Explorar skills

Reviews a service or codebase against a full observability checklist — logs, metrics, traces, and alerting gaps.

Plan reproducible ML experiment runs with explicit parameters, metrics, and artifacts. Use before model training to standardize tracking-ready experiment definitions.

Generates comprehensive unit tests for any function or module with edge cases.

A Claude Skills collection providing ptrade‑dev strategy guardrails with lifecycle checks, API‑aware validation, and error‑pattern detection, plus structured parsing and webpage‑to‑Markdown tools—enabling LLMs to reliably analyze, generate, and debug PTrade/SimTradeLab strategies

Actively enumerate in-scope hosts and services, then produce normalized network mapping artifacts.

Diagnosing context FAILURES — lost-in-middle, poisoning, distraction, confusion, and clash patterns with model-agnostic measurement workflows. Use when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, context clash, or agent performance degradation. NOT for learning context basics or

Use when the user asks to merge another branch into the current branch, pull upstream changes without rebasing, or resolve merge conflicts.

Guided setup of Exasol Personal — a single-node Exasol database deployed to your own cloud account. Covers AWS account preparation, CLI installation, deployment, sample data loading, and MCP server setup.

Maintains and formats a CHANGELOG.md following Keep a Changelog conventions from git history or PR list.

Use when auditing and fixing performance hot paths in a scope — N+1 queries, overfetching, wasted recomputation, blocking hot paths, unbounded growth. Triggers on "audit performance", "fix slow paths", "check for N+1", "performance review".

Audita um projeto dbt para prontidão de agentes de IA, identificando erros potenciais que um agente poderia cometer com os dados. Gera um relatório priorizado detalhando modos de falha como números, tabelas ou junções incorretas, utilizando uma arquitetura escalável de duas passagens com subagentes paralelos.

Metodologia de Product Discovery com 18 tarefas, do estudo de mercado ao plano financeiro para investidores. Ideal para validar startups, avaliar hipóteses de mercado e preparar-se para rodadas de investimento.