Research

Deep web research with relevance scoring and knowledge graph storage. Use when researching topics, companies, people, or concepts. Performs Graph-of-Thoughts style exploration with parallel branching, relevance scoring, and synthesis into themed reports.

59 stars 10 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ratacat/claude-skills --skill research
Manual install
git clone --depth 1 https://github.com/ratacat/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/research ~/.claude/skills/research

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Deep Research Skill

A Graph-of-Thoughts research system that builds a knowledge graph through structured exploration, stores all findings in SQLite, and uses graph operations (merging, traversal, contradiction detection, relationship inference) to synthesize insights.

## CRITICAL REQUIREMENTS

**You MUST use the database for all operations.** Every finding, every URL, every search query, every relationship MUST be recorded. The database is not optional—it is the core of this methodology. If you skip database operations, the research is invalid.

**You MUST perform graph operations.** After each exploration phase, you MUST run merging, relationship inference, and contradiction detection. These are not suggestions—they are required steps.

**You MUST work iteratively.** Do not try to gather all information then synthesize. Work in cycles: explore → store → analyze graph → identify gaps → explore gaps → repeat.

## Arguments

Parse the user's input to extract:
- `topic`: The research subject (required unless --list or --continue)
- `--depth N`: How many levels deep to explore (default: 2)
- `--branches N`: How many aspects to explore in parallel (default: 5)
- `--continue "topic"`: Resume a previous research session
- `--list`: Show all saved research sessions

## Database Setup

Before ANY research, initialize the database. This is mandatory:

```bash
sqlite3 research.db < ~/.claude/skills/research/schema.sql 2>/dev/null || true
```
Read the full skill on GitHub

Details

Skill name
research
Path
skills/research/SKILL.md
Repo updated
11 February 2026

FAQ

What does the Research skill do?

Deep web research with relevance scoring and knowledge graph storage. Use when researching topics, companies, people, or concepts. Performs Graph-of-Thoughts style exploration with parallel branching, relevance scoring, and synthesis into themed reports.

How do I install the Research skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ratacat/claude-skills --skill research. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Research popular?

It lives in ratacat/claude-skills, which has 59 GitHub stars and 10 forks.

Related skills

Skill Creator

59

ratacat/claude-skills

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Skill & Plugin Authoring10

Skill Installer

59

ratacat/claude-skills

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Software Development10

Agent Browser

59

ratacat/claude-skills

Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".

AI, LLMs & Agents10

API Research

31

daydreamsai/skills-market

Researches and validates live data APIs for a given topic. Finds free/public endpoints that work without authentication. Use when sourcing data APIs before building a paid agent.

Research & Science16

Repo Research Analyst

59

ratacat/claude-skills

Use this agent when you need to conduct thorough research on a repository's structure, documentation, and patterns. This includes analyzing architecture files, examining GitHub issues for patterns, reviewing contribution guidelines, checking for templates, and searching codebases for implementation patterns. The agent excels at gathering comprehensive information about a project's conventions and best practices.\ \ Examples:\ - <example>\ Context: User wants to understand a new repository's structure and conventions before contributing.\ user: "I need to understand how this project is organize

Research & Science10

Hotseat

49

robinebers/skills

Challenge the user's plan by asking one researched question at a time. After every user answer, inspect relevant code/docs/tools before asking the next question. Use when the user wants to think through, sharpen, rethink, or be challenged on a plan or idea.

Research & Science

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.