18 skills total · 18 unscanned
Skills by NousResearch
Create polished technical architecture diagrams rendered as standalone HTML with embedded SVG graphics and a dark aesthetic. The skill generates diagrams for system architecture,…
This skill analyzes articles and generates coordinated illustrations by combining three dimensions: type (infographic, scene, flowchart, comparison, framework, timeline), style…
baoyu-comic transforms content into illustrated knowledge comics with customizable art styles (ligne-claire, manga, realistic, ink-brush, chalk, minimalist) and atmospheric tones.…
baoyu-infographic lets you generate custom infographics by pairing any of 21 layouts—from timelines and comparisons to funnels and dashboards—with any of 21 visual styles, from…
This skill deploys agent-written code to a live workers.dev URL without requiring a Cloudflare account. It uses wrangler's temporary deployment mode to provision a throwaway…
Concept Diagrams produces production-quality SVG visuals with a unified flat, minimal design system—ideal for physics setups, anatomy, floor plans, and process flows. Output…
design-md helps you create and maintain formal design token specifications using Google's open DESIGN.md format. Write machine-readable tokens in YAML paired with human-readable…
Excalidraw lets you build diagrams by writing standard element JSON and saving as `.excalidraw` files that open directly in excalidraw.com. Generate architecture diagrams,…
Google Workspace skill brings Gmail, Calendar, Drive, Sheets, and Docs into your agent workflows using OAuth2 and a Python-backed CLI. It supports both the bundled client and the…
llm-wiki lets you construct and maintain a compounding knowledge base as organized markdown files, with the agent handling summarization, cross-referencing, and consistency checks…
Pinggy Tunnel creates instant public URLs for local services using SSH reverse tunnels, with no daemon installation needed. Free tier offers 60-minute tunnels with random…
PyTorch Lightning transforms raw PyTorch code into clean, organized training workflows by handling device management, distributed strategies (DDP, FSDP, DeepSpeed), and logging…
scrapling enables automated data extraction from sites defended by Cloudflare and similar anti-scraping systems. It uses sophisticated evasion methods to bypass protection layers…
vLLM accelerates LLM inference for production deployments using PagedAttention and continuous batching to achieve significantly higher throughput than standard approaches. It…
This skill enforces a disciplined debugging process: establish a tight feedback loop that reproduces the exact symptom, gather evidence across system boundaries, trace data flow…
This skill teaches post-training techniques for aligning language models to human preferences. It covers supervised fine-tuning, direct preference optimization (DPO), and online…
Whisper is OpenAI's multilingual speech recognition model for converting audio and video into text across 99 languages. It handles noisy recordings, supports translation to…
YouTube Content fetches transcripts from any YouTube video and reformats them into multiple output types—summaries, social threads, blog articles, timestamped chapters, and…