GitHub
Deep-Research-skills
#592 of 964 in the AI Agent Index
10 Score
Real usage —
Momentum —
Attention 39
About
If you find this project helpful, please give it a star! :star:
Inspired by RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context
A structured research workflow skill for Claude Code, OpenCode, and Codex, supporting two-phase research: outline generation (extensible) and deep investigation. Human-in-the-loop design ensures precise control at every stage.
Important: In OpenCode, ANY model's websearch requires OPENCODEENABLEEXA=1. A plain export only affects the current shell; writing it to /.bashrc makes it persistent. Without it, you only get web fetch, which is weaker for the deep research phase.
Add or update /.codex/config.toml using either…
Across sources
1.7k Stars
- Stars 1.7k
- Forks 135
- Commits 46
- Releases 0