自動化安裝 Kubernetes 叢集的 AI Agent Skill

autocli

当需要理解或扩展基础设施层（加载器、基类、路径、错误处理）等底层开发时使用。

legal-risk-visualization

Control and monitor Xiaomi Mijia smart home devices. Use this skill when the user wants to: 1) Switch device status (on/off, brightness, etc.) 2) List available home devices 3) Run automation scenes 4) Check environmental statistics.

Reusable Polymarket + OpenClaw trading operations skill for any workspace. Use when the user needs to set up, run, tune, monitor, and deploy an automated Polymarket trading project (paper/live), including env configuration, risk controls, reporting, and dashboard operations.

根据用户粘贴的录音转写文本，提炼企业内部培训总纲（模块→课时→要点→案例→练习→作业），并支持按 lesson 逐步扩写为细致培训文档。

content-parser

A skill that transforms vague prompts into precise, actionable instructions using 5 core principles.

>-

Transform one source asset into a coordinated pack for multiple channels

在新数据集接入前检查字段、单位、缺失率、异常值与可用性。；use for data, dataset, audit workflows；do not use for 伪造统计结果, 替代正式数据治理平台.

Organize the Downloads folder into a clean, searchable command center

分析退货原因并区分产品问题、预期错配、物流问题和描述问题。；use for ecommerce, returns, analysis workflows；do not use for 伪造订单数据, 替代客服系统.

整理下载目录或临时资料目录，先给分类方案、命名建议和移动预案，再决定是否执行。；use for files, organize, downloads workflows；do not use for 直接删除文件, 修改系统目录.

A proactive agent that anticipates needs and takes initiative. Monitors environment, suggests actions, and proposes tasks based on context. Perfect for agents that need to be proactive rather than reactive.

Use when users need a lightweight HotTrender crawler for four-region daily hotspot trends or custom keyword/vertical hotspot discovery. Prefer the bundled basic crawler runtime and existing provider scripts before writing code. This skill intentionally excludes DingTalk push, OSS publishing, ActionCard pages, lp-ads workspace, worker queues, databases, and LLM summaries.

Craw & Core (Lobster Dungeon) — The first game designed for AI Agents to play. You observe. AI explores. The Abyss tells stories.

Multi-platform video auto-publisher. Automatically upload videos to Douyin, WeChat Channels, Xiaohongshu, Bilibili, YouTube and more. Supports batch publishing, scheduled posting, auto-caption generation, and hashtag optimization.

Upload any data file (CSV, Excel, JSON, SQL export) and get a complete analysis report with insights, anomalies, and actionable recommendations — no code required.

opencli

Extract metadata and content from WeChat Official Account articles. Use when user needs to parse WeChat article URLs (mp.weixin.qq.com), extract article info (title, author, content, publish time, cover image), or convert WeChat articles to structured data. Supports various article types including posts, videos, images, voice messages, and reposts.

Youtube Highest Quality Downloader - Download highest quality silent video and pure audio from YouTube, then merge into video with sound

Simplified CLI tools for camoufox anti-detection browser automation. Provides fox-open, fox-scrape, fox-eval, fox-close, and fox-bilibili-stats commands for easy web scraping and data extraction.

Publish and download WeChat Public Platform content and Baijiahao articles via a local CLI.

3-in-1 China 12306 query — tickets, route stops, transfer plans. Zero login. Filter 高铁/动车/火车 by type, time, duration. Pure Python, text/json/csv output. 火车票/余票/经停站/中转换乘.

这是一个用于 CoPAW (Copilot Automation Workflow) 的标准 Skill，支持自动爬取银登网不良贷款转让公告及转让结果，并利用大模型（LLM）提取关键数据。

Access Bank of Japan (BOJ/日本銀行) statistical data — price indices (CGPI, SPPI), flow of funds, balance of payments, BIS statistics, interest rates, money supply, exchange rates. Japan central bank monetary policy data. No API key required.

Search and retrieve Japanese government statistics (人口, GDP, CPI, 貿易, 雇用) from e-Stat API — Japan's official open data portal with 3,000+ statistical tables. Population, economy, trade, employment data. Free API.

Ingest Taiwan civil court judgments (HTML or PDF) — exclusively covering Taiwan civil cases — into Qdrant with Ollama embeddings, preserving traceability, deduplication, and incremental updates.

douyin-download

Smart web content fetcher - articles and videos from WeChat, Feishu, Bilibili, Zhihu, Toutiao, YouTube, etc. Triggers: '抓取文章', '下载网页', '保存文章', 'fetch URL', '下载视频', '抓取飞书文档', '抓取微信文章', '把这个链接内容保存下来', '下载B站视频', 'download video', 'scrape article'.

Read and extract content from all Feishu (Lark) document types using the official Feishu Open API

>

This skill helps merchants learn and understand Weimob's features and capabilities (e.g., Weimob Shop, Wholesale Shop, Smart Retail, Smart Supermarket, Smart Mall, WeCom Assistant, and WeCom Mini Assistant). It should be triggered when a user asks about Weimob's functions, product capabilities, or operational workflows.

本技能用于将用户的查询请求转发到 DeepSeek 网页版，利用 DeepSeek 的联网搜索能力获取最新信息，同时减轻主模型的负担。

台股月營收抓取與分析。從公開資訊觀測站(MOPS)取得上市/上櫃公司當月營收，計算YoY/MoM年增率與月增率，輸出BEAT/MISS/NEUTRAL信號。用於：(1)月營收公布後自動分析 (2)觸發投資Pipeline決策 (3)更新ANALYSIS_INDEX監控條件

Import Personal Documents. Use when the user wants to import a local directory or explicit files into 材序 at the ingest stage, including “导入一批材料”“先把这个目录吃进去”“先建立可继续建库的解析上下文”. Prefer caixu-skill when the user asks for the full end-to-end mainline or is unsure which stage to run. This skill creates or loads a library, starts an ingest pipeline run, lets the agent choose per-file routes over low-level OCR and parser tools, persists ParsedFile records, and hands off library_id plus run_id to build-asset-library. Do not use it for asset extraction, lifecycle judgment, package building, or submission.

pixel-art-processing

Download videos from thousands of websites using yt-dlp.

When the user uploads 发票.zip and 火车票.zip, use the included data tables to calculate eligible business-trip subsidy records, split related vs remaining files, create output workbooks, package two result zips, and report progress at every key step.

与 Quicker 自动化工具集成，读取、搜索和执行 Quicker 动作列表。支持 CSV 和数据库双数据源，智能匹配用户需求并调用本地 QuickerStarter 执行。

Run the installed red-crawler CLI for Xiaohongshu contact discovery. Requires the red-crawler command and Playwright browser runtime; not instruction-only.

Systematically verify academic references to detect AI-hallucinated or fabricated citations. Queries Google Scholar, arXiv, CNKI, and other databases.

Use Chanjing video synthesis APIs to create digital human videos from text or audio, with optional background upload, task polling, and explicit download when the user asks to save the result locally.

AI-powered tour guide with backend API and offline fallback. Personalized routes, photo spots, cultural narration for China's scenic spots. Bilingual support. 中国景区智能导览助手，支持后端API增强与离线备份，个性化路线推荐、拍照机位、文化讲解，中英双语。

>-

验证码识别与解决 - 本地OCR识别 + 第三方API / CAPTCHA Recognition and Solving - Local OCR + Third-party APIs

>

浏览器自动化与网页测试专家。支持基于 MCP 工具（Puppeteer/Playwright）的实时交互，以及基于 Python 脚本的复杂自动化流实现。