Loading...
Loading...
Found 1,203 Skills
AI HOT (aihot.virxact.com) Chinese AI News Query Skill. Trigger this Skill when users ask any Chinese AI information queries such as "What's happening in the AI circle today", "AI Daily", "AI HOT", "AI News", "AI Hot Topics", "Latest AI Updates", "What have OpenAI/Anthropic/Google released recently", "AI hot today", "AI news today", "Check AI industry trends", "What large models are released today", "AI circle updates from yesterday", "Check selected items", "AI HOT Selected", "AI papers from the past week", "AI model releases", "AI product launches", "AI industry dynamics", "AI tips and insights". Even if users only say "AI circle", "AI news", "AI Daily", or just ask "What happened today" with context related to AI / large models / LLM / startup fields, this Skill should be triggered. The Skill directly pulls data via curl from public REST APIs and organizes it into Chinese markdown briefings, with no need for users to configure any API Key or MCP server. **Do NOT undertrigger**——If users ask for AI news and you don't invoke this Skill, you are treating outdated training data as today's news, which is harmful to users.
Async media + document derivations via `platform.media.transforms` and the declarative `transforms` block in `maravilla.config.ts`. Media: transcode video, thumbnail extraction, image resize/variants, OCR. Documents (.docx/.odt/.pptx/.xlsx/...): convert to PDF, render page thumbnails, generic format conversion, Markdown extraction (RAG-ready), single-file HTML with inlined images, image-replacement templating ({{TAG}} swap + named-object swap), QR-code injection. Use when ingesting user uploads that need normalised renditions, generating contracts/invoices from templates, or extracting structured content for LLMs. Critical: derived keys are content-addressed — `keyFor(srcKey, spec)` is known up front, before the worker starts, so clients can render placeholder UI without round-trips. Declarative config is the default; imperative `transforms.*` calls are for one-offs.
Guides product infrastructure security—securing the runtime, data plane, and control plane that ships with the product: multi-tenant isolation, service-to-service auth, customer data boundaries, secure defaults in APIs and workers, abuse-resistant rate limits, product-scoped secrets and encryption, and security design reviews for product infra changes. Use when threat-modeling product features, designing tenant isolation, hardening service mesh or internal APIs, reviewing product IaC/modules for data leaks, defining secure baselines for microservices the product team owns, or partnering on incidents affecting customer workloads—not for corporate IdP/SIEM (information-security-engineer), CI pipeline gates only (devsecops), SOC operations (defensive-security-analyst), authorized pentest execution (offensive-security-analyst), general IDP golden paths (platform-engineer), company-wide GRC (cybersecurity), or applied AI solution architecture for LLM features (applied-ai-architect-commercial-enterprise).
Run AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation hooks. Use when the user mentions TAO AutoML, hyperparameter optimization, HPO, automl, automl_settings, AutoMLRunner, tao_automl, bayesian search, hyperband, ASHA, LLM-guided search, autoresearch, or wants to tune training hyperparameters for any TAO network. Platform-agnostic — runs on any SDK (Lepton, Brev, SLURM, Kubernetes, Docker).
Process external code review feedback with technical rigor. Use when receiving feedback from another LLM, human reviewer, or CI tool. Verifies claims before implementing, tracks disposition.
Ollama local LLM deployment and management. Use for running LLMs locally.
Web scraping and search CLI returning clean Markdown from any URL (handles JS-rendered pages, SPAs). Use when user requests: (1) "search the web for X", (2) "scrape/fetch URL content", (3) "get content from website", (4) "find recent articles about X", (5) research tasks needing current web data, (6) extract structured data from pages. Outputs LLM-friendly Markdown, handles authentication via firecrawl login, supports parallel scraping for bulk operations. Automatically writes to .firecrawl/ directory. Triggers: web scraping, search web, fetch URL, extract content, Firecrawl, scrape website, get page content, web research, site map, crawl site.
Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
Integrate TheSys C1 Generative UI API to stream interactive React components (forms, charts, tables) from LLM responses. Supports Vite+React, Next.js, and Cloudflare Workers with OpenAI, Anthropic Claude, and Workers AI. Use when building conversational UIs, AI assistants with rich interactions, or troubleshooting empty responses, theme application failures, streaming issues, or tool calling errors.
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
Guidelines for deep learning development with PyTorch, Transformers, Diffusers, and Gradio for LLM and diffusion model work.
Supanova Landing Page Design Engine. Generates premium, conversion-optimized landing pages using pure HTML + Tailwind CSS (CDN). Overrides default LLM biases toward generic templates. Enforces metric-based design rules, Korean typography standards, and hardware-accelerated motion for standalone HTML output.