majiayu000/claude-skill-registry - Página 22

llm-evaluation

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

Idioma do texto original: inglês

llm-evaluation

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

Idioma do texto original: inglês

llm-function-calling

Implementing function calling (tool use) with LLMs for structured outputs and external integrations.

Idioma do texto original: inglês

llm-gateway-routing

LLM gateway and routing configuration using OpenRouter and LiteLLM. Invoke when: - Setting up multi-model access (OpenRouter, LiteLLM) - Configuring model fallbacks and reliability - Implementing cost-based or latency-based routing - A/B testing different…

Idioma do texto original: inglês

llmintegration

LLM integration patterns for Claude, GPT, Gemini, and Ollama. Activate for AI API integration, prompt engineering, token management, extended thinking, and multi-model orchestration.

Idioma do texto original: inglês

llm-integration

Guide for using LLM utilities in speedy_utils, including memoized OpenAI clients and chat format transformations.

Idioma do texto original: inglês

llm-judge-patterns

Comprehensive guide to using LLMs as judges for automated evaluation including prompt patterns, calibration, bias reduction, and multi-judge ensembles

Idioma do texto original: inglês

llm-local-deployment

Comprehensive guide for deploying LLMs locally using Ollama, vLLM, and llama.cpp. Local deployment offers privacy, cost control, and reduced latency compared to cloud APIs. This skill covers everythin

Idioma do texto original: inglês

llm-ops

Local LLM health checks and cache management. Probe Ollama/vLLM/SGLang endpoints, clean model caches.

Idioma do texto original: inglês

llm-pipeline

Pydantic-AI agents, RAG, embeddings for Pulse Radar knowledge extraction.

Idioma do texto original: inglês

llm-streaming-response-handler

Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI/Anthropic/Claude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on "LLM streaming", "SSE",…

Idioma do texto original: inglês

llm-streaming

LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, or streaming with tool calls.

Idioma do texto original: inglês

llm-token-optimization

See the main LLM Cost Optimization skill for comprehensive coverage of token economics and optimization strategies.

Idioma do texto original: inglês

llm-txt-protocol

LLM Text Protocol provides standardized patterns for text-based interactions with language models. It encompasses prompt engineering, response formatting, and text processing patterns that ensure cons

Idioma do texto original: inglês

llms-txt-support

Detect and use llms.txt files for LLM-optimized documentation. Use when checking if a site has LLM-ready docs before scraping.

Idioma do texto original: inglês

local-llm-fine-tuning

Guides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniques like LoRA and QLoRA.

Idioma do texto original: inglês

local-rag-search

Local Retrieval-Augmented Generation with vector search.

Idioma do texto original: inglês

logfire

Use for Pydantic Logfire observability, tracing, and debugging. Query exceptions, spans, logs with SQL. View traces in Logfire UI. 4 tools for application monitoring and error analysis.

Idioma do texto original: inglês

long-document-llm-pipeline

Use when processing documents over 50K characters through LLM APIs with section splitting and batch cost reduction.

Idioma do texto original: inglês

longitudinal-drift-detector

Detect behavioral drift and alignment degradation over time.

Idioma do texto original: inglês

looking-up-docs

Library documentation via Context7. Use for API references, code examples, framework docs.

Idioma do texto original: inglês

lora

Parameter-efficient fine-tuning with Low-Rank Adaptation (LoRA). Use when fine-tuning large language models with limited GPU memory, creating task-specific adapters, or when you need to train multiple specialized models from a single base.

Idioma do texto original: inglês

lora-ofl

Imported skill lora_ofl from anthropic

Idioma do texto original: inglês

lumen-ai

Master AI-powered natural language data exploration with Lumen AI. Use this skill when building conversational data analysis interfaces, enabling natural language queries to databases, creating custom AI agents for domain-specific analytics, implementing RAG…

Idioma do texto original: inglês

lyra

Transform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user mentions "optimize prompt", "improve prompt", "lyra", "prompt engineering", or needs help crafting effective AI prompts.

Idioma do texto original: inglês

mcp-local-rag

Provides score interpretation (< 0.3 good, > 0.5 skip), query optimization, and source naming for query_documents, ingest_file, ingest_data tools. Use this skill when working with RAG, searching documents, ingesting files, saving web content, or handling PDF,…

Idioma do texto original: inglês

meta-analyst-agent

AI self-improvement analyst. Tracks AI agent mistakes, analyzes failure patterns, and proposes system improvements. Implements continuous learning loop for trading system enhancement.

Idioma do texto original: coreano

metacognitive-self-mod

Analyze and improve the improvement process. Use for detecting regressions and meta-optimization.

Idioma do texto original: inglês

minimax-mcp-usage

Optimal patterns for MiniMax MCP tools (web_search + understand_image)

Idioma do texto original: inglês

moai-ai-nano-banana

Nano-Banana AI service integration for content generation, image creation, and AI-powered workflows. Use when integrating AI services for content creation.

Idioma do texto original: inglês

model

Inspect or change Babysitter model-routing policy by phase.

Idioma do texto original: inglês

model-ab-test

Use when validating model downgrades for skills or agents. Runs A/B comparison between current and proposed model, scores outputs against test criteria, produces verdict.

Idioma do texto original: inglês

model-fallback

模型自动降级与故障切换。当主模型请求失败、超时、达到速率限制或配额耗尽时，自动切换到备用模型，确保服务连续性。支持多供应商、多优先级的智能模型选择，提供健康监控、自动重试和错误恢复机制。

Idioma do texto original: chinês

model-management

CLI commands to add, update, list, and deprecate AI models in the database. Triggers on "add model", "new model", "update model", "deprecate model", "model pricing", "model cli".

Idioma do texto original: inglês

model-manager

Test, validate, and add new AI models to the eval suite. Use when user asks to add new models, test model access, check pricing, or update models.yml.

Idioma do texto original: inglês

model-router

Route work to the cheapest model tier that can reliably complete it.

Idioma do texto original: inglês

model-routing

Model selection strategy for subagents — haiku for exploration, sonnet for implementation, opus for architecture/security

Idioma do texto original: inglês

model-switch

Switch the agent's model at runtime and restart. Use when the user asks to change models (e.g., "switch to kimi", "use opus", "go cheaper"), or when the agent decides a different model is better for the current workload.

Idioma do texto original: inglês

model-usage

Step-by-step guidance for model usage.

Idioma do texto original: inglês

model-usage

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model…

Idioma do texto original: inglês