Loading...
Loading...
Found 1,275 Skills
Skill for writing and updating scalar.config.json — Scalar Docs configuration reference for users and LLMs.
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep scan, 2/10 bar). Trend tracking across audit runs. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review". (gstack) Voice triggers (speech-to-text aliases): "see-so", "see so", "security review", "security check", "vulnerability scan", "run security".
Trigger when the user wants to create a new dashboard, set up monitoring for a service or infrastructure component, or import a pre-built dashboard template. Includes requests like "create a dashboard for PostgreSQL", "monitor my Redis cluster", "set up observability for my k8s cluster", "I need a dashboard for tracking LLM costs".
Make websites accessible for AI agents. Navigate, click, type, extract, wait — using Chrome with existing login sessions. No LLM API key needed.
Guides edge and tactical autonomous systems—perception-planning-control under latency and safety constraints; behavior trees/state machines vs learned policies; human-on-the-loop; geofencing, no-strike rules, mission abort; sim and field testing; ROS2/middleware patterns; sensor fusion; degraded modes; autonomy audit logging. Use for UAS/autonomous stacks, safety rules, HITL, sim-to-field validation, fail-safe—not LLM products (ai-engineer), LLM red team (ai-redteam), safeguard serving (ml-infrastructure-engineer-safeguards), governance only (ai-risk-governance), MCU firmware without autonomy (embedded-real-time-software-engineer), plant PLC/DCS (control-software-developer), HIL security bench (hardware-in-the-loop-security-tester).
Convert any document to Markdown with Microsoft's `markitdown` CLI — PDF, Word, Excel, PowerPoint, HTML, CSV, JSON, XML, ZIP, EPub, images (OCR/EXIF), audio (transcription), and YouTube URLs. Use whenever the user wants to extract text from a binary document, transcribe audio, OCR an image, scrape a YouTube transcript, or pre-process a file for an LLM context window — even when they just say "convert this pdf", "what's in this docx", "transcribe this mp3", or "get the text out of this".
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
Implements and debugs browser Prompt API integrations in JavaScript or TypeScript web apps. Use when adding LanguageModel availability checks, session creation, prompt or promptStreaming flows, structured output, download progress UX, or iframe permission-policy handling. Don't use for server-side LLM SDKs, REST AI APIs, or non-browser providers.
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map.