Skill UI

A comprehensive offensive checklist for assessing the security and robustness of AI and Large Language Model (LLM) applications. It covers advanced adversarial techniques such as prompt injection, jailbreaking, model extraction, data poisoning, and analyzing system vulnerabilities across components. Essential for red-teaming and security assessment.

Use the Parallel CLI for web search, URL/PDF extraction, deep research, data enrichment, entity discovery, and recurring web monitoring. Best when requests need current web evidence, academic sources, or change tracking.

A comprehensive workflow for scraping and extracting structured data from Google search results using the SerpApi. It captures all key components, including organic listings, knowledge graphs, answer boxes, People Also Ask (PAA), local pack results, and related searches. Ideal for SEO monitoring, market research, competitive analysis, or building search-powered features that require deep, structured data insights.

This workflow utilizes the SerpApi to perform advanced, multi-engine searches across platforms including YouTube, Bing, Google News, Google Shopping, and Google Maps. It is essential for data scraping, SEO research, and building comprehensive search features that require aggregating results from diverse sources beyond standard Google search. Use it to collect videos metadata, product pricing, local business details, and news articles efficiently.

This guide details how to use Skyvern's AI-powered Command Line Interface (CLI) for advanced browser automation. Users can perform tasks such as quick data validation, structured data extraction, form filling, secure login, and building complex, multi-step, reusable workflows across various websites. It offers solutions for scenarios where deterministic selectors fail.

TweetClaw provides comprehensive automation capabilities for X/Twitter using the Xquik REST API. It allows users to perform full read and write operations—including posting, replying, liking, following, and sending DMs. Key features include advanced tweet searching, bulk data scraping (23 tools), account monitoring, running structured giveaways, and composing algorithm-optimized content. Ideal for social media managers, digital marketers, and data analysts needing deep platform insights.

This router entry point is designed for comprehensive testing of file access, download endpoints, and file upload workflows. Use this guide when validating file paths, detecting Local File Inclusion (LFI), or analyzing vulnerabilities in preview, storage, or extraction processes. It helps categorize whether the security issue relates to path traversal or insecure data processing chains.

A comprehensive playbook detailing NoSQL injection techniques, moving beyond traditional SQLi. Covers deep vulnerabilities in MongoDB, including operator injection, login bypass, blind data extraction using regex, and $where execution. Also includes attacks specific to Redis, CouchDB, and general API parameter pollution.

A comprehensive, advanced playbook for conducting deep network traffic analysis and PCAP forensics. Covers essential skills like PCAP repair, advanced Wireshark filtering (HTTP, DNS, TLS), data extraction (file carving, credential harvesting), and detecting covert channels. It guides users through sophisticated techniques, including TLS decryption workflows and DNS tunneling identification.

This skill enables developers to integrate X (Twitter) data extraction into applications and AI workflows. It supports SDKs, REST APIs, Apify Actors, and MCP tools for searching tweets, exporting followers, and automating account actions with secure webhooks.

This comprehensive guide covers essential operations for handling PDF documents, including text, table, and metadata extraction using libraries like pdfplumber. It details document creation with reportlab, merging/splitting with pypdf/qpdf, and advanced OCR for scanned PDFs. Ideal for automating complex document workflows and structured data ingestion.

This skill extracts full transcripts and rich metadata from a single YouTube video URL. It uses yt-dlp to download subtitles, cleans VTT timing markers, and pulls video details (title, channel, date). The output is a structured, queryable Markdown file, ideal for populating a personal knowledge vault and enabling downstream knowledge graph extraction or content repurposing.