🎯
Skills
Loading...
Showing 30 of 137305 results
Write, review, or improve Swift APIs using Swift API Design Guidelines for naming, argument labels, documentation comments, terminology, and general conventions. Use when designing new APIs, refactoring existing interfaces, or reviewing API clarity and fluency.
From-scratch PyTorch implementation of Google TurboQuant (ICLR 2026) for LLM KV-cache compression: Stage 1 random orthogonal rotation + Lloyd-Max scalar quantization, Stage 2 QJL 1-bit sign residual correction for unbiased inner products — achieving 5x compression at 3-bit (58MB vs 289MB FP16) with 99.5% attention fidelity on Qwen2.5-3B.
A scientific research skill for querying UniProt to retrieve comprehensive protein sequence data, functional annotations, and cross-references to other databases.
A Claude Code skill for selecting and running models locally with llama.cpp and GGUF format on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUF files, quantization selection, running local servers, conversion workflows, and OpenAI-compatible local serving.
Provides comprehensive regulatory compliance guidance, risk assessment, and strategic advisory services for navigating complex industry-specific regulatory landscapes and ensuring organizational adherence.
A prototyping skill from the Designer Skills Collection covering wireframe specifications within the prototyping-testing plugin, which helps validate designs through prototyping strategies, usability testing, heuristic evaluation, and A/B experiments.
A collection of 255+ universal agentic skills for AI coding assistants including Claude Code, Gemini CLI, Codex CLI, Antigravity IDE, GitHub Copilot, and Cursor.
Designs and architects software solutions using best practices from Agent Playbook, a collection of practical guides and skills for AI Agents.
A UI component skill from a 160+ skill marketing and SEO markdown library for AI agents, providing guidance for implementing marketing components. The library covers navigation, hero sections, CTAs, testimonials, and various layout patterns integrated with project context.
PyTorch-native distributed training skill for LLMs and VLMs using NVIDIA NeMo AutoModel, with Hugging Face model support, training recipes, multi-GPU launchers, and validation workflows.
An NVIDIA-verified skill that guides AI agents through developing training recipes with NeMo AutoModel, enabling PyTorch-native distributed training configurations for LLMs and VLMs with customizable launchers and validation workflows.
Generates a multi-page marketing site that actually teaches people what a web app does — real screenshots, animated GIF walkthroughs, per-feature deep-dives, and workflow demos — by browsing the running app and capturing sequences. Has quick, standard, and thorough depth levels tuned for complex or agentic apps.
A collection of production-ready Claude Code skills covering Tailwind CSS v4, shadcn/ui integration, and modern web development patterns.
Skill for routing tasks to appropriate skills within Agent Playbook, a collection of practical guides, prompts, and skills for AI agents like Claude Code, Codex, and Gemini CLI.
A marketing strategy skill from a 160+ skill marketing and SEO markdown library for AI agents, providing workflows for strategy and planning. The strategies category covers launch, brand, commercial, GTM, PMF, pricing, and domain approaches integrated with project context.
Agent skills for Laravel + Inertia.js + React integration with 30+ rules covering page components, forms, navigation, shared data, layouts, and file uploads.
Claude Code skill that wraps the Codex CLI as a plugin, exposing /codex:review, /codex:adversarial-review, and /codex:rescue for delegating read-only reviews or background bug-investigation/fix tasks to OpenAI Codex — with /codex:status, /codex:result, and /codex:cancel for managing jobs.
Covers wiring external agent frameworks (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, and others) into CopilotKit applications via the AG-UI streaming protocol.
Guides AI agents through building synthetic datasets using NVIDIA's Data Designer library. Supports interactive and autopilot modes with declarative pipeline generation, category/Jinja2 samplers, and seed dataset integration.
A collection of 255+ universal agentic skills for AI coding assistants including Claude Code, Gemini CLI, Codex CLI, Antigravity IDE, GitHub Copilot, and Cursor.
NVIDIA NeMo AutoModel skill for configuring launcher settings in PyTorch-native distributed training workflows for LLMs and VLMs, with Hugging Face support, recipes, and validation workflows.
An auto-generated security skill based on the OpenClaw Security Watchdog project, providing security monitoring and threat detection capabilities for AI agent workflows.
Code-review-graph uses Tree-sitter to build a structural code map and tracks changes incrementally for precise AI context, achieving 8.2x average token reduction.
Produces public list-price Flex Credit estimates for Salesforce Agentforce and Data Cloud — modeling prompt tiers (starter/basic/standard/advanced at 2-16 FC), action types (standard/voice/sandbox at 16-30 FC), Data Cloud monthly tiering (1.0x to 0.2x multipliers), and Private Connect uplift at $0.004 per FC.
A TanStack DB skill for the client-first reactive database with live queries. Part of the tanstack-skills collection covering the complete TanStack ecosystem.
Extracts design systems from UI images, generating consistent, implementation-ready design documentation and UI prompts for product development.
An NVIDIA-verified skill that guides AI agents through starting router modes for NVIDIA Dynamo deployment on Kubernetes, part of the Dynamo skill set covering recipe deployment, interconnect validation, and day-2 troubleshooting.
A skill that automatically manages OpenRouter's 30+ free AI models for unlimited free AI usage in OpenClaw agents. Auto-ranks models by context length, capabilities, and provider trust, with smart fallbacks and a background watcher daemon for automatic failover on rate limits.