AI Claude Code skills custom commands developer tools GitHub

15 Best Claude Code Skills You Should Install in 2026

The Prompt Shelf ·

Claude Code Skills are custom slash commands that live in your .claude/skills/ directory. They turn multi-step workflows into one-line commands. Think of them as plugins that make Claude an expert in a specific domain.

The Skills ecosystem exploded in early 2026. There are now thousands of skills across GitHub, and separating the genuinely useful from the noise is hard. This list is the result of analyzing star counts, actual usage patterns, and community feedback across 200+ repositories.

Every skill listed here is open-source, free, and installable in under a minute.

How to Install a Skill

# Clone the skill into your project's .claude/skills/ directory
git clone https://github.com/user/skill-name .claude/skills/skill-name

# Or copy just the SKILL.md file
curl -o .claude/skills/skill-name/SKILL.md https://raw.githubusercontent.com/user/skill-name/main/SKILL.md

Claude Code automatically discovers skills in .claude/skills/ and makes them available as slash commands.

The Must-Install List

1. Impeccable — Design Audit & Polish

GitHub: pbakaus/impeccable · 10,000+ stars

Created by Paul Bakaus (former Google engineer), Impeccable is the gold standard for frontend design skills. One skill file, 20 commands, and seven deep reference guides covering typography, color, spatial design, motion, interaction, responsive layout, and UX writing.

Key commands:

  • /audit — Scan your UI for design problems
  • /arrange — Fix spacing and layout issues
  • /typeset — Apply proper typography hierarchy
  • /polish — Final design pass for production readiness

Works with Claude Code, Cursor, Gemini CLI, and Codex CLI. If you build any kind of frontend, this is the first skill to install.

2. Planning With Files — Persistent Task Management

GitHub: OthmanAdi/planning-with-files · 17,700+ stars

The most starred individual skill on GitHub. Implements Manus-style persistent markdown planning, using the filesystem as “disk” (persistent memory) versus the context window as “RAM” (volatile).

Creates task_plan.md, progress.md, and findings.md as working memory that survives across sessions. Compatible with 40+ agents supporting the Agent Skills spec.

If your Claude Code sessions frequently crash or you work on multi-day tasks, this skill prevents you from losing progress.

3. Humanizer — Remove AI Writing Patterns

GitHub: blader/humanizer · 11,700+ stars

Based on Wikipedia’s “Signs of AI writing” guide, Humanizer detects and removes 20+ patterns that make text obviously AI-generated: inflated symbolism, em dash overuse, rule of three, AI vocabulary (“delve,” “tapestry,” “landscape”), and negative parallelisms.

Does a second audit pass specifically looking for “obviously AI-generated” markers. Essential if you use Claude to write documentation, blog posts, or marketing copy.

4. Understand-Anything — Codebase Knowledge Graphs

GitHub: Lum1104/Understand-Anything · 7,200+ stars

Turns any codebase into an interactive knowledge graph. A multi-agent pipeline scans your project, extracts every file, function, class, and dependency, builds a knowledge graph, and opens an interactive web dashboard with color-coded architectural layers.

Key commands:

  • /understand-diff — Visualize what changed
  • /understand-explain — Get architectural explanations
  • /understand-chat — Ask questions about the codebase

Perfect for onboarding onto unfamiliar codebases.

5. Dev Browser — Give Claude a Web Browser

GitHub: SawyerHood/dev-browser · 5,100+ stars

Gives Claude the ability to use a real web browser with cookies, localStorage, and page state that persist between executions. Uses ARIA-based element discovery with semantic snapshots.

Claude autonomously decides when to use the browser — for testing deployed features, verifying API responses, or checking how a page renders. Turns Claude from a code-only assistant into one that can see and interact with your running application.

6. Trail of Bits Security Skills

GitHub: trailofbits/skills · 4,100+ stars

From one of the most respected security research firms. Includes CodeQL and Semgrep static analysis, Semgrep rule creation, smart contract entry-point analysis, variant analysis, audit context building, and security-focused differential review.

If you write code that handles money, auth, or sensitive data, these skills turn Claude into a security auditor that catches vulnerabilities before they ship.

7. Playwright Skill — Browser Automation

GitHub: lackeyjb/playwright-skill · 2,250+ stars

Claude autonomously writes and executes Playwright tests and automation. v4.0 includes auto-detection that scans common dev server ports (3000, 5173, 8080) and smart test management.

Different from Dev Browser in that this focuses on automated testing workflows rather than interactive browsing.

8. Godogen — Build Godot Games From Text

GitHub: htdt/godogen · 2,400+ stars

The most impressive domain-specific skill. Builds complete Godot 4 game projects from a text description. The AI pipeline handles architecture planning, 2D/3D asset generation (via Gemini and Tripo3D), GDScript writing, and visual QA by capturing screenshots from the running engine.

Includes a custom language spec and quirks database for GDScript, which is critical because GDScript has enough differences from Python that generic AI coding produces broken code.

9. Context Engineering Kit

GitHub: NeoLabHQ/context-engineering-kit · 730+ stars

Hand-crafted context engineering techniques with minimal token footprint. Includes Spec-Driven Development (turns prompts into production-ready implementations through structured planning), domain-driven design patterns, and subagent-driven development.

Tested on real production projects with a claimed 100% working code success rate. The techniques are transferable — even if you do not use this specific skill, the patterns it teaches are worth studying.

10. Learning Opportunities — Deliberate Skill Development

GitHub: DrCatHicks/learning-opportunities · 720+ stars

The most unusual skill on this list. After you complete architectural work (new files, schema changes, refactors), Claude offers optional 10-15 minute learning exercises based on cognitive psychology research: prediction, generation, retrieval practice, and spaced repetition.

The idea is that AI-assisted coding can make you a worse programmer if you never engage with the “why.” This skill fights that by turning every coding session into a learning session.

11. Sahil Lavingia’s Entrepreneur Skills

GitHub: slavingia/skills · 5,700+ stars

From the CEO of Gumroad. Claude Code skills based on “The Minimalist Entrepreneur” methodology. Includes /validate-idea, /find-community, /first-customers, and /company-values.

Not a coding skill — it turns Claude into a business advisor. Interesting proof that Skills are not limited to technical workflows.

12. Claude Sessions — Session Tracking

GitHub: iannuttall/claude-sessions · 1,178 stars

Custom slash commands for comprehensive development session tracking and documentation. Solves the problem of losing context between Claude Code sessions by maintaining structured logs of what was done, what was decided, and what needs to happen next.

13. Second Brain Skills

GitHub: coleam00/second-brain-skills · 575 stars

Turns Claude Code into a “Second Brain” with three core capabilities: Brand System (define your voice and brand once, reuse everywhere), MCP Client Integration (progressive disclosure of tool capabilities), and Remotion skill for programmatic video creation.

14. Prompt Master — AI Prompt Writing

GitHub: nidhinjs/prompt-master · 4,000+ stars

Meta-skill: Claude writes optimized prompts for other AI tools. Zero wasted tokens or credits through full context and memory retention. Useful when you are building AI-powered features and need to craft prompts for production use.

15. Anything to NotebookLM

GitHub: joeseesun/anything-to-notebooklm · 642 stars

Multi-source content processor. Converts web pages, YouTube videos, PDFs, Markdown, and search queries into Podcasts, presentations, mind maps, and quizzes via NotebookLM integration.

Awesome Lists for Discovery

If you want to explore beyond this list:

What Makes a Good Skill

After reviewing hundreds of skills, the pattern is clear:

  1. Focused scope. One skill does one thing well. Impeccable does design. Trail of Bits does security. Mixing concerns produces mediocre results.
  2. Runnable examples. Skills that include example commands and expected outputs get adopted faster.
  3. Under 200 lines. The best skills are concise. If your SKILL.md is 500+ lines, Claude will deprioritize later sections.
  4. Domain knowledge baked in. The value of a skill is the expertise it encodes. Godogen’s GDScript quirks database is more valuable than the automation around it.

Further Reading

More from the blog

Explore the collection

Browse all AI coding rules — CLAUDE.md, .cursorrules, AGENTS.md, and more.

Browse Rules