Skip to main content
Claude Skills is a library of structured workflows — called skills — that you invoke with a single slash command in Claude Code. Each skill encodes domain knowledge, step-by-step processes, quality gates, and self-review checklists so Claude handles complex tasks reliably, every time.

Installation

Clone the repo and link skills to your Claude Code config in under two minutes.

Quick Start

Run your first skill and understand how the slash-command system works.

Browse All Skills

Explore 20+ skills across building, research, visualization, and debugging.

Create a Skill

Learn how to build your own skills using harness engineering best practices.

​
What skills solve

Claude Code is powerful out of the box, but complex tasks — scaffolding a Python library, running multi-dimensional research, diagnosing flaky tests — require careful prompting and domain knowledge that gets lost between sessions. You end up re-explaining workflows, catching the same mistakes, and missing the same steps. Skills fix that. Each skill is a directory of markdown files that Claude loads as context when you invoke it. The main SKILL.md defines workflow steps, golden rules, and a self-review checklist. Additional reference files cover specific phases, loaded only when needed.

Building & Shipping

Ship product ideas end-to-end, scaffold Python libraries, initialize GitHub repos with CI/CD, and build board games.

Research & Design

Multi-dimensional research, adversarial design review, gap finding, spec writing, and competitive analysis.

Visualization

Render interactive charts, diagrams, slide decks, tables, and Gantt timelines live in the browser.

Debugging & Quality

Diagnose flaky tests with structured experiments and scan codebases for 24 production readiness items.

​
How it works

1

Install skills

Clone the repository and symlink the skills directory (or individual skills) into ~/.claude/skills/.
2

Invoke a skill

Type a slash command in Claude Code — for example /deep-research or /ship-it. Claude loads the skill’s context automatically.
3

Claude follows the workflow

The skill’s SKILL.md guides Claude through numbered phases, quality gates, and a self-review checklist. No additional prompting needed.
4

Get reliable output

Every skill encodes golden rules and feedback loops so output is consistent across sessions, regardless of context drift.
Skills live in ~/.claude/skills/ and are available in every Claude Code session. You can use the entire library or symlink only the skills you need.