Transcribe audio files to text using a local Whisper ASR service. Use when: the user wants to transcribe an audio file to text, convert speech to text from an audio recording, extract text from voice recordings, or needs transcription of podcasts/interviews/voice notes. Only works for English language audio. The skill…
Deeply understand any video by extracting transcript evidence and visual evidence from a URL or local file. Use whenever the user pastes a video link or local video and wants analysis, summary, transcription, UI inspection, timestamped answers, comparison against local code/docs, or wants 'the part where they talk…
Conversation-driven video editing skill for agentic workflows. Use when the user wants an agent to take raw footage or multiple source clips and turn them into an edited video by reasoning from transcripts plus on-demand visual drill-downs: trimming filler words, selecting best takes, assembling multi-clip edits…
Crawl websites to extract text content from multiple pages and internal links. Use when the user wants to scrape a website, gather content across a section, archive docs text, understand a site more thoroughly by following internal links, or follow internal links beyond a single page. Prefer this general skill for…
Create net-new UI assets that match an existing web application's design system, including icons, hero art, feature graphics, mockups, and branded visuals. Use when the project needs additional visual assets that fit the current product style. Do not use this for replacing all existing site imagery at scale, or for…
Route web scraping, crawling, site-ingestion, URL discovery, structured extraction, and public-site capture tasks to the right local stack. Make sure to use this whenever the user wants to scrape a site, crawl docs, export markdown from many pages, map a website, capture a public website for later analysis, understand…
Fetch and analyze web content using a specialised extraction workflow that converts HTML to clean markdown, extracts main article content, handles images and links, and provides AI analysis. Use this when you need cleaner page extraction than a raw fetch, when comparing a small set of URLs, or when the user asks to…
Fetch YouTube video captions/transcripts and metadata. Use when you need to download video transcripts, extract captions from YouTube URLs, get video descriptions and metadata, or process YouTube video text content. Supports residential proxy for reliable caption and metadata fetching (credentials can be auto-loaded…
Search YouTube videos by query or within specific channels. Supports date filtering, sort ordering, and duration filters to exclude YouTube Shorts. Returns LLM-optimized JSON with video details.
★not rated 2 2mo agoA40 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: