do.research

Coordinate planning and execution agents to produce Obsidian research notes.

6|3|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/dull-bird/DeepOrbit --skill do-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: do.research
Source: https://github.com/dull-bird/DeepOrbit/tree/main/skills/do.research
Command: npx skills add https://github.com/dull-bird/DeepOrbit --skill do-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of conducting deep, structured research by orchestrating a planning agent and a separate execution agent to produce consistent, Obsidian-ready research notes, atomic wiki concepts, examples, and visual maps while preserving user control.

Core Features & Use Cases

  • Two-agent workflow: A Planning Agent drafts a research plan and identifies existing vault context; an Execution Agent runs with fresh context to gather sources, write the main research note, and create atomic wiki entries.
  • Obsidian-first outputs: Produces properly formatted notes with required YAML frontmatter, paths under 30_Research and 40_Wiki, example files, and appends links to daily notes or related projects.
  • Use Case: Turn a topic like "Consistent Hashing" or "OAuth2" into a vetted research plan, then generate a complete research note, concise wiki concepts, examples directory, and references automatically after user confirmation.

Quick Start

Use /do:research to create a research plan for "Consistent Hashing", review the generated plan at the reported path, then confirm to execute the research and produce Obsidian notes.

Frequently Asked Questions about do.research

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

FAQPage Schema
How do I automate research planning and generate Obsidian notes?

Automate research planning by using a two-agent workflow where a planning agent drafts a strategy and an execution agent generates Obsidian-formatted notes, examples, and atomic wiki entries. This coordinates deep research execution while maintaining user control over the final output.

What is the best way to structure deep research into an Obsidian wiki?

The best way to structure deep research into an Obsidian wiki is using an orchestrated two-agent system that produces main research notes with YAML frontmatter under 30_Research paths, and creates atomic wiki concepts under 40_Wiki, appending links to daily notes automatically.

How do I create atomic wiki entries and examples for complex topics?

Create atomic wiki entries and examples for complex topics by running an execution agent with fresh context after confirming a drafted research plan. The agent gathers sources and outputs concise wiki concepts, example files, and visual maps formatted for Obsidian.

Can I review a research plan before the agent writes the notes?

Yes, you can review a research plan before notes are written. The planning agent drafts the strategy and reports the file path, requiring your explicit confirmation before the execution agent proceeds to gather sources and generate the Obsidian-formatted research notes.

Does this research workflow require specific Obsidian folder paths?

Yes, the research workflow requires specific Obsidian folder paths. It enforces path and frontmatter rules by saving main research notes under 30_Research and atomic wiki entries under 40_Wiki, ensuring consistent knowledge-management integration across your vault.