发现 Skills

Real-time voice conversations in Discord voice channels with Claude AI

Create a minimalist marketing plan focused on building an audience through content, not ads. Use when someone has product–market fit (about 100 customers) and wants to scale with marketing, or needs a content strategy.

Browser automation skill for controlling Google's NotebookLM. Handles reading and querying notebooks, adding sources (URLs, text, files, YouTube links, synthesized content), generating Studio outputs (Audio Overview, infographics, slide decks, study guides, briefing docs, mind maps, timelines, FAQs), and creating new notebooks. Triggers on any phrase involving NotebookLM — 'open NotebookLM', 'check my [name] notebook', 'pull info from NotebookLM', 'ask my notebook about X', 'add [source] to NotebookLM', 'create an infographic in NotebookLM', 'use NotebookLM Studio', 'generate a slide deck from my notebook', or any variation where the goal involves NotebookLM. Requires browser automation environment — fails gracefully when unavailable.

Complete Proxmox VE management - create/clone/start/stop VMs and LXC containers, manage snapshots, backups, storage, and templates. Use when user wants to manage Proxmox infrastructure, virtual machines, or containers.

Office productivity workflow covering document creation, spreadsheet automation, presentation generation, and integration with LibreOffice and Microsoft Office formats.

Conduct comprehensive AI-powered research with citations via the Tavily CLI. Use this skill when the user wants deep research, a detailed report, a comparison, market analysis, literature review, or says "research", "investigate", "analyze in depth", "compare X vs Y", "what does the market look like for", or needs multi-source synthesis with explicit citations. Returns a structured report grounded in web sources. Takes 30-120 seconds. For quick fact-finding, use tavily-search instead.

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.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Technical SEO auditor and fixer. Runs Lighthouse/PageSpeed audits on websites or local dev servers, analyzes SEO, performance, and accessibility scores, and automatically implements fixes for meta tags, structured data, Core Web Vitals, and accessibility issues.

Data visualization and chart generator with SVG file output. 数据可视化、数据图表、图表生成、柱状图、bar chart、折线图、line chart、饼图、pie chart、ASCII图表、数据报表、趋势图、sparkline、仪表盘、dashboard、HTML图表、SVG图表、SVG文件输出、数据分析图、统计图表、表格生成、格式化表格、数据展示、可视化报告、数据看板、进度条、热力图、趋势分析、变化率。Generate bar charts, line charts, pie charts, tables, sparklines, dashboards, progress bars, trend analysis, and heatmaps as ASCII or HTML. Also generates SVG chart files (bar/pie/line) that open directly in browsers. Use when: (1) creating data visualizations/charts, (2) generating bar/line/pie charts, (3) formatting data into tables, (4) building HTML chart reports, (5) showing data trends or distributions, (6) any chart, dashboard, or data visualization task, (7) progress tracking, (8) trend analysis with change rates, (9) heatmap visualization, (10) generating SVG chart files for sharing or embedding. 适用场景：生成图表、数据可视化、做报表、展示数据趋势、对比数据、ASCII图表终端展示、HTML图表报告输出、SVG图表文件生成、进度条、热力图、趋势分析。

Control Home Assistant - smart plugs, lights, scenes, automations.

Provides comprehensive guidance for Electron framework including main process, renderer process, IPC communication, window management, and desktop app development. Use when the user asks about Electron, needs to create desktop applications, implement Electron features, or build cross-platform desktop apps.

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as 'Deploy my app', 'Deploy this to production', 'Create a preview deployment', 'Deploy and give me the link', or 'Push this live'. No authentication required - returns preview URL and claimable deployment link.

Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, and expand scope when doing so yields a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold core scope while cherry-picking expansions), HOLD SCOPE (maximum rigor), and SCOPE REDUCTION (strip to essentials).

Write/restructure the NSFC main text "(2) Research Content" and simultaneously arrange "Features and Innovations" and "Three-Year Annual Research Plan", outputting three extraTex files that can be directly applied to the LaTeX template. This is suitable for users who need to write/revise "Research Content, Research Objectives, Key Scientific Issues, Technical Routes, Innovations, Three-Year Plans/Milestones", etc.

Convert PDF files to and from Word, Excel, Image, and other formats

AI prompt generator for image and text. AI绘画提示词、AI画图、Midjourney提示词、MJ提示词、Stable Diffusion提示词、SD提示词、DALL-E提示词、AI绘图、AI生图、AI画画、文生图提示词、text-to-image prompt、写作提示词、ChatGPT提示词、Claude提示词、prompt engineering、提示词工程、提示词优化、负面提示词、negative prompt、画风提示词、风格提示词、风格词库、工作流、提示词升级。Generate image prompts for Midjourney/SD/DALL-E and writing prompts for ChatGPT/Claude. Use when: (1) generating AI image/art prompts, (2) creating Midjourney/Stable Diffusion/DALL-E prompts, (3) translating Chinese descriptions to English prompts, (4) enhancing or optimizing existing prompts, (5) batch generating prompt variations, (6) creating writing prompts, (7) browsing style-specific keyword libraries, (8) getting comprehensive negative prompt reference, (9) following complete image generation workflows, (10) upgrading simple descriptions to professional prompts, (11) any AI art or prompt engineering task. 适用场景：生成AI绘画提示词、Midjourney出图、SD出图、中文转英文提示词、优化提示词、批量生成提示词变体、风格词库查询、负面提示词参考、完整出图工作流、提示词升级优化。纯本地模板生成，不依赖外部API。

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify code", "clean up code", "refactor for clarity", "improve readability", or review recently modified code for elegance. Focuses on project-specific best practices.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

OpenClaw skill for Facebook Graph API workflows focused on Pages posting, comments, and Page management using direct HTTPS requests.

Interact with Jenkins CI/CD server via REST API. Use when you need to trigger builds, check build status, view console output, manage jobs, or monitor Jenkins nodes and queue. Supports deployment to different Jenkins instances via environment variables.