Deep Research skills
Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control
Install
pip install pyyamlInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Deep Research Skill for Claude Code / OpenCode / Codex
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.
Use Cases
- Academic Research: Paper surveys, benchmark reviews, literature analysis
- Technical Research: Technology comparison, framework evaluation, tool selection
- Market Research: Competitor analysis, industry trends, product comparison
- Due Diligence: Company research, investment analysis, risk assessment
Installation
git clone https://github.com/Weizhena/deep-research-skills.git
cd deep-research-skills
Claude Code
# English version
cp -r skills/research-en/* ~/.claude/skills/
# Chinese version
cp -r skills/research-zh/* ~/.claude/skills/
# Required: Install agent and modules
cp agents/web-search-agent.md ~/.claude/agents/
cp -r agents/web-search-modules ~/.claude/agents/
# Required: Install Python dependency
pip install pyyaml
OpenCode (default: gpt-5.4)
# Skills (same as Claude Code)
cp -r skills/research-en/* ~/.claude/skills/ # or research-zh for Chinese
# Required: Enable web search for current shell
export OPENCODE_ENABLE_EXA=1
# Optional: make it permanent
echo 'export OPENCODE_ENABLE_EXA=1' >> ~/.bashrc
source ~/.bashrc
# Required: Install agent and modules
cp agents/web-search-opencode.md ~/.config/opencode/agents/web-search.md
cp -r agents/web-search-modules ~/.config/opencode/agents/
# Required: Install Python dependency
pip install pyyaml
Important: In OpenCode, ANY model's websearch requires
OPENCODE_ENABLE_EXA=1. A plainexportonly affects the current shell; writing it to~/.bashrcmakes it persistent. Without it, you only getweb fetch, which is weaker for the deep research phase.
Codex
# English version
mkdir -p ~/.codex/skills ~/.codex/agents
cp -r skills/research-codex-en/* ~/.codex/skills/
# Chinese version
mkdir -p ~/.codex/skills ~/.codex/agents
cp -r skills/research-codex-zh/* ~/.codex/skills/
# Required: Install web researcher agent and modules
cp agents-codex/web-researcher.toml ~/.codex/agents/
cp -r agents-codex/web-search-modules ~/.codex/agents/
# Required: Install Python dependency
pip install pyyaml
Add or update ~/.codex/config.toml using either method below:
Option A: Automatic script
cd deep-research-skills
bash scripts/install-codex.sh
Option B: Manual edit
suppress_unstable_features_warning = true
[features]
multi_agent = true
default_mode_request_user_input = true
[agents.web_researcher]
description = "Use this agent when you need to research information on the internet, particularly for debugging issues, finding solutions to technical problems, or gathering comprehensive information from multiple sources. This agent excels at finding relevant discussions. Use when you need creative search strategies, thorough investigation, or compilation of findings from multiple sources."
config_file = "agents/web-researcher.toml"
Commands
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…