pixel-art-processing
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →pixel-art-processing
>
Recommend optimal GCP Committed Use Discount portfolio (spend-based vs resource-based) with risk analysis
Analyze AWS Cost & Usage Reports to identify top cost drivers, waste, and anomalies across all linked accounts
Design an interruption-resilient GCP Spot VM strategy for eligible workloads with 60-91% savings
Use when bulk-managing Terraform modules at scale — upgrading providers across AWS, GCP, Azure, or DigitalOcean repositories, standardizing GitHub Actions workflows, automating semantic releases, running security scans, or performing end-to-end maintenance cycles across 10–200+ module repositories
国内动漫每周更新日历。用于查询动漫更新时间、本周新番列表、追番日历。当用户询问动漫更新时间表、本周更新、追番日历、新番列表时触发此技能。
国内金价查询工具。用于查询黄金实时价格、银行金条价格、金店零售价、国际金价和黄金未来趋势分析。当用户询问金价、黄金价格、今日金价、金店价格、银行金条、国际金价、伦敦金、黄金走势或未来趋势时触发此技能。
Orchestrate real ELPA-style ensemble forecasting workflows by triggering external sub-model training jobs (for example PyTorch/Prophet/TiDE/transformers), then computing ELPA online/offline weights from validation errors. Use when you need production-oriented ensemble training instead of lightweight simulation adapters.
自动遍历下载文件夹或桌面,利用视觉模型“看”文件内容并重命名,最后归档到指定分类目录。
抖音视频下载工具 - 通过第三方解析服务实现无水印视频下载
Use when Cartograph CLI or MCP is available and you need repository orientation, task-scoped context, or doc inputs with minimal token cost.
Download Instagram Reels, transcribe audio, and extract captions. Share a reel URL and get back a full transcript with the original description.
交互式数据清洗 CLI,支持自动类型推断、缺失值处理、重复检测
Web scraping and content extraction using Firecrawl API. Use when users need to crawl websites, extract structured data, convert web pages to markdown, scrape multiple URLs, or build knowledge bases from web content. Supports single page extraction, site-wide crawling, batch processing, and structured data extraction with CSS selectors.
Smooth CLI is a browser for AI agents to interact with websites, authenticate, scrape data, and perform complex web-based tasks using natural language.
AI新闻一键发布技能。从36氪/虎嗅获取AI新闻,改写成爆款文章,发布到微信公众号。触发词:发布AI新闻、公众号发文章、科技新闻发布、爆款文章。
>
Clash/Mihomo 代理管理。安装配置、查看状态、切换模式/节点、测速、外网失败时自动代理。
Free daily growth assistant for online businesses. Track basic revenue metrics, get daily action priorities, and monitor progress toward goals.
Download videos from thousands of websites using yt-dlp.
Skill for interacting with the Lean-Claw Arena to prove math theorems using Lean 4.
Battle in Grid Clash - join 8-agent grid battles. Fetch equipment data to choose the best weapon, armor, and tier. Use when user wants to participate in Grid Clash battles.
>
> Stop burning context. Manage your agent's token budget intelligently.
Publish content across TikTok, Instagram, YouTube, Facebook, LinkedIn, Vimeo, Vimeo OTT, and Mux. Manage team workflows, collaborate with your team, and track verified publish history.
Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.
Deploy, manage, and monitor static websites via the EzyHost API. Upload files, build with AI, track analytics, manage custom domains, QR codes, email capture, and team collaboration.
Real mailing address for your AI agent. Receive, scan, and forward postal mail — or send letters and documents. CMRA postal mail infrastructure your agent manages via API.
Knowledge Base Collector - save YouTube, URLs, text to Obsidian with AI summarization. Auto-transcribes videos, fetches pages, supports weekly/monthly digest emails and nightly research.
Tell users what terminal games exist in GameClaw and how to download the released CLI binaries from GitHub. Use this when users ask what games are available, want a GameClaw game, need Linux/macOS download links, or want quick run instructions for a released game.
Document OCR and parsing — converts PDF/images to Markdown on remote L4 GPU via Modal. Trigger when user says: OCR, PDF to markdown, parse PDF, extract text from PDF, 文档识别, PDF转Markdown, 扫描件识别. Takes local PDF/image files and returns Markdown with layout, tables, formulas, and OCR preserved.
Speech enhancement / vocal denoising on remote (FREE) L4 GPU. Trigger when user says: denoise, remove noise, clean up audio, 去噪, 降噪, enhance audio. Takes local audio/video files and returns noise-reduced speech audio.
Vocal isolation / background music removal on remote (FREE) L4 GPU. Trigger when user says: isolate vocals, remove background music, extract voice, 提取人声, 去除背景音乐, vocal separation. Takes local audio/video files and returns isolated vocals.
3x Faster than Whisper, Speech-to-text transcription with sentence-level timestamps on remote (FREE) L4 GPU. Trigger when user says: transcribe, speech to text, STT, speech recognition, 转录, 语音转文字. Takes local audio/video files and returns .txt (plain text) and .srt (subtitles).
MUST use after brainstorming and before executing. Creates detailed implementation plans with checkpoints, verification criteria, and execution options.
Use when managing a self-hosted Dify instance, checking feature feasibility, or orchestrating apps, prompts, datasets, and knowledge-base operations via the dify-manager MCP server.
Process, filter, and transform JSON data using jq - the lightweight and flexible command-line JSON processor.
"Convert CSV data to JSON array of objects"
Scan SBOM for known CVE vulnerabilities
Data processing pipelines for OpenClaw. Deploy skills from the Expanso marketplace to transform, analyze, and process data locally.
AI-powered email triage with calendar sync and response drafting
Flatten nested JSON objects
"Pretty print JSON with indentation"
"Validate JSON syntax and structure"
"Extract keywords and key phrases from text for SEO, tagging, and indexing"
Detect the language of text using AI
"Sanitize log entries by removing passwords, tokens, and sensitive patterns"
"Redact PII from text, replacing sensitive data with placeholders"
Detect hardcoded secrets (API keys, tokens, passwords) in text or code