use when user mentions "search", "look up", "find information", "what is", "how to", or "google something". The skill provides instant answers, definitions, abstracts, and related topics without requiring external API credentials.

网络搜索技能，使用 Minimax Coding Plan Search API 进行网络搜索

Unified multi-provider web search and URL extraction skill with intelligent auto-routing across Serper, Brave, Tavily, Querit, Linkup, Exa, Firecrawl, Perplexity, You.com, and SearXNG.

Build, debug, and deploy websites with HTML, CSS, JavaScript, modern frameworks, and production best practices.

公众号文章写作全流程助手（通用版）。支持多账号管理，适用于任何公众号方向。 当用户说"今天写什么"、"帮我写公众号"、"选题"、"公众号选题"、"写文章"、 "公众号文章"、"更新公众号风格"、"这篇文章写得好"、"新建公众号"时触发。 支持完整工作流：初始化/切换账号画像 → 搜索热门话题生成选题 → 选题确认 → 文章创作 → 存档到企业微信文档 → 持续学习风格。

用于撰写结构清晰的中文周报。只要用户提到“周报、weekly report、本周总结、工作复盘、下周计划、给老板汇报”，即使没有明确说“写周报”，也应主动使用此技能来生成可直接发送的周报内容。

Use when you want to generate Architecture Decision Records from this session. Triggers on \"write ADRs\", \"document our decisions\", \"create decision records\", \"record the choices we made\". Also useful after design discussions where decisions were reached but not documented. Does NOT extract decisions alone (use adr-decision-extraction) or provide MADR template (use adr-writing). Orchestrates the full workflow: subagent extraction, user confirmation, parallel generation, and verification.

1. **ALWAYS use Digital Asset (DA) standard** for ALL NFT-related contracts (collections, marketplaces, minting) 2. **ALWAYS import** `aptos_token_objects::collection` and `aptos_token_objects::token` modules 3. **ALWAYS use** `Object<AptosToken>` for NFT references (NOT generic `Object<T>`) 4. **NEVER use legacy TokenV1** standard or `aptos_token::token` module (deprecated) 5. See `../../../patterns/move/DIGITAL_ASSETS.md` for complete NFT patterns

Write, update, and read OpenNote notes through the public API. Use when the user wants to publish notes, upload note images, manage labels, or look up previously written notes.

Plan, draft, version, and refine written content with enforced versioning and quality audits.

作家风格蒸馏器。给定一位作家的虚构作品 + 非虚构文本 + 生平定位，蒸馏出她的核心信念、世界观、句法纪律、论证习惯与黑名单，最终产出一份可调用的写作风格 skill，用于在写作时进入这位作家的状态。 适用场景：私人写作风格借鉴；为某个组织或品牌建立有出处可考的 voice；为虚构作品塑造叙事者声音；为论文/散文/书信寻找一个非 AI 默认体的语调。 内置交互纪律：禁止 AI 单方面下定论，蒸馏过程必须包含两次用户校验——表面阅读后的"信念候选确认"、与"黑名单/反例"的人为加锋。

Fix AI writing patterns that create repetitive and robotic content

浏览器智能控制。自动化操作、截图、填表、数据抓取。

小红书爆款内容写作助手，帮助生成高点击率、**像人写**的笔记。包含去AI味检查、7种标题公式、5种开头模板、3种结尾模板、SEO优化。Use when user wants to write XiaoHongShu content, generate viral post titles, or needs help with RedNote writing. Trigger on: 写小红书笔记、小红书文案、爆款标题、种草笔记、学习日记、干货分享。

每日数据追踪与历史记录。维护每日关键指标的历史表格（日期/Revenue/Gross Adds/EOP/Paid Subs/端拆分），支持 WoW 计算和趋势分析。数据追加到 memory/powerbi-daily-track.md 的历史表。

Use when user needs to write professional business emails in multiple languages. Use when drafting foreign trade emails such as inquiry replies, quotation emails, or follow-up messages. Use when generating personalized B2B email sequences for international clients. Use when user mentions "邮件撰写", "外贸邮件", "多语言邮件", "开发信", "询盘回复", "报价邮件", "跟进邮件", "商务邮件".

基于ZAKER权威资讯库进行关键词新闻检索，支持指定时间范围。Use when the user asks about 搜索新闻, 某事件新闻, 某人物新闻, 某关键词相关新闻, 查新闻, 新闻检索, 相关新闻, 某时间段新闻.

name: 邮件生成助手 description: 根据用户提供的要点，自动生成正式或友好的英文/中文邮件。 trigger: 用户说“写封邮件”、“生成邮件”或“帮我起草邮件”。 input: - 收件人 (string, required) - 主题 (string, optional) - 要点列表 (array, required) - 语气 (enum: 正式/友好, default: 正式) steps: 1. 解析用户给出的邮件要点。 2. 根据语气选择模板（正式：Dear X, ...；友好：Hi X, ...）。 3. 将要点组织成连贯段落，添加适当的开场和结尾。 4. 输出完整邮件正文，并提示用户可修改。 output: 纯文本格式的邮件内容，带标题和落款。 example: user: 帮我写封正式邮件给 john@example.com，主题是项目进度汇报。要点：1. 已完成前端开发；2. 后端预计周五完成；3. 需要下周安排测试。 assistant: 邮件正文...

Use when 需要理解紫鸟ERP API 的定位、能力、权限体系或调用流程， 用于 ERP 系统对接规划、集成设计或接口评估。 不要用于直接查阅具体接口参数——查阅时读取 reference/ 下对应文件。

当需要获取网页内容时使用（搜索结果页面、博客文章、文档等）。使用 URL 转 Markdown 服务将网页转换为可读文本。 触发场景：用户说"帮我查一下"、"看看这个链接"、"获取 xx 的信息"等需要上网抓信息的情况。