AI for Developers
Agent skill (SKILL.md) Open source MIT 2.5k

Deep Research Skills

Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control

Install

For this project
$ npx skills add Weizhena/Deep-Research-skills -a claude-code
For every project
$ npx skills add Weizhena/Deep-Research-skills -a claude-code -g

Or copy the skill folder into .claude/skills/ (project) or ~/.claude/skills/ (all projects).

For this project
$ npx skills add Weizhena/Deep-Research-skills -a codex
For every project
$ npx skills add Weizhena/Deep-Research-skills -a codex -g

Or copy the skill folder into .agents/skills/ (project) or ~/.agents/skills/ (all projects).

For this project
$ npx skills add Weizhena/Deep-Research-skills -a opencode
For every project
$ npx skills add Weizhena/Deep-Research-skills -a opencode -g

Or copy the skill folder into .agents/skills/ (project) or ~/.config/opencode/skills/ (all projects).

See the repository README for installation instructions.

When to use

Use it when you want a research task broken into an outline you approve first, and then investigated item by item, instead of a one-shot answer.

Deep Research Skill is a structured research workflow for Claude Code, OpenCode and Codex, with human-in-the-loop control at each stage. It works in two phases: outline generation, which you can extend, and deep investigation. It was inspired by the RhinoInsight paper on controlling model behavior and context in deep research.

The README lists use cases such as academic research (paper surveys and benchmark reviews), technical research (technology comparison and tool selection), market research (competitor analysis) and due diligence (company research and risk assessment). Install by cloning the repo and copying the English or Chinese skill folder into the agent's skills directory.

Related skills

All skills