1.3K skills · sorted by relevance
Plataforma de observabilidade de IA de código aberto para rastreamento de LLM, avaliação e monitoramento. Use ao debugar aplicações de LLM com rastreamentos detalhados, executar avaliações em datasets ou monitorar sistemas de IA em produção com insights em tempo real.
The English summary is being prepared. Showing the original description.
Domine estratégias abrangentes de avaliação para aplicações LLM, desde métricas automatizadas até avaliação humana e testes A/B.
The English summary is being prepared. Showing the original description.
Avalia modelos de geração de código em HumanEval, MBPP, MultiPL-E e 15+ benchmarks com métricas pass@k. Use ao comparar modelos de código, avaliar capacidades de codificação, testar suporte multilíngue ou medir qualidade de geração de código. Padrão da indústria do BigCode Project usado pelos leaderboards do HuggingFace.
The English summary is being prepared. Showing the original description.
Testes e benchmarking de agentes LLM incluindo testes comportamentais, avaliação de capacidades, métricas de confiabilidade e monitoramento em produção—onde até os melhores agentes alcançam menos de 50% em benchmarks do mundo real. Use quando: testes de agentes, avaliação de agentes, benchmark de agentes, confiabilidade de agentes, teste de agentes.
The English summary is being prepared. Showing the original description.
Avalia LLMs em 100+ benchmarks de 18+ harnesses (MMLU, HumanEval, GSM8K, segurança, VLM) com execução multi-backend. Use quando precisar de avaliação escalável em Docker local, HPC Slurm ou plataformas cloud. Plataforma enterprise-grade da NVIDIA com arquitetura container-first para benchmarking reproduzível.
The English summary is being prepared. Showing the original description.
Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures. Use when a healthcare deployment must be gated on patient-safety tests for CDSS accuracy, PHI exposure, and workflow integrity.
The English summary is being prepared. Showing the original description.
Audits SwiftUI performance: rendering, scrolling, CPU and memory, unnecessary view updates, body re-evaluations, and layout thrashing, with Instruments guidance when code review is inconclusive. Use when a SwiftUI screen stutters, scrolls poorly, or uses too much CPU.
The English summary is being prepared. Showing the original description.
Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO, tech debt, technical debt, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, or technology strategy.
The English summary is being prepared. Showing the original description.
Use when turning expert materials, execution traces, repository evidence, or long-form documents into an inspectable, correctable, and empirically verified agent skill. Covers source governance, capability-vs-behavior separation, contrastive induction from successes and failures, intervention testing, versioning, rollback, and task-conditioned vs. reusable-library evaluation.
The English summary is being prepared. Showing the original description.
Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce a concrete action plan for improvements. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals, evaluate, benchmark, fix wrong behaviors, improve quality, or do quality assurance for any Python project that calls an LLM model.
The English summary is being prepared. Showing the original description.
Use when designing defensive monitoring for agent systems whose risks accumulate across users, sessions, subagents, files, or tool calls. Adds online cross-context clustering with rare escalation, time-to-detect evaluation, provenance checks for control-like workspace content, and sanitized commits for persistent prompt-injection defense.
The English summary is being prepared. Showing the original description.
Use when evaluating MCP-enabled agents, tool-using LLM systems, multi-server workflows, tool-selection quality, trajectory quality, task completion, or MCP security regressions.
The English summary is being prepared. Showing the original description.
Use when comparing basic, enhanced, GraphRAG, or agentic RAG designs, evaluating domain-specific RAG quality, tuning retrieval components, or deciding whether agentic RAG is worth its cost.
The English summary is being prepared. Showing the original description.
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
The English summary is being prepared. Showing the original description.
Validate and implement Sinclair ZX Spectrum 48K ROM-visible behavior in the EMULATORS repository, including reset and restart vectors, IM1/NMI handling, keyboard scanning and repeat, beeper and tape routines, screen/printer output, channels and streams, BASIC tokenization and execution, expression evaluation, memory movement, system variables, calculator stack, floating-point formats, ROM traps, localized ROM selection, and firmware/hardware timing contracts. Use when Codex reviews or edits ZX Spectrum ROM loading, KERNAL-style traps, keyboard, tape, screen, printer, BASIC files, tokens, system variables, startup, interrupts, or compatibility tests.
The English summary is being prepared. Showing the original description.
Automatic quality check on significant outputs via isolated sub-agent. Spawns reflection-agent for objective evaluation without conversation context bias.
The English summary is being prepared. Showing the original description.
Professional business analysis skill aligned with BABOK® Guide v3 standards. Use this skill when you need to elicit and document requirements, analyze business processes, conduct stakeholder analysis, develop business cases, perform gap analysis, or create business requirements documents (BRD). Ideal for requirements gathering, process mapping (BPMN), financial analysis (ROI, NPV), stakeholder engagement, and solution evaluation. Triggers: "gather requirements", "create business case", "analyze process", "stakeholder analysis", "gap analysis", "BRD", "functional requirements", or requests involving business analysis tasks.
The English summary is being prepared. Showing the original description.
Professional contract review skill for business agreements including NDAs, MSAs, SLAs, SOWs, and software license agreements. Provides systematic clause-by-clause analysis, risk assessment with quantified scoring, red flag detection, and negotiation guidance. Use this skill when reviewing vendor contracts, partnership agreements, service agreements, or any business contract requiring risk evaluation and negotiation preparation. Triggers include "review this contract", "analyze this NDA", "check this agreement for risks", "prepare for contract negotiation", or when evaluating terms and conditions.
The English summary is being prepared. Showing the original description.
Evaluate plan.md design decisions for dominant-axis misalignment using the Decision Quality framework. Detects when a plan optimizes for the wrong evaluation axis given the nature of the change. Use during plan review alongside logic-validator and scope-justification-reviewer.
The English summary is being prepared. Showing the original description.
Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project clients, creating versioned agents with PromptAgentDefinition, running evaluations, managing connections/deployments/datasets/indexes, or using OpenAI-compatible clients. This i...
The English summary is being prepared. Showing the original description.
Build AI applications using Azure AI Projects SDK for JavaScript (@azure/ai-projects). Use when working with Foundry project clients, agents, connections, deployments, datasets, indexes, evaluations, or getting OpenAI clients.
The English summary is being prepared. Showing the original description.
Azure AI Projects SDK for .NET. High-level client for Azure AI Foundry projects including agents, connections, datasets, deployments, evaluations, and indexes. Use for AI Foundry project management, versioned agents, and orchestration. Triggers: "AI Projects", "AIProjectClient", "Foundry project"...
The English summary is being prepared. Showing the original description.
Azure AI Projects SDK for Java. High-level SDK for Azure AI Foundry project management including connections, datasets, indexes, and evaluations. Triggers: "AIProjectClient java", "azure ai projects java", "Foundry project java", "ConnectionsClient", "DatasetsClient", "IndexesClient".
The English summary is being prepared. Showing the original description.
Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code spe...
The English summary is being prepared. Showing the original description.