AI-AGENT-Skills

商品价格全网对比技能，获取商品在淘宝(Taobao)、天猫(TMall)、京东(JD.com)、拼多多(PinDuoDuo)、抖音(Douyin)、快手(KaiShou)的最优价格、优惠券，当用户想购物或者获取优惠信息时使用。Get the best price, coupons for goods on Chinese e-commerce platforms, compare product prices, and use when users want to shop or get discount information.

本地敏感数据脱敏与可逆还原工具 v1.3。当用户提到任何与"脱敏"、"隐私保护"、"敏感数据处理"、"个人信息保护"相关的内容时，必须激活本技能。 支持 PDF 图像级遮盖脱敏、OCR 脱敏、Word/Markdown/Excel 精准替换脱敏。 自动检测 17 种敏感数据类型（姓名、手机号、身份证、银行卡、邮箱、密码、API Key、地址、IP、护照、公司名等）。 多格式全管道输出：OCR脱敏文本 + 脱敏版PDF + 脱敏版DOCX + 脱敏版MD + 汇总映射表 + 反脱敏指南。 触发关键词：脱敏、隐私、敏感数据、个人信息、加隐私、redact、redaction、mask、privacy、personal data、PII、个人信息保护、数据脱敏、隐私处理、隐去、掩盖、打码、保护隐私、去隐私、遮盖、擦除、替换敏感信息。 支持文件格式：.pdf, .docx, .xlsx, .xls, .md, .markdown, .jpg, .jpeg, .png 处理流程：OCR识别 → 关键词脱敏 → PDF遮盖 → 格式转换脱敏 → 输出多格式结果。

Browser automation for AI agents. Use when the user needs to interact with websites — navigating, filling forms, clicking buttons, extracting data, taking screenshots, or automating any browser task. PinchTab (primary) for fresh automation, Chrome Relay (fallback) for the user's existing browser tabs.

Interact with Discord: send messages, photos, files to any channel. Manage Discord bot integration with Alma.

Find, organize, and manage files on the user's computer. Search by name, type, size, or date. Move, rename, compress, and clean up files.

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.

Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).

Generate and edit images using AI. Use when users ask to: create/draw/generate images, edit/modify photos, change backgrounds, add elements to images, create avatars, make logos, etc. Covers requests like 'draw a cat', 'change the background to blue', 'generate a logo'. NOT for selfies — use the selfie skill for 'send a selfie', 'send me a selfie', 'take a selfie'.

Search and manage Alma's memory and conversation history. Use when the user asks about past conversations, personal facts, preferences, or anything that requires recalling information ("do you know my...", "we talked about before...", "do you remember...", "help me find what we said about..."). Also used to store new memories and search through archived chat threads.

通过妙搭开发插件来创建简单网页，例如信息可视化展示（图表、看板、简报、报表等）、PPT/演示文稿、简单工具或应用原型。用户提到"妙搭"或"vibe coding"时也适用。注意：CRM/ERP/OA等管理系统（但用户明确说做"原型/demo/展示页"时仍适用本skill），AI对话/智能体/AI助手（核心功能是对话交互的）、定时任务/自动化/推送、AI智能能力、知识库等需求不适用本skill；纯创作类需求（写文章/脚本/文案/生成图片/视频等不是做一个应用的）、写个脚本（Python 等）及纯数据分析（用户只要分析结论、未要求做报告/看板/可视化）不要包装成应用。

创建数据库、建表、执行 SQL、查询数据、查看表结构。当用户需要数据库、数据表、数据持久化、PostgreSQL 操作时使用。通过 miaoda-data-cli db 子命令（db init / db sql / db schema）完成数据库初始化、DDL/DML/SELECT 执行和表结构查看。

Use when user needs to parse, extract, or read content from documents (PDF, Word, Excel, PPT, etc.) Converts documents to Markdown via IDP (Intelligent Document Parsing). 触发词：文档解析, 解析文档, 解析 PDF, 解析 Word, 解析 Excel, 读取文档, 提取文档内容, doc parse, IDP, 智能文档解析, parse document, 文档转 Markdown, 读取 PDF, 读取 PPT, 提取表格, 文档识别

Use when user needs to understand, analyze, or describe image content. Supports screenshots, photos, diagrams — provide local file path as input. No browser needed. Do NOT use Read tool to read images — use this skill instead. 当用户需要看图、理解图片内容、分析截图、识别图中信息时使用此技能。触发词：图片理解, 图片分析, 图片描述, 识别图片, 看图, 图片识别, image understanding, describe image, analyze image, 图片内容, 看看这张图, 这张图是什么, 图中有什么, 看不了图, 无法看图

OpenClaw agent runtime guide: sandbox environment, security config, available skills, tool limitations, and common user request handling. 运行环境说明、沙箱安全配置、可用技能、工具限制、常见问题处理。触发词：环境限制, 没有权限, sudo, 无法安装, 安全配置, dangerouslyDisable, no-sandbox, Browser Relay, Browser Replay, 内置技能, 可用工具

Use when user wants to search, find, install, or manage skills from Volcengine Skillhub (FindSkill), or asks whether a specific capability exists as a marketplace skill (如'有没有XX技能'/'有没有什么技能可以做XX'). Provides CLI commands for skill discovery and installation via npx skills. 触发词：技能市场, 技能搜索, 搜索技能, 安装技能, 查找技能, find skill, skill hub, skillhub, findskill, skills add, skills find, 技能安装, 技能下载, 技能广场, 火山技能市场, 有没有XX技能

Use when user needs to convert audio or voice recordings to text. Provides necessary command usage instructions for converting audio to text. Supports multiple languages. 触发词：语音转文字, 音频转文字, 语音识别, speech to text, STT, 转录, 听写, 会议记录转文字, 录音转文字, transcribe, 音频识别, voice to text, 语音转换

Use when user needs to generate images from text descriptions. Provides necessary command usage instructions for generating images from text. Supports various aspect ratios and AI watermark. 触发词：生成图片, 画图, 图片生成, text to image, 文字生成图片, AI 画图, 生成配图, 生成封面, 生成插图, generate image, 画一张, 做一张图

Use when user needs to crawl or fetch a specific URL to extract its content. Provides necessary command usage instructions for fetching known URLs. 触发词：网页抓取, 抓取网页, 提取网页内容, web crawl, 爬取, fetch url, 抓取 URL, 读取网页

ALWAYS use this skill FIRST when you need to find, look up, or verify ANY information from the internet — do NOT guess URLs and fetch them directly. Provides necessary command usage instructions for keyword-based web search with structured results. 触发词：搜索, 网页搜索, 搜一下, 查一下, 查询, 了解, 找一下, 帮我看看, web search, look up, find out, search, 查资料, 搜索引擎, 最新信息, 最近动态

Generate original songs with lyrics and vocals. Use when users ask to sing, create a song, make music, compose, or generate audio. Supports style prompts, custom lyrics, duration control, and instrumental mode.

Listen to and appreciate music files. Analyze audio for genre, mood, tempo, and lyrics. Use when users share audio/music files, ask about songs, or want music analysis.

Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.

Edit Jupyter notebook (.ipynb) cells — insert, replace, or delete cells. Use when working with notebooks.

Switch into structured planning mode before outlining multi-step solutions, and exit when done.

React to a message with an emoji. Works on Telegram, Discord, and Feishu.

Create, manage, and delete scheduled tasks (cron jobs) and configure heartbeat. Use when users ask for reminders, recurring tasks, daily summaries, periodic checks, or anything time-based. Also manages HEARTBEAT.md for periodic awareness checks.

Take screenshots of the screen using macOS screencapture. Use when users ask to see the screen, debug UI, or capture what's displayed. Resize before returning to avoid blowing up model context.

Read and update Alma's own settings via the `alma` CLI. MUST USE when users ask to change voice, TTS, models, or any configuration. Run `alma voices` to list voices, `alma config list` to see all settings. ALWAYS use this skill instead of guessing.

Daily self-reflection and personal growth. Triggered by heartbeat at end of day. Review the day's experiences, extract lessons, update personality, and write a diary entry.

Take selfies with consistent face/appearance. Use when users ask for selfies, self-portraits, or say things like 'send a selfie', 'take a selfie', 'snap one'. NOT for general image generation or editing — use image-gen for those.

Send files, photos, audio, or videos to the current conversation (channel chat or GUI thread). MUST use whenever you need to deliver any file to the user. Covers: sending images, selfies, generated art, documents, music, videos, voice messages, screenshots, or ANY file the user asks to see. Triggers: 'send it to me', 'send it over', 'let me see', 'send me', 'show me', 'send photo', 'send file', sharing any file path. NEVER paste raw file paths in text — ALWAYS use this skill to send files.

Search and analyze your own session logs (older/parent conversations) using jq.

Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".

Search, install, and manage Alma skills from the skills.sh ecosystem. Use when the user needs a capability Alma doesn't have yet, or when you encounter a task you can't do with current skills.

Search and install new skills to extend your capabilities. Use when you encounter a task beyond your current skills.

Get system information — OS version, disk usage, memory, running processes, network status. Use when users ask about their computer status or system health.

全网电商商品检索与比价工具（China E-commerce Price Comparison）。 支持淘宝/天猫、京东、拼多多、抖音、快手、1688 等主流电商平台。 根据商品名称跨平台搜索、智能过滤、生成比价表格、推荐优选商品并获取购买链接。 China e-commerce product search and price comparison tool. Search and compare prices across Taobao, Tmall, JD.com (Jingdong), Pinduoduo (PDD), Douyin Shop, Kuaishou Shop, 1688 (Alibaba wholesale), Suning, Vipshop. Find the cheapest price, best deals, discounts, coupons, and get purchase links. Supports cross-platform product search, smart filtering, recommendation ranking, and price table generation. Use when user asks to: compare prices across platforms, find the lowest price, search products on Taobao/JD/Pinduoduo, find deals or coupons, check where to buy cheap, get purchase links, do shopping research, or find the best value product.

Global multi-step task tracking. Create, update, and monitor long-running tasks across threads. Tasks persist across restarts and are visible in all conversations.

Interact with Telegram Bot API: send messages/photos/files/videos/audio/stickers/polls to any chat/group/channel, manage groups (pin/unpin/ban/kick/promote/restrict/set title/description/photo), forward/copy/delete/edit messages, react to messages, create invite links, manage forum topics, inline keyboards, and more. Use for ANY Telegram operation.

Manage chat threads — create, list, switch, delete, and search conversations. Use when users want to organize their chats.