bmad-technical-research

Conducts web-verified technical research and generates cited research reports on technologies and architectures.

Updated May 7, 2026
One-click install
npx skills add https://github.com/jgabriellima/deep-agent-skill --skill bmad-technical-research-jgabriellima
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-technical-research
Source: https://github.com/jgabriellima/deep-agent-skill/tree/main/skills/bmad-technical-research
Command: npx skills add https://github.com/jgabriellima/deep-agent-skill --skill bmad-technical-research-jgabriellima

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Producing a trustworthy technical research report requires gathering current data, verifying sources, and structuring findings across architecture, integration, and implementation domains, which is slow and error-prone when done manually. ## Core Features & Use Cases - Guided Six-Step Workflow: Walks through scope confirmation, technology stack analysis, integration patterns, architectural patterns, implementation research, and final synthesis with user confirmation at each stage. - Web-Verified Research: Requires live web search with multi-source validation and confidence levels for every technical claim, with citations appended to the report. - Structured Report Generation: Produces a complete research document with executive summary, table of contents, recommendations, and source documentation from a Markdown template. - Use Case: Ask for a technical research report comparing GraphQL and REST API architectures, and the workflow interviews you on scope, searches current sources, and delivers a fully cited report saved to your planning artifacts folder. ## Quick Start Ask the agent to conduct a technical research report on a topic such as serverless deployment options for Node.js and confirm the proposed research scope.

Frequently Asked Questions about bmad-technical-research

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a technical research report with this workflow?▼

State the technology topic you want researched, then confirm the proposed scope covering architecture, technology stack, integration, and implementation. The workflow runs six steps with web search verification and saves a cited Markdown report to your planning artifacts folder.

What topics can technical research cover?▼

It covers programming languages, frameworks, databases, cloud platforms, API and integration patterns, architectural design, scalability, security, and implementation practices. Any technology or architecture question, such as React versus Vue or GraphQL versus REST, is a valid topic.

Does technical research require web search access?▼

Yes, web search is a hard prerequisite and the workflow aborts if it is unavailable. Every technical claim must be verified against current public sources with citations rather than relying on training data alone.

Where is the research report saved?▼

The report is created under the planning artifacts directory configured in the BMad config file, named with the research topic slug and date. Content is appended step by step and finalized with an executive summary and table of contents.

Can I customize the research workflow behavior?▼

Yes, the customize.toml file supports activation steps, persistent facts loaded from project files, and an on-complete action. Team and user-level TOML overrides merge with the defaults using structural merge rules.