Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 388,304 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Upload images to img402.dev for embedding in GitHub PRs, issues, and comments. Images 1MB or under are free AND permanent — no payment, no auth — which covers virtually every screenshot. Larger images (up to 10MB) are free for 30 days, or permanent for $0.01 USDC via x402. Use when the agent needs to share an image in…
Plugin Claude Code
Bundles 31 skills, 7 agents · 1,868 tokens together
Personal skills, commands, and workflows for Claude Code.
Skill Claude CodeCodex
Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
Skill Claude CodeCodex
An automated testing setup for web applications that uses Playwright to control a real browser and checks complete user journeys with the live backend.
Skill Claude Code
Structured git workflow with Conventional Commits standard. Covers commit formatting, PR creation via gh CLI, merge conflict resolution, advanced git operations (cherry-pick, bisect, worktrees), repository archaeology, and branch cleanup.
Plugin Claude Code
Bundles 9 skills · 1,350 tokens together
Oxy platform skills for coding agents: custom apps and Oxy Functions, semantic models, agents, automations, Airway pipelines, evals, and the oxyc CLI.
Skill Claude CodeCodex
Run a comprehensive code audit on any codebase. Analyzes security vulnerabilities, hardcoded secrets, dependency CVEs, test coverage, code structure, and AI-generated code patterns. Generates CODEAUDITREPORT.md with findings, severity ratings, and remediation guidance. Intelligently selects and orchestrates the best…
Skill Claude Code
Create, refactor, evaluate, and package agent skills. USE FOR: "create a skill", "turn this workflow into a skill", "improve my skill", "add evals", "package for reuse". DO NOT USE FOR: one-off answers, brainstorming without reuse, translation, documentation without agent execution.
mehdiozdemir/awesome-agent-skills
Skill Claude CodeCodex needs its repo
Generates comprehensive test suites for code including unit tests, integration tests, and end-to-end tests. Use when creating tests for functions, classes, APIs, or entire modules, covering edge cases, error conditions, and ensuring high code coverage.
Skill Claude CodeCodex
Controls response length and pacing in all conversations. Use this skill in EVERY chat by default. It keeps replies short, bans preamble and recap, and forces one-thing-at-a-time collaboration instead of dumping full plans. Especially important during new-project brainstorming, where the natural failure mode is…
Skill Claude Code
Run a Claude–Codex adversarial review of a plan or code change. Use only when the user explicitly asks for a debate, cross-review, or second opinion; every round spends a paid turn on the other provider.
Skill Claude CodeCodex
A session-saving workflow that records the current work in a readable Markdown snapshot so it can be resumed later in a new session.
Plugin Claude Code
Bundles 14 skills, 1 MCP server · 896 tokens together
Create product photos, virtual try-on images, fashion lookbooks, professional headshots from photos, and videos with Astria. Reuse people and product references across scenes or run saved photoshoot templates.
Skill Claude Code
Run the 4CO-OP multi-stage coding pipeline for a feature request, including the nightly monitor window and performance logging.
Plugin Claude Code
Bundles 3 skills · 442 tokens together
Phrase-specific agent skills.
Plugin Claude Code
Bundles 1 skill · 91 tokens together
Generate a complete, cross-platform .devcontainer setup for any project: host git/Claude Code/Codex credentials mounted in and ready to go, mise as tool-version manager and task runner, language-tailored toolchains and caches, a doctor check/repair command, Anthropic cloud (claude.ai/code) bootstrap, and graceful…
Skill Claude CodeCodex
A tool for generating and updating `llms.txt`, a website file that summarizes content for language models, from Qiniu Cloud's official website.
Skill Claude Code
Scaffolds a new Express.js REST API application with TypeScript, structured routing, middleware, and error handling. Guides through project creation, configuration, and initial setup. Use when the user wants to create, start, or scaffold a new Express server, API, or backend project.
Plugin Claude Code
Bundles 2 skills · 209 tokens together
Custom agent skills: diverge (brainstorming partner) and vervlaamser (Flemish humanizer for Dutch text).
Skill Claude CodeCodex
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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Plugin Claude Code
Bundles 2 skills · 387 tokens together
Coding agent skills for instrumenting, tracing and testing agents with Monocle. Instrument a Python agentic app, verify the traces against a good-trace rubric, and auto-create the instrumentation when it's missing or incomplete.
Skill Claude CodeCodex
Generates a portable, single-file HTML artifact from free-form planning output. Takes any input — issue body, RFC, spike summary, grilling transcript, inline content, file path, Google Doc content, or braindump — and produces either a static report or an animated slideshow, both styled with Elastic's EUI Borealis…
Skill Claude Code
A setup guide for starting a Go project in the current directory. Go is a compiled programming language, and the guide checks existing source files and project configuration before continuing.
Skill Claude CodeCodex
Use when implementation work should be handed to cheap delegate agents instead of typed by hand — a groomed ticket, a story with separate frontend and backend sides, a mechanical sweep across many files, a DB or localization change — or when the user invokes /coordinate. Also use when a delegate agent has reported…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: