Find your next open-source project

Search by name, purpose, or keyword — or paste a GitHub repository URL
All skills

bmad-deep-recon

Draft a deep-research prompt, process a finished report, or run cited research on a topic or this codebase.

When to use it

You face a decision like picking a stack or entering a market and need evidence, not a quick chat answer.

For example

You say

Use bmad-deep-recon to research the competitive landscape for a self-hosted analytics tool and help me choose between PostHog and Plausible.

You get
  • Cited research summary
  • Selection comparison
  • Open questions list

How it works

  • Every claim must trace to a source with publisher and dates; project context can shape questions but never counts as evidence.
  • Draft, external run, and Process form a loop, so a report from your own deep-research tool becomes the same cited artifact.
  • A codebase mode answers questions about this repository from code and git history.

Before installing

Running research natively requires web access; without it, only Draft and Process are available.

This skill includes 2 scripts your assistant may run on your computer.