Infinite Gratitude - Multi-agent Research

Dispatch multiple agents to research a topic in parallel, compile findings, and iterate on new discoveries.

Sby Skills Guide Bot
Data & AIIntermediate
007/23/2026
Claude Code
#research#multi-agent#knowledge#automation

Recommended for


name: infinite-gratitude description: Multi-agent research that keeps bringing gifts back โ€” like cats! Dispatch multiple agents to research a topic in parallel, compile findings, and iterate on new discoveries. argument-hint: "<topic>" [--depth quick|normal|deep] [--agents 1-10]

Infinite Gratitude ๐Ÿพ

็„ก้™่ฒ“ๅ ฑๆฉ | ็„ก้™ใฎๆฉ่ฟ”ใ— Multi-agent research that keeps bringing gifts back โ€” like cats! ๐Ÿฑ

Quick Reference

| Option | Values | Default | |--------|--------|---------| | topic | Required | - | | --depth | quick / normal / deep | normal | | --agents | 1-10 | 5 |

Usage

/infinite-gratitude "pet AI recognition"
/infinite-gratitude "RAG best practices" --depth deep
/infinite-gratitude "React state management" --agents 3

Behavior

Step 1: Split Directions

Split {topic} into 5 parallel research directions:

  1. GitHub projects
  2. HuggingFace models
  3. Papers / articles
  4. Competitors
  5. Best practices

Step 2: Dispatch Agents

Task(
    prompt="Research {direction} for {topic}...",
    subagent_type="research-scout",
    model="haiku",
    run_in_background=True
)

Step 3: Collect Gifts

Compile all findings into structured report.

Step 4: Loop

If follow-up questions exist โ†’ Ask user โ†’ Continue? โ†’ Back to Step 2

Step 5: Final Report

Example Output

๐Ÿพ Infinite Gratitude!

๐Ÿ“‹ Topic: "pet AI recognition"
๐Ÿฑ Dispatching 5 agents...

โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”
๐ŸŽ Wave 1
โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”

๐Ÿฑ GitHub: MegaDescriptor, wildlife-datasets...
๐Ÿฑ HuggingFace: DINOv2, CLIP...
๐Ÿฑ Papers: Petnow uses Siamese Network...
๐Ÿฑ Competitors: Petnow 99%...
๐Ÿฑ Tutorials: ArcFace > Triplet Loss...

๐Ÿ’ก Key: Data volume is everything!

๐Ÿ” New questions:
   - How to implement ArcFace?
   - How to use MegaDescriptor?

Continue? (y/n)

๐Ÿพ by washinmura.jp

Notes

  • Uses haiku model to save cost
  • Max 5 agents per wave
  • Deep mode loops until satisfied

Additional Resources

Related Skills

  • ai-dojo โ€” Foundation for AI coding agents
  • research-scout โ€” Single-agent research

Part of ๐Ÿฅ‹ AI Dojo Series by Washin Village ๐Ÿพ

Related skills