Production-ready skills for Claude Code CLI - Cloudflare, React, Tailwind v4, and AI integrations
Production-ready skills for Claude Code CLI - Cloudflare, React, Tailwind v4, and AI integrations
145 production-ready skills for Claude Code CLI
Version 3.9.0 | Last Updated: 2026-09-09
A curated collection of battle-tested skills for building modern web applications with Cloudflare, AI integrations, React, Tailwind, and more.
# Add the marketplace
/plugin marketplace add https://github.com/secondsky/claude-skills
# Install individual skills as needed
/plugin install cloudflare-d1@claude-skills
/plugin install tailwind-v4-shadcn@claude-skills
/plugin install gemini-cli@claude-skillsThe authoritative catalog is .claude-plugin/marketplace.json, summarized in the category table below. A human-readable catalog is auto-generated in MARKETPLACE.md.
This repo generates .codex-plugin/ manifests and a .agents/plugins/marketplace.json for all 145 plugins, so Codex CLI can install them natively:
# Add the marketplace (from GitHub)
codex plugin marketplace add secondsky/claude-skills
# Browse and install plugins in the Codex TUI
# /plugins # opens the plugin browser
# Space # enable/disable a pluginSkills are auto-discovered from each plugin's skills/ directory — the same SKILL.md files Claude Code uses. Claude-specific slash commands and subagents are not carried into Codex (use Codex's /import command for that).
skills.sh is an open agent-skills registry and npx skills CLI (maintained by Vercel) that auto-detects your coding agent — Claude Code, Cursor, Codex, Copilot, Cline, opencode, and 70+ others — and installs each skill into the correct directory for that harness. It is the universal cross-harness path for harnesses without a marketplace (opencode, Gemini CLI) or where this repo's manifest format isn't generated yet (Cursor).
…Bulk install note:
npx skills add secondsky/claude-skills --allinstalls every discovered skill at once, but discovery walks skills.sh's standard container directories (skills/,.claude/skills/, …). This repo nests skills underplugins//skills//, so--allmay not pick up everything in one pass — install the skills you need by name with--skill, or runnpx skills add secondsky/claude-skills -lto list what it finds.
skills.sh runs every published skill through three scanners (Gen Agent Trust Hub, Socket, Snyk) plus an LLM-based meta-analyzer, and publishes the results at skills.sh/audits. The LLM analysis stage has been publicly shown (Trail of Bits, June 2026) to both miss genuinely malicious skills and flag unfamiliar version pins (e.g. newest dependency versions) as suspicious false positives. Treat skills.sh warnings as advisory, not authoritative — and verify against this repo's own version pins before acting on a warning.
This repository contains 145 production-tested skills for Claude Code, each focused on a specific technology or capability.
Individual Skills: Each skill is a standalone unit with:
SKILL.md - Core knowledge and guidanceInstallation Options:
/plugin install @claude-skillsnpx skills add secondsky/claude-skills --skill (see Installing with skills.sh)Each skill is individually installable. Install only the skills you need.
Full Catalog: The authoritative list is .claude-plugin/marketplace.json; a human-readable version is generated in MARKETPLACE.md.
| Category | Skills | Examples |
|---|---|---|
| tooling | 27 | turborepo, plan-interview, code-review, tech-debt, humanize-writing |
| frontend | 26 | nuxt-v4, nuxt-v5, tailwind-v4-shadcn, tanstack-query, nuxt-studio, maz-ui, threejs |
| cloudflare | 21 | cloudflare-d1, cloudflare-workers-ai, cloudflare-agents |
| api | 16 | api-design-principles, graphql-implementation |
| ai | 7 | gemini-cli, ml-model-training, tanstack-ai |
| web | 10 | hono-routing, firecrawl-scraper, web-performance |
| security | 6 | csrf-protection, xss-prevention, cybersecurity |
| mobile | 5 | react-native-app, react-native-skills |
| woocommerce | 4 | woocommerce-backend-dev |
| testing | 4 | vitest-testing, playwright-testing |
| design | 4 | design-review, design-system-creation |
| auth | 4 | better-auth |
| architecture | 3 | microservices-patterns, architecture-patterns |
| data | 2 | recommendation-engine, recommendation-system |
| cms | 2 | hugo, wordpress-plugin-core |
| database | 1 | drizzle-orm-d1 |
| seo | 2 | seo-optimizer, seo-keyword-cluster-builder |
| documentation | 1 | technical-specification |
Claude Code automatically checks ~/.claude/skills/ for relevant skills before planning tasks:
User: "Set up a Cloudflare Worker with D1 database"
↓
Claude: [Checks skills automatically]
↓
Claude: "Found cloudflare-d1 skills.
These prevent 12 documented errors. Use them?"
↓
User: "Yes"
↓
Result: Production-ready setup, zero errors, ~65% token savingsNote: Due to token limits, not all skills may be visible at once. See ⚠️ Important: Token Limits below.
Each plugin is a directory under plugins// containing one or more skills:
plugins/[plugin-name]/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest (marketplace metadata)
├── README.md
├── skills/
│ └── [skill-name]/
│ ├── SKILL.md # Core knowledge and guidance
│ ├── templates/ # Ready-to-copy templates
│ ├── scripts/ # Helper utilities
│ └── references/ # Extended documentation
└── (optional) agents/, commands/, hooks/Writing Quality:
Plugin Additions:
Skill Overhauls:
.check(), z.xor, z.file, z.json, new format validators), and added a 12-rule best-practices rulebookOffensive Security (new category):
csrf-protection, xss-prevention, vulnerability-scanning, security-headers-configuration, defense-in-depth-validation) for remediation. Integrates 20 Aradotso dev-security skills across 5 grouped reference docs.Supply Chain Security (cross-cutting):
Full-Stack Frameworks:
Infrastructure:
Plugin Enhancements:
Frontend Expansion:
Developer Workflow:
Mobile Development:
Enhanced Authentication:
Claude Code has a 15,000 character limit for the total size of skill descriptions in the system prompt. This limit also applies to commands and agents.
What this means:
To verify which skills are currently loaded:
# Ask Claude Code directly
"Check what skills/plugins you see in your system prompt"Claude will report something like: "85 of 145 skills visible due to token limits"
You can double the headroom for skill descriptions by setting an environment variable:
# Increase limit to 30,000 characters
export SLASH_COMMAND_TOOL_CHAR_BUDGET=30000
# Then launch Claude Code
claudeThis gives you approximately 2x more skill visibility in the system prompt.
Note: This is a temporary workaround. The Claude Code team is working on better s
No open issues yet, or sync has not completed.