Deep-Research-skills

Weizhena/Deep-Research-skills

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

Install

GitHub: Weizhena/Deep-Research-skills
Stars: ★ 2.4k
License: MIT
Language: Python
Last push: Aug 23, 2026
Topics: deep-research-agent · gpt-skills · llm-agent · opencode · opencode-skills · research

Run structured two-phase deep research: generate an outline, then investigate each item
Academic research such as paper surveys, benchmark reviews and literature analysis
Technical research such as technology comparison, framework evaluation and tool selection
Market research and due diligence such as competitor and company analysis

git clone https://github.com/Weizhena/deep-research-skills.git and copy the skills for your language into the skills folder
Copy the web-search agent and modules as instructed, and run pip install pyyaml
Run /research <topic> to make an outline, adding /research-add-items if needed
Run /research-deep to investigate each item, then /research-report for a Markdown report

Requires Python and pyyaml. In OpenCode, web search needs export OPENCODE_ENABLE_EXA=1; without it you only get the weaker web fetch.

Summarized by AI from the project docs; check the official docs before relying on it.

reaCommunity skills · ★ 386k
Reverse engineer anything with agents, from app behavior down to native binaries.
skillsCommunity skills · ★ 184k
Public repository for Agent Skills
ponytailCommunity skills · ★ 176k
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
agent-skillsCommunity skills · ★ 111k
Production-grade engineering skills for AI coding agents.
paperclipCommunity skills · ★ 107k
The open-source app everyone uses to manage agents at work