CMS, document processing, and media generation.
Download images and videos from X (Twitter) posts to ~/Downloads. Use when user shares an X/Twitter link and wants to save media, or says '下载', 'download', '保存图片', '保存视频', or provides a x.com/twitter.com URL with intent to download media.
Intelligent draft merging tool with quality assessment and conflict resolution. Merges multiple drafts into a high-quality article, supporting multiple input formats, intelligent evaluation, conflict detection, highlight fusion, and multi-format output. Use when user says "合并稿子", "合稿", "merge drafts", "把这几篇合成一篇", "综合这几份稿子", "多稿合一", "稿件合并", "draft merge", "整合稿件", "汇总文稿", "把所有稿子合并", "起草稿合并", "初稿合并", "多个版本合并", "copy merge", "文章合并".
Generate Obsidian-compatible visualization files (Excalidraw / Mermaid / Canvas). Supports text descriptions and image inputs, outputs editable diagrams in Obsidian or standard formats.
Extract and parse content from URLs. Triggers on: user provides a URL to extract content from, another skill needs to parse source material, "parse this URL", "extract content", "解析链接", "提取内容".
整理和起草法律文书（庭后意见书、代理词、上诉状、答辩状、反驳意见书、质证意见等）。当用户提供案件素材（庭审笔录、证据清单、法律条文、口头陈述要点）需要整理成结构化法律文书时使用。支持行政诉讼、民事诉讼、消费者权益保护、互联网平台纠纷、合同纠纷等场景。
Organize, deduplicate, summarize, and compress OpenClaw or Clawd memory files. Use when the user asks to organize memory, reduce duplication, convert raw daily notes into concise summaries, or maintain long-term memory in `MEMORY.md`.
This skill should be used when users need to scrape hot news topics from Chinese platforms (微博、知乎、B站、抖音、今日头条、腾讯新闻、澎湃新闻), generate summaries, and cite sources. It supports both API-based and direct scraping methods, and offers both extractive and abstractive summarization techniques.
Convert files to beautifully formatted Markdown. TRIGGER when user asks to convert a file to Markdown, extract text from PDF/DOCX/PPTX/XLSX, or format a document as Markdown.
Quickly save web content as formatted Markdown. TRIGGER when user pastes a URL and wants to save/clip it, read-later, or extract content from YouTube, Twitter/X, WeChat, Bilibili, Telegram, RSS, or any web page.
将txt文本转换为epub文件，使用纯规则进行章节识别与分割。适用于小说、教程和一般长文，不内置AI接口。
Convert Markdown files to PDF with multiple backend options (WeasyPrint, Pandoc, wkhtmltopdf). Supports syntax highlighting, tables, images, custom CSS themes, and page styling. Use when converting Markdown (.md) to PDF, generating documents from markdown, creating PDF reports, or any markdown-to-pdf conversion task. Triggers on markdown to pdf, md to pdf, convert markdown pdf, generate pdf from markdown.
Generate job-specific tailored resumes from a base profile and job description. First collects structured user info (personal details, work history, side projects, education, skills, certificates), then reads a target JD to produce a polished HTML resume customized to match. Outputs print-optimized HTML that exports cleanly to PDF via browser print. Use when user wants to create/rewrite/tailor a resume for a specific job posting, optimize a resume for ATS, build a resume from scratch, or says "make me a resume" / "tailor my resume" / "customize resume for this job". Supports Chinese and English resumes.
AI-powered JD-matched resume generator with native Chinese and English support. Collects structured user profile (work history, projects, skills, education), parses target job descriptions, performs explicit match analysis before generating, then outputs print-optimized HTML resume + auto-export PDF. Core strengths: (1) JD→resume full pipeline with transparency, (2) Chinese resume native support, (3) persistent profile reuse across multiple JDs. Use when: tailoring resume for a job posting, creating resume from scratch, optimizing for ATS, building Chinese/English resume, "make me a resume", "customize resume for this job", "简历定制", "针对岗位优化简历".
导出电商数据为 Excel/PDF 报告，支持价格历史、销量分析、竞品对比。适合电商卖家、市场分析师。
中文日常工具集：天气预报、汇率查询、新闻摘要、快递追踪。适合中文用户日常使用，无需API密钥，开箱即用。Use when Chinese users need weather forecasts, currency exchange rates, news summaries, or package tracking in Chinese.
Instantly summarize any content — articles, PDFs, YouTube videos, web pages, long documents, or pasted text. Extracts key points, action items, and insights. Use when you need to quickly digest long content, create meeting notes, or extract takeaways from any source.
Fetch recent unread Gmail (yesterday + today) and send a digest to the user.
Professional resume generator with PDF, Word, and HTML export. Supports multiple templates, auto-layout, Chinese/English bilingual, and Markdown/HTML input. Perfect for academic and professional CVs.
PDF manipulation via Stirling-PDF API. Merge, split, convert, OCR, compress, sign, redact, and more. Self-hosted.
Stateless translation and summarization machine. Always respond with raw JSON only — no markdown, no explanation, no preamble, no code fences. Trigger this skill whenever the input contains an "action" field with value "translate", "summarize", "translate_and_summarize", or "heartbeat", OR when the user sends plain text intended to be translated or summarized. Also trigger for any request like "dịch", "translate", "summarize", "tóm tắt", "dịch và tóm tắt" or any message that should be converted to a structured JSON translation result. Always use this skill — do NOT attempt to build translation/summarization JSON from scratch without it.
PDF 学习助手，帮助用户从 PDF 文档中学习知识。当用户说"辅助学习"、"用 sigma 学习"、"帮我学习这本书"时触发。功能：(1) 读取 PDF 并按类别存储在 ~/.learning-docs/ 下，(2) 对 PDF 内容做 RAG 检索，(3) 结合通用知识用 sigma 技能对用户进行提问式学习。
