Skills — le catalogue de compétences de vos agents
Chaque skill est une capacité prête à l'emploi (GitHub, PDF, analyse d'images, marketing…) que votre agent charge et utilise de façon autonome. Installez en un clic depuis votre portail.
Create, read, edit, merge, split PDF files. Supports text extraction, table extraction, form filling, watermarks, OCR, and HTML-to-PDF conversion.
Enforces MFA by requiring a secret word to access protected sensitive data and allows emergency reset with a super secret word.
支持双引擎的PDF OCR识别技能，可从影印版PDF文件和图片文件中提取文字内容
Analyze local images including screenshots, receipts, and documents to extract structured text, UI elements, and provide content summaries with confidence le...
飞书电子表格（Sheets）完整操作。当需要创建、读取或编辑飞书电子表格时激活此 skill。 支持：创建表格、读写单元格、追加数据、图片插入、样式设置、合并单元格、行列操作、查找替换。 需要飞书应用凭证：channels.feishu.appId 和 channels.feishu.appSecret（配置在...
OCR documents (PDFs and images) using Gemini 2.5 Flash, PaddleOCR (local), or RapidOCR (local).
Track daily expenses in structured markdown files organized by month. Use when the user wants to log spending, view expense summaries, analyze spending patte...
B2B case study writing with STAR framework, data visualization, and research. Covers structure, customer quotes, metrics presentation, and distribution forma...
智能数据分析 Skill，输入 CSV/Excel 文件和分析需求，输出带交互式 ECharts 图表的 HTML 自包含分析报告
Extract article content from any URL as clean Markdown. Uses Scrapling script as primary method (with auto fast→stealth fallback), Jina Reader as alternative...
PDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。
Repairs garbled speech-to-text input: fixes mistranscribed names, numbers, and commands in voice-dictated messages. Use when a message arrived by voice and a word breaks the sentence, dictation mangles proper nouns, jargon, amounts, times, or email addresses, the user says "no, I said X" or repeats themselves, transcripts contain filler, spoken punctuation, or hallucinated sentences, the user dictates an email or document by voice, or an STT engine (Whisper or cloud speech) needs vocabulary tuning for recurring terms. Not for transcribing audio files or for typed-text typos.
Send generated charts, photos, documents, and ElevenLabs TTS voice clips securely through Telegram using executed shell commands.
党政机关公文生成技能，支持通知、报告、请示、函等公文类型，符合GB/T 9704-2012标准。当用户需要生成党政机关公文、创建正式文件、导出Word格式公文时调用。无论用户使用何种表述方式（如'帮我写个报告'、'生成一份通知'、'制作公文'等），只要涉及公文文档生成，都应使用此技能。
Tasks and goals management via simple markdown files. Create, track, and complete tasks and goals with streak tracking. Stores data in ~/.openclaw/goalgetter...
Extract text from PDF files with automatic OCR fallback for scanned/image-based PDFs. Use when: (1) a user sends a PDF file and the framework did not auto-in...
Create, inspect, and edit Microsoft PowerPoint presentations and PPTX decks with reliable layouts, templates, placeholders, notes, charts, and visual QA. Use...
Generate visually unified image-based PPT/PPTX decks from articles, reports, papers, notes, or outlines.
Match your reading taste by scanning local ebooks and bookmarks to find and recommend books from readers who share your interests and vibes.
获取并生成 A股单只股票的关键指标“体检卡”（估值/盈利质量/现金流/负债/分红/交易活跃度等），输出为统一 Markdown，便于对比与持续跟踪。用在："帮我查600406关键指标"、"做一张国电南瑞体检卡"。
Download ebooks (epub/pdf) from Anna's Archive and upload them to MEGA automatically. Use when the user asks to download a book, find an ebook, search for a...
Convert a guizang-ppt-skill magazine HTML deck into a real editable PowerPoint PPTX. Use this skill whenever the user asks to export, convert, or rebuild a g...
生成中文A股深度策略研报（HTML/PDF格式）。 当用户提到任何A股代码（6位数字）、股票名称、想分析某只股票、或要求生成研报/策略报告时，立即使用此技能。 适用场景：个股深度分析、ST股风险研判、热点题材追踪、戴帽摘帽分析、行业龙头估值分析、困境反转研判。 输出：专业排版研报，包含封面、核心观点、价格结构、数...
跟课程进度逐讲伴读：拿到一讲 PDF 就写顺原讲义顺序的中文伴读文档（每 1–3 页一节、讲透、标考试怎么考与证据级别），并把新知识落进课程文件夹 study/记忆库；追问已入库概念、期末统一总结。用于"给这个 PPT 写辅助文档""把 lecture N 入库""write a companion doc for this lecture"；触发词 $course-study。不代写要提交的作业答卷（同型题只在附录里演练并标明来源）；物理题的费曼式讲解归 $feynman-physics-distiller；「总结今天的记忆」不属本 skill。