Os cinco dom铆nios pontuados e seus t贸picos de tarefas. Expanda qualquer tarefa para ver o conhecimento e as habilidades que ela testa. Pule para um dom铆nio abaixo.
Designing agentic loops, coordinator-subagent systems, multi-step workflows with enforcement, hooks, task decomposition, and session state.
Dom铆nio 2. Tool Design & MCP Integration
18%
Designing clear tool interfaces, structured error responses, tool distribution and tool_choice, MCP server integration, and built-in tool selection.
Dom铆nio 3. Claude Code Configuration & Workflows
20%
CLAUDE.md hierarchy, custom slash commands and skills, path-specific rules, plan mode vs direct execution, iterative refinement, and CI/CD integration.
Dom铆nio 4. Prompt Engineering & Structured Output
20%
Explicit criteria to reduce false positives, few-shot prompting, structured output via tool_use and JSON schemas, validation/retry loops, batch processing, and multi-pass review.
Dom铆nio 5. Context Management & Reliability
15%
Preserving critical information across long interactions, escalation and ambiguity resolution, error propagation, large-codebase context, human review and confidence calibration, and provenance.
