octo-research

Research - Deep Multi-AI Research

Your first output line MUST be: 🐙 Octopus Research

🤖 INSTRUCTIONS FOR CLAUDE

MANDATORY COMPLIANCE — DO NOT SKIP

When the user explicitly invokes /octo:research, you MUST execute the structured research workflow below. You are PROHIBITED from answering directly, skipping the multi-provider research, or deciding the topic is "too simple" for deep research. The user chose this command deliberately — respect that choice.

EXECUTION MECHANISM — NON-NEGOTIABLE

You MUST execute this command by invoking the corresponding skill via the Skill tool. You are PROHIBITED from:

• ❌ Using the Agent tool to research/implement yourself instead of invoking the skill
• ❌ Using WebFetch/Read/Grep as a substitute for multi-provider dispatch
• ❌ Skipping orchestrate.sh calls because "I can do this faster directly"
• ❌ Implementing the task using only Claude-native tools (Agent, Write, Edit)

Multi-LLM orchestration is the purpose of this command. If you execute using only Claude, you've violated the command's contract.

---

When the user invokes this command (e.g., /octo:research <arguments>):

Step 1: Ask Research Intensity

CRITICAL: Before starting research, use the AskUserQuestion tool to select intensity:

AskUserQuestion({
  questions: [
    {
      question: "How thorough should the research be?",
      header: "Research Intensity",
      multiSelect: false,
      options: [
        {label: "Quick (1-2 min)", description: "2 agents — fast problem space scan"},
        {label: "Standard (2-4 min)", description: "4-5 agents — balanced multi-perspective coverage (recommended)"},
        {label: "Deep (3-6 min)", description: "6-7 agents — exhaustive analysis with web search"}
      ]
    }
  ]
})

Map the answer to an intensity value:

• "Quick" → quick
• "Standard" → standard
• "Deep" → deep

Step 2: Invoke Skill with Intensity

✓ CORRECT - Use the Skill tool:

Skill(skill: "octo:discover", args: "[intensity=quick|standard|deep] <user's arguments>")