Deep-Research-skills

Provides structured deep research capabilities for Claude Code, OpenCode, and Codex, supporting a two-phase research process.

Agent SkillResearchOpen source

View source →

Type: Agent Skill
Open source: Yes
GitHub Stars: ★ 1.3k
Source: skill-github
Repository: github.com/Weizhena/Deep-Research-skills

Overview

Deep-Research-skills is a structured research workflow skill designed for Claude Code, OpenCode, and Codex. It supports a two-phase research approach: outline generation (scalable) and in-depth investigation. With human-machine interaction design, it ensures precise control at each stage. This skill assists users with tasks such as academic research, technical research, market research, and due diligence. Installation requires copying the skill files to a specified directory and installing the Python dependency pyyaml. Ideal for users requiring in-depth research capabilities.

Capabilities

▪Generate research outlines
▪Add more research items
▪Add more field definitions
▪Conduct in-depth research on each item
▪Generate Markdown reports

Use cases

Academic researchTechnical researchMarket researchDue diligence

Setup

Requires: API KeyNode 环境Python 环境

git clone https://github.com/Weizhena/deep-research-skills.git && cd deep-research-skills && cp -r skills/research-en/* ~/.claude/skills/ && cp agents/web-search-agent.md ~/.claude/agents/ && cp -r agents/web-search-modules ~/.claude/agents/ && pip install pyyaml

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How to install Deep-Research-skills?

Clone the repository and copy the skill files to the designated directory, then install the Python dependency pyyaml.

Which platforms are supported?

Supports Claude Code, OpenCode, and Codex.

Related skills

Scrapling

An adaptive web scraping framework capable of handling everything from single requests to large-scale scraping.

MCP

TrendRadar

An AI-driven tool for sentiment monitoring and trend analysis, supporting multi-platform aggregation, RSS subscription, and intelligent notifications.

MCP