Everything for Claude Code

Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 370,655 indexed, measured the same four ways as everything else here.

code-review

3049

cloudshipai/station

Skill Claude Code

Systematic code review process with focus on quality, security, and best practices.

not rated 430 +1 7mo ago A 18 tokens original Apache-2.0

prism-scan

3050

Cranot/super-hermes

Skill Claude Code

Structural analysis through dynamically generated cognitive lenses. Generates the optimal analytical lens for the specific code/artifact, then executes it. Finds conservation laws, structural invariants, and concrete bugs that vanilla analysis misses. Use on any code file, system design, or text artifact.

not rated 430 +6 1mo ago A SkillSpector: pass 58 tokens original MIT

yushui2022/MathModel-Skill

Skill Claude Code needs its repo

A workflow for choosing mathematical models and shaping a modelling paper around its scoring criteria. It also defines coordination rules for keeping a long modelling task on track.

not rated 430 +46 changed 10d ago A SkillSpector: pass 62 tokens original MIT

tunelo

3052

jiweiyuan/tunelo

Skill Claude CodeCodex

Expose local services and files to the internet through a public HTTPS URL. Designed for AI agents — when you need to let a user preview files remotely, share a dev server, demo an app, or give temporary access to localhost. Use this whenever the user says "share this", "let me see it on my phone", "send me the link"…

not rated 429 +1 1mo ago C 86 tokens

api-debugging

3053

ownpilot/OwnPilot

Skill Claude Code

Systematic approach to debugging REST APIs, HTTP errors, authentication issues, and network problems. Use when the user has API errors, status code issues, timeout problems, or needs help troubleshooting HTTP requests.

not rated 429 5d ago A SkillSpector: pass 44 tokens original MIT

swiftui-expert-skill

3054

AFK-surf/OpenBridge

Skill Claude CodeCodex

Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, modern APIs, Swift concurrency, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.

not rated 429 +1 3mo ago A SkillSpector: pass 68 tokens original MIT

yupi-skill

3055

liyupi/yupi-skill

Skill Claude CodeCodex

A response-style skill that makes the agent answer as 程序员鱼皮, a Chinese programming educator and entrepreneur.

not rated 429 +2 5mo ago A 192 tokens original MIT

godot-mcp

3056

tomyud1/godot-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Godot game engine integration — control the Godot editor with AI. Runs locally from the godot-mcp-server npm package.

not rated 429 +5 21d ago A Socket: warn tokens not measured original MIT

google-ai-edge/litert-samples

Skill Claude CodeCodex

Rapidly migrate an Android application from legacy TensorFlow Lite (TFLite) to modern LiteRT CompiledModel API v2.1.6 in Open Source GitHub repositories. Supports True Async Execution (runAsync), Zero-Copy I/O Buffers, NPU JIT compilation, and automated 2-stage verification self-testing.

not rated 429 +4 3d ago A SkillSpector: pass 76 tokens original Apache-2.0

paper2poster

3058

QuZhan51496/paper2anything

Skill Claude Code

Convert academic papers (PDF) into conference posters (HTML/PNG). You are the conductor: you decide what each section needs — an original paper figure or text — write the outline, hand-author the poster HTML, and iterate on the render using your own visual read and a blind-reader content quiz. Use when the user wants…

not rated 429 +13 2mo ago A SkillSpector: pass 76 tokens original Apache-2.0

subframe

3059

SubframeApp/subframe

Plugin Claude Code

Bundles 3 skills, 2 MCP servers · 205 tokens together

Design and build UIs with Subframe. Create pixel-perfect React + Tailwind pages using your design system, explore design variations, and implement with business logic.

not rated 429 +1 changed 5d ago A tokens not measured

blockbench

3060

jasonjgardner/blockbench-mcp-plugin

MCP server Claude CodeCodexCursor +2

MCP server "blockbench", hosted remotely at localhost, as configured in jasonjgardner/blockbench-mcp-plugin.

not rated 429 +10 today A tokens not measured GPL-3.0

registry-broker

3061

hashgraph-online/registry-broker-skills

Skill Claude CodeCodex

Search and chat with AI agents across the Universal Agentic Registry via the Hashgraph Online Registry Broker API. Use when discovering agents, starting conversations, finding incoming messages, or registering new agents.

not rated 428 +6 13d ago A 42 tokens original Apache-2.0

pentest-playbook

3062

SeaOf0/dsh-redteam-model

Skill Claude CodeCodex

A penetration-testing playbook for examining authorized websites, applications, and services for real, verified security weaknesses.

not rated 428 +103 2d ago A SkillSpector: warn 429 tokens original MIT

daily-report

3063

openvort/openvort

Skill Claude CodeCodex

A workflow for generating a daily work report.

not rated 427 +3 4mo ago A 26 tokens AGPL-3.0

superpowers-lab

3064

obra/superpowers-lab

Plugin Claude Code

Bundles 4 skills · 182 tokens together

Experimental skills for Claude Code Superpowers - new techniques and tools under development.

not rated 427 +4 3mo ago A tokens not measured original MIT

meta-ads-analyzer

3065

mathiaschu/meta-ads-analyzer

Skill Claude CodeCodex

Provides expert-level analysis and diagnosis for Meta Ads campaigns. Use this skill to interpret performance data, identify root causes of issues, and generate actionable recommendations, with a special focus on correctly handling the 'Breakdown Effect'. Use when the user mentions Meta Ads analysis, campaign…

not rated 427 +1 6mo ago A 82 tokens original MIT

metric-reconciliation

3066

nimrodfisher/data-analytics-skills

Skill Claude CodeCodex

Cross-source metric validation and discrepancy investigation. Use when metrics from different sources don't match, investigating data quality issues between systems, or validating data migration accuracy.

not rated 427 +8 4mo ago A 34 tokens

remctl

3067

viticci/remctl

Skill Claude CodeCodex

Use when an agent needs to operate Apple Reminders through RemCTL or diagnose its installation, signed Capability Host, permissions, or agent-runner access on macOS.

not rated 427 +8 changed 9d ago A 36 tokens original MIT

bashunit

3068

TypedDevs/bashunit

Skill Claude CodeCodex needs its repo

Write and run tests for bash scripts with bashunit. Use when adding or fixing tests for shell code, when a bashunit run fails, or when asked to raise coverage of a bash script. Covers loading the code under test, the assertion catalogue, the fast edit-run loop, and the API traps that produce silently-passing tests.

not rated 427 +3 yesterday A 70 tokens original MIT

podcast

3069

zarazhangrui/personalized-podcast

Skill Claude CodeCodex

Generate a podcast episode from content you provide. Paste text, point to local files, or describe a topic. Two AI hosts discuss it in a natural conversation. Listen locally or in your favorite podcast app via RSS.

not rated 426 +3 5mo ago B 46 tokens

earn-hunter

3070

okx/agent-trade-kit

Skill Claude CodeCodex

A monitoring skill for OKX Earn products, which let users put supported cryptocurrency assets into flexible, fixed-term, or short-term earning programmes.

not rated 426 +6 changed 7d ago A SkillSpector: warn 114 tokens original MIT

gpt-image-gen

3071

code-yeongyu/senpi

Skill Claude CodeCodex

MUST read before generating images. Prompt-crafting guide for gpt-image-2.5 covering tool routing (native imagegeneration server tool vs the generateimage tool), model and quality selection, prompt structure, exact text rendering, reference-image editing, transparent assets, output formats, and multi-turn refinement.

not rated 426 +6 changed 3d ago A SkillSpector: pass 66 tokens original MIT

xilinx-suite

3072

QingquanYao/xilinx-skill

Plugin Claude Code

Bundles 1 skill · 399 tokens together

Xilinx full-toolchain assistant covering Vivado, Vitis HLS, Vitis Unified IDE, and PetaLinux -- from HLS algorithm to boot image.

not rated 426 +5 4mo ago A tokens not measured

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: