Explorar skills

Structured hypothesis formulation: turn observations into testable hypotheses with predictions, propose mechanisms, design experiments. Follows the scientific method. Use scientific-brainstorming for open ideation; hypogenic for automated LLM hypothesis testing on datasets.

Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, cl

Use when setting up LibreChat logging, configuring metrics collection, integrating Langfuse for LLM observability, tracking token usage and costs, or analyzing LibreChat server logs. Also use when asked about monitoring LibreChat in production or debugging performance from logs.

Use quando o usuário deseja otimizar conteúdo para mecanismos de busca de IA, ser citado por LLMs ou aparecer em respostas geradas por IA. Também se aplica a termos como 'AI SEO', 'AEO', 'LLMO' e 'otimização para ChatGPT'.

Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, cl

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.

Analisa dados de ocupação, utilização e presença de diversas fontes (Wi-Fi, crachás, sensores, câmeras, pesquisas, reservas) para identificar tendências, picos, padrões semanais, anomalias e recomendações. Use ao analisar dados de contagem de pessoas, fluxo, crachá, Wi-Fi, ocupação ou uso de instalações.

Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model's knowledge cutoff. Provides access to multiple Perplexity models including Sonar

Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, cl

Implement real-time data streaming with Server-Sent Events (SSE), WebSockets, and ReadableStream APIs. Master backpressure handling, reconnection strategies, and LLM streaming for 2025+ real-time applications.

Padrões BAML genéricos para prompting de LLM com segurança de tipo, cobrindo design de esquema, geração de DTO, wrappers de cliente e geração de código entre linguagens. É agnóstico a frameworks.

Use when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.