Extracts audio, background music, and voiceovers from local videos and social media links into MP3 or WAV formats.
This skill should be used when the user asks to "compress this video", "reduce file size", "make this video smaller", "optimize for web"…
Use when planning channel distribution and measuring video performance.
Generate AI videos using varg SDK React engine.
Optimize prompts for AI video generation platforms including Sora, Runway, Pika, and Kling
Remove backgrounds from videos — video background removal API for transparent videos, alpha-channel clips, and green-screen-free footage.
Translate and dub existing videos into multiple languages using HeyGen.
Complete browser automation with Playwright.
YC Office Hours — two modes. (gstack)
Use when planning a viral / organic-distribution campaign for a mobile app, B2C product, or creator program.
Virtual economy modeling for MMOs — currency systems, sink/faucet balance, reward schedules, inflation control, auction houses, and…
Implement computer vision features including text recognition (OCR), face detection, barcode scanning, image segmentation, object…
Visma Netvisor integration via Apideck's Accounting unified API — same methods work across every connector in Accounting, switch by…
Multi-dimensional visual scoring using pixel-diff and structural analysis for design-to-implementation comparison
Use this skill to audit or define a constrained visual system for a website, interface, landing page, portfolio, or design system.
HTML explainers, diagrams, architecture, timelines, source maps, slide decks, comparison tables, recaps, plan and diff reviews.
A visual & functional crawler operation utilizing Chrome DevTools Protocol (CDP) or Playwright/Puppeteer to audit prototype UI/UX and…
Automate Instacart tasks via Rube MCP (Composio).
Discovers and analyzes open-source contribution opportunities across the vLLM repository for community developers.
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching.
Fetches, categorizes, and generates structured reports on multimodal-related open issues from the vLLM repository.