Loading...
Loading...
Found 1,669 Skills
Read every docs/benchmarks/runs/*.json and surface drift in win rate, latency, escalation rate, and LLM-baseline cost over time
Guides AI ops leadership—LLM SRE, model/prompt releases, eval/incidents, cost/capacity, vendors, and cross-functional cadence. Use for AI platform ops, LLM SLAs, incidents, rollout governance, unit economics, red-team/eval gates, and team rituals—not memory (ai-memory-developer), context code (ai-context-engineer), security programs (cybersecurity), token roadmaps (ai-token-improvement-plan-engineer), solution architecture (applied-ai-architect-commercial-enterprise), skills portfolio (ai-skill-manager), or vertical AI product eng management (engineering-manager-vertical-ai-products). Prompt/eval team management and golden-set release policy: engineering-manager-agent-prompts-evals. Safeguard inference platform: ml-infrastructure-engineer-safeguards. Safeguard model research: ml-research-engineer-safeguards.
Guide for adding support for new LLM or VLM models in Megatron-Bridge. Covers bridge, provider, recipe, tests, docs, and examples.
LLM-first SEO analysis skill with 16 sub-skills, 10 specialist agents, and 89 evidence collection scripts for comprehensive SEO audits
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Build a custom browser-based annotation interface tailored to your data for reviewing LLM traces and collecting structured feedback. Use when you need to build an annotation tool, review traces, or collect human labels.
This skill should be used when the user asks to "audit a website for AI visibility", "scan a domain", "check AI readiness", "evaluate content quality", "run a Morphiq Scan", "check if a site is optimized for LLMs", or mentions scanning a website for LLM citation readiness. Performs a full AI visibility audit across 5 categories (agentic readiness, content quality, chunking & retrieval, query fanout, policy files) and scores the domain on a 100-point rubric.
End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM serving performance by searching each framework's best deployment command, benchmarking them fairly, profiling SGLang if it is slower, identifying kernel/overlap/fusion bottlenecks, patching SGLang code, and revalidating with real model runs.
Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants to "create video training data", "generate video QA datasets", "build CoT reasoning traces from videos", "auto-label videos", or run the video_reasoning_annotation pipeline. Triggers include "video annotation", "video CoT", "video QA", "chain-of-thought", "video captioning pipeline", "video distillation".
Configure Celigo AI agent and guardrail imports -- LLM-powered steps that classify, extract, validate, or generate data within flows. Use when creating agent imports (OpenAI, Gemini), guardrails (PII, moderation), or configuring prompts, structured output, or BYOK connections.
OpenGame is an open-source agentic framework for end-to-end web game creation from a single text prompt, using LLMs, Game Skill (Template + Debug), and headless browser evaluation.
Use when writing, reviewing, or committing code to enforce Karpathy's 4 coding principles — surface assumptions before coding, keep it simple, make surgical changes, define verifiable goals. Triggers on "review my diff", "check complexity", "am I overcomplicating this", "karpathy check", "before I commit", or any code quality concern where the LLM might be overcoding.