Loading...
Loading...
Found 1,066 Skills
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or audit such a base, or initialize a new one. Trigger on phrases like "add this to my wiki", "ingest this paper", "compile this into the knowledge base", "what does my wiki say about X", "lint the wiki", "build a knowledge base from these documents", "research notes", "second brain", "personal knowledge base", or any reference to LLM Wiki / OmegaWiki. Trigger even when the user does not say "wiki" — if they are accumulating sources over time and want them organized, this applies. The skill scales — sharded indexes, atomic pages, YAML frontmatter, and a bundled search script keep the wiki from becoming a context bottleneck at hundreds or thousands of pages.
Unified LLM torch-profiler triage skill for `sglang`, `vllm`, and `TensorRT-LLM`. Use it to inspect an existing `trace.json(.gz)` or profile directory, or to drive live profiling against a running server and return one three-table report with kernel, overlap-opportunity, and fuse-pattern tables.
Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, or another serving framework. Use when a user wants to find the best deployment command for one model across multiple serving frameworks under the same workload, GPU budget, and latency SLA.
· Turn notes into structured LLM prompts or improve existing prompts. Triggers: 'write a prompt', 'system prompt', 'prompt template', 'prompt engineering', 'rewrite this prompt'. Not for skills or routines.
Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.
Expert skill for using TileKernels, a library of optimized GPU kernels for LLM operations (MoE routing, quantization, transpose, engram gating, Manifold HyperConnection) built with TileLang.
Framework for collective skill evolution in multi-user LLM agent ecosystems — automatically distills session experience into reusable SKILL.md files and shares them across agent clusters.
System prompt toolkit that removes AI slop and makes any LLM respond like a normal person — concise, direct, no filler.
Expert skill for building AI systems with Weft, a Rust-based programming language where LLMs, humans, APIs, and infrastructure are first-class primitives with typed connections and durable execution.
Lossless DFlash speculative decoding for MLX on Apple Silicon — 1.7–4x faster LLM inference using block diffusion drafting with target model verification.
Karpathy LLM Wiki 패턴 기반 지식 관리 스킬. 코드 프로젝트와 옵시디언 노트 모두 지원. Raw Source(코드·문서)를 읽어 docs/wiki/에 누적형 지식베이스를 구축·유지한다. "wiki", "위키", "ingest", "인제스트", "wiki 점검", "wiki lint", "wiki 업데이트", "문서화해줘", "아키텍처 설명해줘", "어떻게 동작해?" 키워드로 트리거. qmd 검색 도구와 연동하여 토큰 절약 + 높은 검색 정확도 제공.
Expert guidance for building conversational AI applications with Chainlit framework in Python. Use when (1) creating chat interfaces for LLM applications, (2) building apps with OpenAI, LangChain, LlamaIndex, or Mistral AI, (3) implementing streaming responses, (4) adding UI elements like images, files, charts, (5) handling user file uploads, (6) implementing authentication (OAuth, password), (7) creating multi-step workflows with visible steps, (8) building RAG applications with document upload, or (9) deploying chat apps to web, Slack, Discord, or Teams.