Deep Research

This is Claude doing actual research before you write code. It scans your local projects for reusable pieces, reads competitor docs and GitHub issues, mines plugin ecosystems to see what users actually need, and compiles it into a research brief. Three depth levels: focused is 30 minutes for one decision, wide is 1-2 hours to understand a product space, deep is 3-6 hours leaving no stone unturned. The insight is that popular plugins reveal what the core product lacks, and 1-star reviews are a map of unmet needs. Use it when you're about to build something new and want to avoid reinventing wheels or missing obvious patterns.

skills.sh installs: 1.2K
GitHub stars: 1.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add jezweb/claude-skills --skill deep-research --agent claude-code

Installs into .claude/skills of the current project.

Files

Deep Research

Comprehensive research and discovery before building something new. Instead of jumping straight into code from training data, this skill goes wide and deep — local exploration, web research, competitor analysis, ecosystem signals, future-casting — and produces a research brief that makes the actual build 10x more productive.

Depth Levels

The difference is scope of ambition, not just time.

Depth	Purpose	Scope
focused	Answer a specific question	One decision: "CodeMirror vs ProseMirror?" — targeted search, local scan, 1-2 comparisons. Produces a 1-page recommendation.
wide	Understand the space	Landscape for a new product or feature. Competitors, ecosystem, user needs, architecture options. Enough to write a spec.
deep	Plan a major build	Leave no stone unturned. Everything in wide PLUS library/component research, plugin ecosystems, GitHub issues mining, community sentiment, future-casting, technical deep-dives on every decision. Enough to drive weeks of coding.

Default: wide