Zhang Lu.
← Skills

/research

Deep research in the PRD methodology: Proposal → Baseline → parallel sub-agent team → auto stitch → Lead synthesis. Parallel multi-dimensional investigation maximizes information density, producing an actionable bilingual report.

source: local ✎ handwritten

Purpose

A PRD-driven deep research skill. The pipeline:

Proposal → Baseline → parallel sub-agent team → auto stitch → Lead synthesis

Fully orchestrate an agent team to run parallel, multi-dimensional investigation and maximize information density.

When to use

The user wants to research any topic in depth:

  • Technical evaluation
  • Competitive analysis
  • Architecture decision
  • Trend investigation
  • Market research

→ produces an actionable bilingual report

When not to use

  • Looking up a library’s API docs → use /context7
  • Debugging → use /tdd
  • Framework selection → use /framework-selection

Trigger examples

  • /research AI search architecture migration
  • /research compare Dify / Coze / Mars Agent
  • /research https://github.com/karpathy/autoresearch
  • /research livestream monetization trends 2026 --quick