Pesquisa e Web

Decompose large tasks across parallel agents — use for migrations, multi-file refactors, or batch work

How to handle code review feedback — verify before implementing, push back when wrong, never agree blindly

Brainstorm creatively with pattern spotting and paradox hunting — use for ideation and exploration

Manage tasks with Claude Code native tools — use to track TODOs, delegate work, and monitor progress

Environment diagnostics — check providers, auth, config, hooks, scheduler, and more

Show where you are in the workflow and what to do next — use for progress checks and orientation

Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert

Write an AI-optimized PRD using multi-AI orchestration — use when scoping a new feature or product

Evidence before claims — run verification commands before declaring work complete, fixed, or passing

Route ordinary init, review, and security requests to Claude-native capabilities first; escalate to Octopus only when multi-LLM diversity adds value

Craft better prompts using proven optimization techniques — use when your prompt needs refinement

Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning