В каталоге 185 367 навыков в 14 категориях.
Test llm-mux IR translator - cross-format API translation
A technique skill uses the same engine as genre skills. Use it whenever a task is tagged LLM, NPC
Expert guide for LLM observability in production — token cost tracking, hallucination rate monitoring, latency analysis,...
Frame Claude's identity as an LLM operator that does not tire, treats convergence as zero findings (not exhausted budget...
LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de q...
Use when when you need specialized assistance with this domain
LLM-OPS -- IA de Producao workflow skill. Use this skill when the user needs LLM Operations -- RAG, embeddings, vector d...
Local LLM health checks and cache management. Probe Ollama/vLLM/SGLang endpoints, clean model caches.
Optimize websites for AI assistant recommendations. ChatGPT, Gemini, Perplexity, Claude. Get cited in AI answers.
Add a two-layer quality gate around any LLM call so bad model output never reaches the user. Use when building agents or...
Review or plan changes that affect prompts, model output validation, fallback behavior, or LLM-driven decisions.
Protocol for two LLM agents (Claude, Codex or any other) to agree and work from one shared folder: message format, chann...
AI-first application patterns, LLM testing, prompt management
Pydantic-AI agents, RAG, embeddings for Pulse Radar knowledge extraction.
Plan and execute large language model pretraining from data preparation to checkpoint management
look up and explain llm api pricing across models.dev, openrouter, and official provider pages. use when the user asks f...
Design, harden, evaluate, and version prompts for model-agnostic LLM applications. Use for system instructions, few-shot...
Use when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hal...
Optimize prompts for better LLM outputs through systematic analysis and refinement
Generate multiple LLM responses using diverse system prompt variants to increase reasoning diversity for self-consistenc...
LeeWay-governed LLM Prompting and Engineering workflow. Use when a task requires llm prompting procedures, validation, a...
Set up a new LLM provider connection, discover valid model ids, create and validate a model profile — securely and end-t...
Comprehensive LLM model evaluation and ranking system. Use when users ask to compare language models, find the best mode...
Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a sing...
Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements....
This skill should be used when users want to route LLM requests to different AI providers (OpenAI, Grok/xAI, Groq, DeepS...
Use when designing how one canonical agent core runs across Codex, Claude Code, Gemini CLI, Cursor, and AGENTS.md-compat...
Security patterns for LLM integrations including prompt injection defense and hallucination prevention. Use when impleme...
U-llm-sdk and claude-only-sdk patterns. Use when working on projects with LLM service, designing LLM integrations, or im...
Optimize content for AI search engines (ChatGPT, Perplexity, Google AI Overviews, Claude). Use when working with AEO, GE...
OWASP LLM Top 10 security testing - prompt injection, system prompt leakage, excessive agency, sensitive data disclosure
审查提示词注入、工具授权、数据隔离与代理执行边界
Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG ex...
Comprehensive guide to securing LLM applications including prompt injection prevention, jailbreak detection, guardrails,...
Security testing for LLM-powered applications including prompt injection, jailbreak detection, data leakage prevention,...
Restructure Web-UI / human-triggered tasks into CLI + file-output loops the LLM can iterate alone, with structured logs...
LLM inference infrastructure, serving frameworks (vLLM, TGI, TensorRT-LLM), quantization techniques, batching strategies...
LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, o...
Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handl...
Use when the user needs to extract structured data (JSON objects, arrays, enums) from an LLM response; The user is build...
Get reliable JSON, enums, and typed objects from LLMs using response_format, tool_use, and schema-constrained decoding a...
Detects compromised or backdoored models loaded from unverified sources, floating tags, or unreviewed registries. Use wh...
Assign each new agent a different directional rotation pattern from a set of permutations to ensure swarm coverage diver...
Comprehensive LLM security testing prompts for bias detection, data leakage, alignment testing, and adversarial prompt r...
Use this skill when you need to test LLM behavior, failure modes, and evidence-based quality boundaries; triggers includ...
Testing patterns for LLM-based applications. Use when testing AI/ML integrations, mocking LLM responses, testing async t...
Entfernt KI-Spuren, Chat-Reste, Platzhalter und LLM-Stilmuster aus fertigen Texten und prüft die AI-Disclosure auf Volls...
Scalable TF-IDF retrieval over large document corpora using frozen vocabulary and chunked top-k merging.
See the main LLM Cost Optimization skill for comprehensive coverage of token economics and optimization strategies.
Security patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend lim...
LLM Tuning Patterns
LLM Text Protocol provides standardized patterns for text-based interactions with language models. It encompasses prompt...
Design UI for LLM-powered features — streaming response display, hallucination states, RAG source attribution, generativ...
Use when an LLM judge (vision or text) is the acceptance gate for subjective quality (render realism, design polish, doc...
Build and maintain a persistent markdown wiki that an LLM updates on the user's behalf, usually inside an Obsidian vault...
Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementa...
Explain and apply the foundational LLM Wiki architecture and knowledge-management strategy. Use for setup, architecture,...
Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compil...
Build external-knowledge wikis.
Karpathy 风格 LLM Wiki / markdown knowledge base 工作流。用于 ingest、query、lint 持久化知识库;先做 orientation,再按 analysis -> generation...
Karpathy's LLM Wiki: build/query interlinked markdown KB.
Use when the user wants a compiled markdown wiki, Karpathy llm-wiki ingest/query/lint, or to file sources into interlink...
Bootstrap and maintain an LLM-generated wiki knowledge base in a project, following the llm-wiki pattern (persistent, co...
Guide users through setting up a personal LLM-maintained wiki — a persistent, compounding knowledge base where the LLM i...
Use when designing, building, or maintaining a persistent Obsidian-compatible knowledge base that an LLM updates over ti...
Enable and configure the llm-wiki addon for long-term, long-form project memory, select a wiki profile, and route ingest...
Search, ingest, create, and maintain notes in a topic-specific personal wiki (raw sources + cited wiki pages), following...
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gis...
Build and maintain a structured LLM-generated wiki for any codebase. Use when the user asks to analyze/understand/docume...
Use when searching, asking, ingesting, compiling, reviewing, refreshing, validating, or answering from the shared local...
Build and maintain a personal knowledge base (wiki) using LLMs. Instead of RAG-style retrieval, the LLM incrementally co...
个人知识库构建系统(基于 Karpathy llm-wiki 方法论)。让 AI 持续构建和维护你的知识库, 支持多种素材源(网页、推特、公众号、小红书、知乎、YouTube、PDF、本地文件), 自动整理为结构化的 wiki。 触发条件:...
Compile a Raw source into concise, linked Wiki notes. Use when a new source lands in Raw/Sources/ or when a source is ma...
Validate Wiki and source note health. Use before commits, after ingests, or when notes were edited by hand.
Use when the user wants to lint a repo following the Karpathy LLM Wiki pattern (raw/ + wiki/ + SCHEMA.md / index.md / lo...
Routine maintenance and safe commits. Use when committing changes, rebuilding indexes, or checking overall vault health.
Answer questions from the compiled Wiki. Use whenever the user asks a knowledge question that this vault might cover.
Dense retrieval over a FAISS-indexed Wikipedia corpus to provide grounding context for LLM question answering.
Operate AlexsJones/llmfit to inspect detected hardware, rank model fit, estimate plans and storage, run the local REST A...
Use before changing code, after editing, and whenever an LLMGRAPH answer says maybe_more or cannot_see. Explains which o...
Practical guide for llmlb assistant CLI commands replacing the legacy MCP server flow.
Interactive meal planning wizard. Use when user wants to create a meal plan, optimize their diet, set up nutritional con...
LLMOps — RAG 운영, 프롬프트 버전 관리, Ragas 기반 LLM 평가, NeMo 가드레일. Use when LLM 앱을 운영 환경에서 품질 평가하고 프롬프트 변경을 관리하거나 가드레일을 붙일 때.
LLMアプリケーションの設計・運用・評価・最適化。プロンプト管理、RAG構築、ファインチューニング、評価パイプライン、コスト最適化、本番運用。「LLM」「プロンプト」「RAG」「ファインチューニング」「AI運用」「評価」に関する質問で使用。
Build production LLMOps platforms with CI/CD, model promotion workflows, evaluation gates, rollback, and governance acro...
Router skill for LLMQuant commodities workflows. Use when the user needs commodity spot, futures curve, inventory, roll...
Router skill for LLMQuant credit workflows. Use when the user needs issuer credit review, spread regime analysis, high-y...
Router skill for LLMQuant crypto workflows. Use when the user needs crypto market regime analysis, token research, perpe...
Router skill for LLMQuant Data primitive workflows. Use when the user needs SEC filings, 13F holders, macro snapshots, o...
Router skill for LLMQuant equities workflows. Use when the user needs stock analysis, equity comparison, research memos,...
Router skill for LLMQuant equity derivatives workflows. Use when the user needs single-stock derivative, convertible, wa...
Router skill for LLMQuant ETFs workflows. Use when the user needs ETF holdings, overlap, concentration, issuer snapshot,...
Router skill for LLMQuant event workflows. Use when the user needs earnings event briefs, M&A tracking, regulatory risk,...
Router skill for LLMQuant investor-lens workflows. Use when the user wants an investor-style reasoning overlay grounded...
Router skill for LLMQuant macro workflows. Use when the user needs macro dashboards, Fed or central-bank previews, infla...
Router skill for LLMQuant market-intelligence workflows. Use when the user needs macro views, market sentiment dashboard...
Router skill for LLMQuant options workflows. Use when the user needs IV rank, option scoring, strategy construction, Gre...