claudekit-skills Documentation

Technical Documentation: mrgoonie/claudekit-skills

ℹ️ Provenance: Multi-Tier Ingestion · CodeWiki Reference

Overview (`README.md`)

ClaudeKit - Agent Skills

Agent Skills are specialized workflows that empower Claude to perform complex, multi-step tasks with precision and reliability. They combine mission briefs, guardrails, and integration hints to transform generic AI assistance into disciplined automation.

Learn more about Agent Skills: https://docs.claude.com/en/docs/agents-and-tools/agent-skills/overview

My other projects

🎉 NEW [Dec 2025]: Claude Code Marketplace!

ClaudeKit Skills is now available as a Plugin Marketplace for seamless installation and automatic updates!

bash

/plugin marketplace add mrgoonie/claudekit-skills
/plugin install ai-ml-tools@claudekit-skills

No more manual git clones! Install and update skills with simple commands. See Getting Started for full installation guide.

Update [Nov 2025]: No more context bloat with "mcp-manager" subagent + "mcp-management" skills!

📖 Read more here: MCP_MANAGEMENT.md

✨ Skills just got refactored!

📖 Read more here: REFACTOR.md

Skills catalog

🔐 Authentication & Security

better-auth - Comprehensive TypeScript authentication framework supporting email/password, OAuth, 2FA, passkeys, and multi-tenancy. Works with any framework (Next.js, Nuxt, SvelteKit, etc.).

🤖 AI & Agent Development

context-engineering - Master context engineering for AI agent systems. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, or building multi-agent coordination.
google-adk-python - Google's Agent Development Kit (ADK) for building AI agents with tool integration, multi-agent orchestration, workflow patterns (sequential, parallel, loop), and deployment to Vertex AI or custom infrastructure.

💻 Backend Development

backend-development - Build robust backend systems with modern technologies (Node.js, Python, Go, Rust), frameworks (NestJS, FastAPI, Django), databases (PostgreSQL, MongoDB, Redis), APIs (REST, GraphQL, gRPC), authentication (OAuth 2.1, JWT), testing strategies, security best practices (OWASP Top 10), performance optimization, scalability patterns (microservices, caching, sharding), DevOps practices (Docker, Kubernetes, CI/CD), and monitoring. Use when designing APIs, implementing authentication, optimizing database queries, setting up CI/CD pipelines, handling security vulnerabilities, building microservices, or developing production-ready backend systems.

🧠 AI & Machine Learning

ai-multimodal - Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio (transcription, summarization up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A), process videos (scene detection, Q&A, temporal analysis, YouTube URLs up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams), generate images (text-to-image, editing, composition). Supports Gemini 2.5/2.0 with context windows up to 2M tokens.
context-engineering - Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, or evaluating agent performance. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, and memory architectures.

🎨 Design & Aesthetics

aesthetic - Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing designs from inspiration sites, generating design images with ai-multimodal, implementing visual hierarchy and color theory, adding micro-interactions, or creating design documentation. Includes workflows for capturing and analyzing inspiration screenshots with chrome-devtools and ai-multimodal, iterative design image generation until aesthetic standards are met, and comprehensive design system guidance covering BEAUTIFUL (aesthetic principles), RIGHT (functionality/accessibility), SATISFYING (micro-interactions), and PEAK (storytelling) stages.

🌐 Web Development

web-frameworks - Build modern full-stack web applications with Next.js (App Router, Server Components, RSC, PPR, SSR, SSG, ISR), Turborepo (monorepo management, task pipelines, remote caching, parallel execution), and RemixIcon (3100+ SVG icons). Create React applications, implement server-side rendering, set up monorepos, optimize build performance, manage shared dependencies.
ui-styling - Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Build design systems, create responsive layouts, add accessible components, customize themes, implement dark mode, generate visual designs and posters.
frontend-design - Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
frontend-development - Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code.
threejs - Build 3D web apps with Three.js (WebGL/WebGPU). Use for 3D scenes, animations, custom shaders, PBR materials, VR/XR experiences, games, data visualizations, product configurators. Includes asset loading (GLTF, FBX, OBJ), post-processing effects, physics simulations, and performance optimization.

🌐 Browser Automation & Testing

chrome-devtools - Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Automate browsers, take screenshots, analyze performance, monitor network traffic, web scraping, and form automation.
web-testing - Comprehensive web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/accessibility testing. Use for test automation, flakiness mitigation, Core Web Vitals, mobile gestures, cross-browser testing.

☁️ Cloud Platforms & DevOps

bunny - Integrate with Bunny.net's cloud platform: CDN (Pull Zones, Edge Rules, Cache), Edge Storage (HTTP/FTP, SDKs), Stream (video upload/encode/DRM), DNS (Zones, DNSSEC, Scriptable DNS), Edge Scripting (JS/TS at the edge), Shield (WAF, DDoS, Rate Limiting), Magic Containers (deploy/autoscale), Optimizer (dynamic images), Database (distributed SQLite), and AI Image Generation. Includes Terraform provider and token authentication.
devops - Deploy and manage cloud infrastructure on Cloudflare (Workers, R2, D1, KV, Pages, Durable Objects, Browser Rendering), Docker containers, and Google Cloud Platform (Compute Engine, GKE, Cloud Run, App Engine, Cloud Storage). Deploy serverless functions to the edge, configure edge computing solutions, manage containers, set up CI/CD pipelines, optimize cloud infrastructure costs.

🗄️ Databases

databases - Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin). Design database schemas, write queries and aggregations, optimize indexes, perform migrations, configure replication and sharding, implement backup and restore strategies.

🛠️ Development Tools

claude-code - Complete guide to Claude Code features: slash commands, hooks, plugins, MCP servers, agent skills, IDE integration, and enterprise deployment.
mcp-builder - Build high-quality MCP servers in Python (FastMCP) or TypeScript. Includes agent-centric design principles, evaluation harnesses, and best practices.
mcp-management - Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
repomix - Package entire repositories into single AI-friendly files (XML, Markdown, JSON). Perfect for codebase analysis, security audits, and LLM context generation.
media-processing - Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration) and ImageMagick (image manipulation, format conversion, batch processing, effects, composition). Supports 100+ formats, hardware acceleration (NVENC, QSV), and complex filtergraphs.

📚 Documentation & Research

docs-seeker - Intelligent documentation discovery using llms.txt standard, GitHub repository analysis via Repomix, and parallel exploration agents for comprehensive coverage.

🧪 Code Quality & Review

code-review - Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.

🐛 Debugging & Quality

debugging/defense-in-depth - Validate at every layer data passes through. Make bugs structurally impossible with entry validation, business logic checks, environment guards, and debug logging.
debugging/root-cause-tracing - Trace bugs backward through the call stack to find original triggers. Fix at the source, not the symptom.
debugging/systematic-debugging - Four-phase framework ensuring root cause investigation before fixes. Never jump to solutions.
debugging/verification-before-completion - Run verification commands and confirm output before claiming success. Evidence before claims, always.

📄 Document Processing

document-skills/docx - Create, edit, and analyze Word documents with tracked changes, comments, formatting preservation, and redlining workflows for professional documents.
document-skills/pdf - Extract text/tables, create PDFs, merge/split documents, fill forms. Uses pypdf and command-line tools for programmatic PDF processing.
document-skills/pptx - Create and edit PowerPoint presentations with layouts, speaker notes, comments, animations, and design elements.
document-skills/xlsx - Build spreadsheets with formulas, formatting, data analysis, and visualization. Includes financial modeling standards and zero-error formula requirements.

🛍️ E-commerce & Platforms

shopify - Build Shopify apps, extensions, and themes using GraphQL/REST APIs, Shopify CLI, Polaris UI. Includes checkout extensions, admin customization, Liquid templating, and Shopify Functions.

💳 Payments & Billing

payment-integration - Comprehensive payment integration for SePay (Vietnamese VietQR/bank transfers), Polar (SaaS monetization with MoR), Stripe (global payments), Paddle (MoR subscriptions), and Creem.io (software licensing). Includes webhook verification, checkout helpers, subscription management, and usage-based billing.

🧠 Problem-Solving Frameworks

problem-solving/collision-zone-thinking - Force unrelated concepts together to discover emergent properties. "What if we treated X like Y?"
problem-solving/inversion-exercise - Flip core assumptions to reveal hidden constraints and alternative approaches. "What if the opposite were true?"
problem-solving/meta-pattern-recognition - Spot patterns appearing in 3+ domains to find universal principles worth extracting.
problem-solving/scale-game - Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales.
problem-solving/simplification-cascades - Find one insight that eliminates multiple components. "If this is true, we don't need X, Y, or Z."
problem-solving/when-stuck - Dispatch to the right problem-solving technique based on your specific type of stuck-ness.

🧠 Advanced Reasoning

sequential-thinking - Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.

📊 Visualization & Diagramming

mermaidjs-v11 - Create diagrams and visualizations using Mermaid.js v11 syntax. Generate flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, user journeys, timelines, architecture diagrams, or any of 24+ diagram types. Supports JavaScript API integration, CLI rendering to SVG/PNG/PDF, theming, configuration, and accessibility features. Essential for documentation, technical diagrams, project planning, system architecture, and visual communication.

🔧 Meta Skills (from Anthropic)

skill-creator - Guide for creating effective skills with specialized workflows, tool integrations, domain expertise, and bundled resources.

Getting started

🚀 Marketplace Installation (Recommended)

ClaudeKit Skills is now available as a Claude Code Plugin Marketplace for seamless installation and automatic updates!

bash

# Add marketplace
/plugin marketplace add mrgoonie/claudekit-skills

# Install plugins you need
/plugin install ai-ml-tools@claudekit-skills
/plugin install web-dev-tools@claudekit-skills
/plugin install devops-tools@claudekit-skills
# ... and more!

Available Plugin Categories:

ai-ml-tools - AI and ML with Gemini API, context engineering
web-dev-tools - React, Next.js, Tailwind CSS
devops-tools - Cloudflare, Docker, GCP, Databases
backend-tools - Node.js, Python, Go, Authentication
document-processing - Word, PDF, PowerPoint, Excel
debugging-tools - Systematic debugging frameworks
problem-solving-tools - Advanced thinking techniques
platform-tools - Bunny.net, Shopify, payments (SePay, Polar, Stripe, Paddle, Creem), MCP management
meta-tools - Skill creation, code review
media-tools - FFmpeg, ImageMagick
research-tools - Documentation discovery
specialized-tools - Sequential thinking, diagrams

📖 Full installation guide: docs/MARKETPLACE.md

📦 Manual Installation (Legacy)

For users who prefer manual installation:

bash

git clone https://github.com/mrgoonie/claudekit-skills
cp -r claudekit-skills/.claude/* /path/to/your/project/.claude/

Note: Manual installation is deprecated. Marketplace installation is recommended for automatic updates and version management.

🎯 Usage

Select Skills: After installation, Claude Code will automatically discover available skills
Activate: Skills are activated based on your task context
Customize: Edit skill instructions to match your processes and tools
Execute: Claude follows the skill's playbook while you supervise the diffs

Star History

Extend beyond the free tier

This collection covers the essentials. If you need advanced regulated-industry skills, analytics dashboards, or tailored onboarding, explore the full ClaudeKit package at ClaudeKit.cc. The commercial bundle stays subtle but unlocks deeper automation while keeping the same transparent workflow philosophy.

I've been spending 6+ months to dig into every aspect of Claude Code so you don't have to.

I've basically been sharing everything I learned about Claude Code on Substack: https://faafospecialist.substack.com/

So if you find this collection useful, please consider supporting my product at ClaudeKit.cc.

Thanks for your support! 🥰

Overview (`.claude/skills/README.md`)

Skills

Skills are folders of instructions, scripts, and resources that Claude loads dynamically to improve performance on specialized tasks. Skills teach Claude how to complete specific tasks in a repeatable way, whether that's creating documents with your company's brand guidelines, analyzing data using your organization's specific workflows, or automating personal tasks.

For more information, check out:

About This Repository

This repository contains example skills that demonstrate what's possible with Claude's skills system. These examples range from creative applications (art, music, design) to technical tasks (testing web apps, MCP server generation) to enterprise workflows (communications, branding, etc.).

Each skill is self-contained in its own directory with a SKILL.md file containing the instructions and metadata that Claude uses. Browse through these examples to get inspiration for your own skills or to understand different patterns and approaches.

The example skills in this repo are open source (Apache 2.0). We've also included the document creation & editing skills that power Claude's document capabilities under the hood in the document-skills/ folder. These are source-available, not open source, but we wanted to share these with developers as a reference for more complex skills that are actively used in a production AI application.

Note: These are reference examples for inspiration and learning. They showcase general-purpose capabilities rather than organization-specific workflows or sensitive content.

Disclaimer

These skills are provided for demonstration and educational purposes only. While some of these capabilities may be available in Claude, the implementations and behaviors you receive from Claude may differ from what is shown in these examples. These examples are meant to illustrate patterns and possibilities. Always test skills thoroughly in your own environment before relying on them for critical tasks.

Example Skills

This repository includes a diverse collection of example skills demonstrating different capabilities:

Creative & Design

algorithmic-art - Create generative art using p5.js with seeded randomness, flow fields, and particle systems
canvas-design - Design beautiful visual art in .png and .pdf formats using design philosophies
slack-gif-creator - Create animated GIFs optimized for Slack's size constraints

Development & Technical

artifacts-builder - Build complex claude.ai HTML artifacts using React, Tailwind CSS, and shadcn/ui components
mcp-server - Guide for creating high-quality MCP servers to integrate external APIs and services
webapp-testing - Test local web applications using Playwright for UI verification and debugging

Enterprise & Communication

brand-guidelines - Apply Anthropic's official brand colors and typography to artifacts
internal-comms - Write internal communications like status reports, newsletters, and FAQs
theme-factory - Style artifacts with 10 pre-set professional themes or generate custom themes on-the-fly

Meta Skills

skill-creator - Guide for creating effective skills that extend Claude's capabilities
template-skill - A basic template to use as a starting point for new skills

Document Skills

The document-skills/ subdirectory contains skills that Anthropic developed to help Claude create various document file formats. These skills demonstrate advanced patterns for working with complex file formats and binary data:

docx - Create, edit, and analyze Word documents with support for tracked changes, comments, formatting preservation, and text extraction
pdf - Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms
pptx - Create, edit, and analyze PowerPoint presentations with support for layouts, templates, charts, and automated slide generation
xlsx - Create, edit, and analyze Excel spreadsheets with support for formulas, formatting, data analysis, and visualization

Important Disclaimer: These document skills are point-in-time snapshots and are not actively maintained or updated. Versions of these skills ship pre-included with Claude. They are primarily intended as reference examples to illustrate how Anthropic approaches developing more complex skills that work with binary file formats and document structures.

Try in Claude Code, Claude.ai, and the API

Claude Code

You can register this repository as a Claude Code Plugin marketplace by running the following command in Claude Code:

text

/plugin marketplace add anthropics/skills

After installing the plugin, you can use the skill by just mentioning it. For instance, if you install the document-skills plugin from the marketplace, you can ask Claude Code to do something like: "use the pdf skill to extract the form fields from path/to/some-file.pdf"

Claude.ai

These example skills are all already available to paid plans in Claude.ai.

To use any skill from this repository or upload custom skills, follow the instructions in Using skills in Claude.

Claude API

You can use Anthropic's pre-built skills, and upload custom skills, via the Claude API. See the Skills API Quickstart for more.

Creating a Basic Skill

Skills are simple to create - just a folder with a SKILL.md file containing YAML frontmatter and instructions. You can use the template-skill in this repository as a starting point:

markdown

---
name: my-skill-name
description: A clear description of what this skill does and when to use it
---

# My Skill Name

[Add your instructions here that Claude will follow when this skill is active]

## Examples
- Example usage 1
- Example usage 2

## Guidelines
- Guideline 1
- Guideline 2

The frontmatter requires only two fields:

name - A unique identifier for your skill (lowercase, hyphens for spaces)
description - A complete description of what the skill does and when to use it

The markdown content below contains the instructions, examples, and guidelines that Claude will follow. For more details, see How to create custom skills.

Partner Skills

Skills are a great way to teach Claude how to get better at using specific pieces of software. As we see awesome example skills from partners, we may highlight some of them here:

Notion - Notion Skills for Claude

Overview (`.claude/skills/common/README.md`)

Common Skill Utilities

This directory contains shared utilities used across multiple skills.

API Key Helper

api_key_helper.py provides standardized configuration for all Gemini-based skills, supporting both Google AI Studio and Vertex AI endpoints.

Usage in Skills

python

import sys
from pathlib import Path

# Add common directory to path
common_dir = Path(__file__).parent.parent.parent / 'common'
sys.path.insert(0, str(common_dir))

from api_key_helper import get_api_key_or_exit

# Get API key with automatic error handling
api_key = get_api_key_or_exit()

API Key Lookup Order

The helper checks for GEMINI_API_KEY in this order:

Process environment variable (recommended for development)
bash
```
export GEMINI_API_KEY='your-api-key'
```

Project root .env file

bash

echo 'GEMINI_API_KEY=your-api-key' > .env

.claude/.env file

bash

echo 'GEMINI_API_KEY=your-api-key' > .claude/.env

.claude/skills/.env file (shared across all Gemini skills)
bash
```
echo 'GEMINI_API_KEY=your-api-key' > .claude/skills/.env
```

Skill directory .env file

bash

echo 'GEMINI_API_KEY=your-api-key' > .claude/skills/your-skill/.env

Vertex AI Support

To use Vertex AI instead of Google AI Studio:

bash

# Enable Vertex AI
export GEMINI_USE_VERTEX=true
export VERTEX_PROJECT_ID=your-gcp-project-id
export VERTEX_LOCATION=us-central1  # Optional, defaults to us-central1

Or in .env file:

text

GEMINI_USE_VERTEX=true
VERTEX_PROJECT_ID=your-gcp-project-id
VERTEX_LOCATION=us-central1

Using get_client() Helper

For automatic client selection (AI Studio or Vertex AI):

python

from api_key_helper import get_client

# Get appropriate client based on configuration
client_info = get_client()

if client_info['type'] == 'vertex':
    # Using Vertex AI
    from vertexai.generative_models import GenerativeModel
    model = GenerativeModel('gemini-2.5-flash')
    response = model.generate_content("Hello")
else:
    # Using AI Studio
    client = client_info['client']
    response = client.models.generate_content(
        model='gemini-2.5-flash',
        contents="Hello"
    )

Using get_vertex_config() Helper

For checking Vertex AI configuration:

python

from api_key_helper import get_vertex_config

vertex_config = get_vertex_config()
if vertex_config['use_vertex']:
    print(f"Using Vertex AI")
    print(f"Project: {vertex_config['project_id']}")
    print(f"Location: {vertex_config['location']}")

Error Handling

If the API key is not found, the helper will:

Print a clear error message
Show all available methods to set the API key
Provide the URL to obtain an API key
Exit with status code 1

For Vertex AI, if VERTEX_PROJECT_ID is missing when GEMINI_USE_VERTEX=true, the helper will provide clear instructions.

This ensures users get immediate, actionable feedback when configuration is missing.

Overview (`.claude/skills/mcp-management/README.md`)

MCP Management Skill

Intelligent management and execution of Model Context Protocol (MCP) servers.

Overview

This skill enables Claude to discover, analyze, and execute MCP server capabilities without polluting the main context window. Perfect for context-efficient MCP integration using subagent-based architecture.

Features

Multi-Server Management: Connect to multiple MCP servers from single config
Intelligent Tool Discovery: Analyze which tools are relevant for specific tasks
Progressive Disclosure: Load only necessary tool definitions
Execution Engine: Call MCP tools with proper parameter handling
Context Efficiency: Delegate MCP operations to mcp-manager subagent

Quick Start

1. Install Dependencies

bash

cd .claude/skills/mcp-management/scripts
npm install

2. Configure MCP Servers

Create .claude/.mcp.json:

json

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-memory"]
    },
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/allowed/path"]
    }
  }
}

See .claude/.mcp.json.example for more examples.

3. Test Connection

bash

cd .claude/skills/mcp-management/scripts
npm run list-tools
# Or directly:
npx tsx cli.ts list-tools

Note: The CLI automatically looks for config at ~/.claude/.mcp.json. You can run it from any directory.

Usage Patterns

Pattern 1: Discover Available Tools

bash

cd .claude/skills/mcp-management/scripts
npm run list-tools
npm run list-prompts
npm run list-resources
# Or directly:
npx tsx cli.ts list-tools
npx tsx cli.ts list-prompts
npx tsx cli.ts list-resources

Pattern 2: LLM-Driven Tool Selection

The LLM reads assets/tools.json and intelligently selects tools. No separate analysis command needed - the LLM's understanding of context and intent is superior to keyword matching.

Pattern 3: Execute MCP Tools

bash

npx tsx cli.ts call-tool memory add '{"key":"name","value":"Alice"}'

Pattern 4: Use with Subagent

In main Claude conversation:

text

User: "I need to search the web and save results"
Main Agent: [Spawns mcp-manager subagent]
mcp-manager: Discovers brave-search + memory tools, reports back
Main Agent: Uses recommended tools for implementation

Architecture

text

Main Agent (Claude)
    ↓ (delegates MCP tasks)
mcp-manager Subagent
    ↓ (uses skill)
mcp-management Skill
    ↓ (connects via)
MCP Servers (memory, filesystem, etc.)

Benefits:

Main agent context stays clean
MCP discovery happens in isolated subagent context
Only relevant tool definitions loaded when needed
Reduced token usage

File Structure

text

mcp-management/
├── SKILL.md                    # Skill definition
├── README.md                   # This file
├── scripts/
│   ├── mcp-client.ts          # Core MCP client manager
│   ├── analyze-tools.ts       # Intelligent tool selection
│   ├── cli.ts                 # Command-line interface
│   ├── package.json           # Dependencies
│   ├── tsconfig.json          # TypeScript config
│   └── .env.example           # Environment template
└── references/
    ├── mcp-protocol.md        # MCP protocol reference
    └── configuration.md       # Config guide

Scripts Reference

mcp-client.ts

Core client manager class:

Load config from .claude/.mcp.json
Connect to multiple MCP servers
List/execute tools, prompts, resources
Lifecycle management

cli.ts

Command-line interface:

list-tools - Show all tools and save to assets/tools.json
list-prompts - Show all prompts
list-resources - Show all resources
call-tool <server> <tool> <json> - Execute tool

Note: Tool analysis is performed by the LLM reading assets/tools.json, which provides better context understanding than algorithmic matching.

Configuration

Environment Variables

Scripts check for variables in this order:

process.env (runtime)
.claude/skills/mcp-management/.env
.claude/skills/.env
.claude/.env

MCP Config Format

json

{
  "mcpServers": {
    "server-name": {
      "command": "executable",          // Required
      "args": ["arg1", "arg2"],        // Required
      "env": {                          // Optional
        "VAR": "value",
        "API_KEY": "${ENV_VAR}"        // Reference env vars
      }
    }
  }
}

Common MCP Servers

Install with npx:

@modelcontextprotocol/server-memory - Key-value storage
@modelcontextprotocol/server-filesystem - File operations
@modelcontextprotocol/server-brave-search - Web search
@modelcontextprotocol/server-puppeteer - Browser automation
@modelcontextprotocol/server-fetch - HTTP requests

Integration with mcp-manager Agent

The mcp-manager agent (.claude/agents/mcp-manager.md) uses this skill to:

Discover: Connect to MCP servers, list capabilities
Analyze: Filter relevant tools for tasks
Execute: Call MCP tools on behalf of main agent
Report: Send concise results back to main agent

This architecture keeps main context clean and enables efficient MCP integration.

Troubleshooting

"Config not found"

Ensure .claude/.mcp.json exists and is valid JSON.

"Server connection failed"

Check:

Server command is installed (npx packages installed?)
Server args are correct
Environment variables are set

"Tool not found"

List available tools first:

bash

cd .claude/skills/mcp-management/scripts
npm run list-tools

Resources

License

MIT

Overview (`.claude/skills/payment-integration/README.md`)

Payment Integration Skill

Comprehensive payment integration skill for SePay (Vietnamese payment gateway), Polar (global SaaS monetization platform), and Stripe (global payment infrastructure).

Features

SePay Integration

Vietnamese payment gateway with VietQR, NAPAS, bank transfers, and cards
44+ supported banks
Webhook verification with API Key/OAuth2 authentication
QR code generation API
Order-based virtual accounts
SDK support for Node.js, PHP, and Laravel

Polar Integration

Global SaaS monetization platform
Merchant of Record (handles global tax compliance)
Subscription management with trials, upgrades, downgrades
Usage-based billing with events and meters
Automated benefit delivery (GitHub repos, Discord roles, license keys, files)
Customer self-service portal
Multi-language SDKs (TypeScript, Python, PHP, Go)
Framework adapters (Next.js, Laravel, Remix, etc.)

Stripe Integration

Global payment infrastructure
CheckoutSessions, PaymentIntents, SetupIntents APIs
Billing and subscriptions at scale
Connect for marketplaces and platforms
Payment Element for custom checkout experiences
Multi-language SDKs (Node.js, Python, Ruby, PHP, Java, Go, .NET)
Best practices for integration design and API version upgrades

Structure

text

/* Detailed source-code truncated for AI context efficiency. */

Usage

Activate the Skill

Claude Code will automatically activate this skill when you mention payment integration, subscriptions, webhooks, or platform-specific terms (SePay, Polar).

Manual Activation

In conversations, simply reference the platforms:

"Implement SePay payment integration"
"Set up Polar subscriptions with usage-based billing"
"Create webhook handler for payment notifications"

Using Scripts

SePay Webhook Verification:

bash

cd $HOME/.claude/skills/payment-integration/scripts
node sepay-webhook-verify.js '{"id":12345,"gateway":"Vietcombank",...}'

Polar Webhook Verification:

bash

node polar-webhook-verify.js '{"type":"order.paid","data":{...}}' base64secret

Checkout Helper:

bash

# SePay
node checkout-helper.js sepay '{"orderInvoiceNumber":"ORD001","orderAmount":100000,...}'

# Polar
node checkout-helper.js polar '{"productPriceId":"price_xxx","successUrl":"https://..."}'

Run Tests:

bash

npm test

Environment Variables

Copy .env.example to .env and configure:

env

# SePay
SEPAY_MERCHANT_ID=SP-TEST-XXXXXXX
SEPAY_SECRET_KEY=spsk_test_xxxxxxxxxxxxx
SEPAY_ENV=sandbox
SEPAY_WEBHOOK_API_KEY=your_key

# Polar
POLAR_ACCESS_TOKEN=polar_xxxxxxxxxxxxxxxx
POLAR_SERVER=sandbox
POLAR_WEBHOOK_SECRET=base64_secret

Progressive Disclosure

The skill uses progressive disclosure to minimize context usage:

SKILL.md - Overview and quick reference (~99 lines)
references/ - Detailed guides loaded as needed (<100 lines each)
scripts/ - Executable helpers with embedded examples

Load only the references you need for your current task.

Platform Selection Guide

Choose SePay for:

Vietnamese market targeting
Bank transfer automation
Local payment methods
QR code payments (VietQR/NAPAS)
Direct bank monitoring

Choose Polar for:

Global market
SaaS/subscription business
Usage-based billing
Automated benefit delivery
Tax compliance (Merchant of Record)
Customer self-service

Choose Stripe for:

Global payment infrastructure
Enterprise-grade payment processing
Connect platforms (marketplaces)
Billing/subscriptions at scale
Custom checkout experiences (Payment Element)
Maximum payment method coverage

Examples

SePay Payment Flow

Load references/sepay/overview.md for authentication
Load references/sepay/sdk.md for integration
Use checkout-helper.js to generate payment form
Load references/sepay/webhooks.md for notifications
Use sepay-webhook-verify.js to verify authenticity

Polar Subscription Flow

Load references/polar/overview.md for setup
Load references/polar/products.md for pricing
Load references/polar/checkouts.md for payment
Load references/polar/subscriptions.md for lifecycle
Load references/polar/webhooks.md for events
Load references/polar/benefits.md for automation

Stripe Integration Flow

Load references/stripe/stripe-best-practices.md for integration design
Choose: Checkout (hosted/embedded) or Payment Element
Use CheckoutSessions API for most use cases
Load references/stripe/stripe-upgrade.md when upgrading API versions

Testing

All scripts include comprehensive test coverage:

SePay webhook verification (with/without authentication)
Polar webhook signature validation
Checkout configuration generation
Error handling and edge cases

Run npm test in the scripts directory to verify functionality.

Support

License

MIT

Version

1.1.0

Overview (`.claude/skills/sequential-thinking/README.md`)

Sequential Thinking Skill

Agent skill for systematic problem-solving through iterative reasoning with revision and branching capabilities.

What This Skill Does

Enables Claude to break down complex problems into sequential thought steps, revise conclusions when needed, and explore alternative solution paths—all while maintaining context throughout the reasoning process.

Installation

This skill requires the Sequential Thinking MCP server to be installed and configured in your Claude Desktop or Claude Code environment.

Step 1: Install MCP Server

Choose one of the following methods:

NPX (Recommended)

Add to your claude_desktop_config.json or MCP settings:

json

{
  "mcpServers": {
    "sequential-thinking": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
    }
  }
}

Docker

json

{
  "mcpServers": {
    "sequentialthinking": {
      "command": "docker",
      "args": ["run", "--rm", "-i", "mcp/sequentialthinking"]
    }
  }
}

Step 2: Add Skill to Project

Copy this skill folder to your project's .claude/skills/ directory:

bash

cp -r sequential-thinking /path/to/your/project/.claude/skills/

Step 3: Verify Installation

Restart Claude and check that the mcp__reasoning__sequentialthinking tool is available.

Usage

Once installed, Claude will automatically use this skill when:

Facing complex multi-step problems
Needing to revise earlier conclusions
Exploring alternative solution approaches
Working through uncertain or evolving scopes

You can also explicitly request it:

text

"Let's think through this step-by-step using sequential thinking"

Configuration

Disable Logging (Optional)

To suppress thought information logging, set environment variable:

json

{
  "mcpServers": {
    "sequential-thinking": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"],
      "env": {
        "DISABLE_THOUGHT_LOGGING": "true"
      }
    }
  }
}

Skill Structure

text

sequential-thinking/
├── SKILL.md              # Main skill definition
├── README.md             # This file
└── references/
    ├── advanced.md       # Revision and branching patterns
    └── examples.md       # Real-world use cases

When Claude Uses This Skill

The skill activates for:

Complex analysis: Breaking down multi-faceted problems
Design decisions: Exploring and comparing alternatives
Debugging: Systematic investigation with course correction
Planning: Multi-stage project planning with evolving scope
Architecture: Evaluating trade-offs across approaches

Learn More

License

MIT

Overview (`.claude/skills/shopify/README.md`)

Shopify API Research Documentation

This directory contains comprehensive research and analysis of various APIs for integration purposes.

Shopify GraphQL Admin API Analysis

File: shopify-graphql-admin-api-analysis.md
Date: 2025-10-25
Status: Complete
Thoroughness: Very Thorough

A comprehensive analysis of Shopify's GraphQL Admin API covering:

API overview and capabilities
Key features and operations
Common query and mutation patterns
Best practices and optimization strategies
Authentication and security considerations
Rate limiting and performance optimization
Typical use cases and implementation patterns
Troubleshooting guide
Code examples in multiple languages
Resources and further learning

Key Sections:

Executive Summary
API Overview
Key Features
Common Operations (Queries & Mutations)
API Structure (Types, Connections, Errors)
Best Practices
Typical Use Cases
API Versions and Deprecation
Tools and SDKs
Security Considerations
Performance Optimization
Common Patterns
Troubleshooting
Resources and Further Learning

Size: 1,348 lines, ~26KB

Usage

These documents are intended for:

Development planning and architecture decisions
Team onboarding and training
Integration implementation reference
Best practices guidance
Troubleshooting support

Maintenance

Documents should be reviewed quarterly
Update when API versions change
Add new findings from implementation experience
Keep code examples current with latest SDK versions

Last Updated: 2025-10-25
Maintained By: Claude Code Engineering Team

Overview (`.claude/skills/chrome-devtools/scripts/README.md`)

Chrome DevTools Scripts

CLI scripts for browser automation using Puppeteer.

CRITICAL: Always check pwd before running scripts.

Installation

Quick Install

bash

pwd  # Should show current working directory
cd .claude/skills/chrome-devtools/scripts
./install.sh  # Auto-checks dependencies and installs

Manual Installation

Linux/WSL - Install system dependencies first:

bash

./install-deps.sh  # Auto-detects OS (Ubuntu, Debian, Fedora, etc.)

Or manually:

bash

sudo apt-get install -y libnss3 libnspr4 libasound2t64 libatk1.0-0 libatk-bridge2.0-0 libcups2 libdrm2 libxkbcommon0 libxcomposite1 libxdamage1 libxfixes3 libxrandr2 libgbm1

All platforms - Install Node dependencies:

bash

npm install

Scripts

CRITICAL: Always check pwd before running scripts.

navigate.js

Navigate to a URL.

bash

node navigate.js --url https://example.com [--wait-until networkidle2] [--timeout 30000]

screenshot.js

Take a screenshot with automatic compression.

Important: Always save screenshots to ./docs/screenshots directory.

bash

node screenshot.js --output screenshot.png [--url https://example.com] [--full-page true] [--selector .element] [--max-size 5] [--no-compress]

Automatic Compression: Screenshots >5MB are automatically compressed using ImageMagick to ensure compatibility with Gemini API and Claude Code. Install ImageMagick for this feature:

macOS: brew install imagemagick
Linux: sudo apt-get install imagemagick

Options:

--max-size N - Custom size threshold in MB (default: 5)
--no-compress - Disable automatic compression
--format png|jpeg - Output format (default: png)
--quality N - JPEG quality 0-100 (default: auto)

click.js

Click an element.

bash

node click.js --selector ".button" [--url https://example.com] [--wait-for ".result"]

fill.js

Fill form fields.

bash

node fill.js --selector "#input" --value "text" [--url https://example.com] [--clear true]

evaluate.js

Execute JavaScript in page context.

bash

node evaluate.js --script "document.title" [--url https://example.com]

snapshot.js

Get DOM snapshot with interactive elements.

bash

node snapshot.js [--url https://example.com] [--output snapshot.json]

console.js

Monitor console messages.

bash

node console.js --url https://example.com [--types error,warn] [--duration 5000]

network.js

Monitor network requests.

bash

node network.js --url https://example.com [--types xhr,fetch] [--output requests.json]

performance.js

Measure performance metrics and record trace.

bash

node performance.js --url https://example.com [--trace trace.json] [--metrics] [--resources true]

Common Options

--headless false - Show browser window
--close false - Keep browser open
--timeout 30000 - Set timeout in milliseconds
--wait-until networkidle2 - Wait strategy (load, domcontentloaded, networkidle0, networkidle2)

Selector Support

Scripts that accept --selector (click.js, fill.js, screenshot.js) support both CSS and XPath selectors.

CSS Selectors (Default)

bash

# Element tag
node click.js --selector "button" --url https://example.com

# Class selector
node click.js --selector ".btn-submit" --url https://example.com

# ID selector
node fill.js --selector "#email" --value "[email protected]" --url https://example.com

# Attribute selector
node click.js --selector 'button[type="submit"]' --url https://example.com

# Complex selector
node screenshot.js --selector "div.container > button.btn-primary" --output btn.png

XPath Selectors

XPath selectors start with / or (// and are automatically detected:

bash

# Text matching - exact
node click.js --selector '//button[text()="Submit"]' --url https://example.com

# Text matching - contains
node click.js --selector '//button[contains(text(),"Submit")]' --url https://example.com

# Attribute matching
node fill.js --selector '//input[@type="email"]' --value "[email protected]"

# Multiple conditions
node click.js --selector '//button[@type="submit" and contains(text(),"Save")]'

# Descendant selection
node screenshot.js --selector '//div[@class="modal"]//button[@class="close"]' --output modal.png

# Nth element
node click.js --selector '(//button)[2]'  # Second button on page

Discovering Selectors

Use snapshot.js to discover correct selectors:

bash

# Get all interactive elements
node snapshot.js --url https://example.com | jq '.elements[]'

# Find buttons
node snapshot.js --url https://example.com | jq '.elements[] | select(.tagName=="BUTTON")'

# Find inputs
node snapshot.js --url https://example.com | jq '.elements[] | select(.tagName=="INPUT")'

Security

XPath selectors are validated to prevent injection attacks. The following patterns are blocked:

javascript:
<script
onerror=, onload=, onclick=
eval(, Function(, constructor(

Selectors exceeding 1000 characters are rejected (DoS prevention).

Output Format

All scripts output JSON to stdout:

json

{
  "success": true,
  "url": "https://example.com",
  "title": "Example Domain",
  ...
}

Errors are output to stderr:

json

{
  "success": false,
  "error": "Error message",
  "stack": "..."
}

Overview (`.claude/skills/repomix/scripts/README.md`)

Repomix Scripts

Utility scripts for batch processing repositories with Repomix.

repomix_batch.py

Batch process multiple repositories (local or remote) using the repomix CLI tool.

Features

Process multiple repositories in one command
Support local and remote repositories
Configurable output formats (XML, Markdown, JSON, Plain)
Environment variable loading from multiple .env file locations
Comprehensive error handling
Progress reporting

Installation

Requires Python 3.10+ and repomix CLI:

bash

# Install repomix
npm install repomix

# Install Python dependencies (if needed)
pip install pytest pytest-cov pytest-mock  # For running tests

Usage

Process single repository:

bash

python repomix_batch.py /path/to/repo

Process multiple repositories:

bash

python repomix_batch.py /repo1 /repo2 /repo3

Process remote repositories:

bash

python repomix_batch.py owner/repo1 owner/repo2 --remote

From JSON file:

bash

python repomix_batch.py -f repos.json

With options:

bash

python repomix_batch.py /repo1 /repo2 \
  --style markdown \
  --output-dir output \
  --remove-comments \
  --include "src/**/*.ts" \
  --ignore "tests/**" \
  --verbose

Configuration File Format

Create repos.json with repository configurations:

json

[
  {
    "path": "/path/to/local/repo",
    "output": "custom-output.xml"
  },
  {
    "path": "owner/repo",
    "remote": true
  },
  {
    "path": "https://github.com/owner/repo",
    "remote": true,
    "output": "repo-output.md"
  }
]

Environment Variables

Loads .env files in order of precedence:

Process environment (highest priority)
./repomix/.env (skill-specific)
./skills/.env (skills directory)
./.claude/.env (lowest priority)

Command Line Options

text

positional arguments:
  repos                  Repository paths or URLs to process

options:
  -h, --help            Show help message
  -f, --file FILE       JSON file containing repository configurations
  --style {xml,markdown,json,plain}
                        Output format (default: xml)
  -o, --output-dir DIR  Output directory (default: repomix-output)
  --remove-comments     Remove comments from source files
  --include PATTERN     Include pattern (glob)
  --ignore PATTERN      Ignore pattern (glob)
  --no-security-check   Disable security checks
  -v, --verbose         Verbose output
  --remote              Treat all repos as remote URLs

Examples

Process local repositories:

bash

python repomix_batch.py /path/to/repo1 /path/to/repo2 --style markdown

Process remote repositories:

bash

python repomix_batch.py yamadashy/repomix facebook/react --remote

Mixed configuration:

bash

python repomix_batch.py \
  /local/repo \
  --remote owner/remote-repo \
  -f additional-repos.json \
  --style json \
  --remove-comments

TypeScript projects only:

bash

python repomix_batch.py /repo1 /repo2 \
  --include "**/*.ts,**/*.tsx" \
  --ignore "**/*.test.ts,dist/" \
  --remove-comments \
  --style markdown

Testing

Run tests with coverage:

bash

cd tests
pytest test_repomix_batch.py -v --cov=repomix_batch --cov-report=term-missing

Current coverage: 99%

Exit Codes

0 - All repositories processed successfully
1 - One or more repositories failed or error occurred

Troubleshooting

repomix not found:

bash

npm install repomix

Permission denied:

bash

chmod +x repomix_batch.py

Timeout errors:

Default timeout: 5 minutes per repository
Reduce scope with --include patterns
Exclude large directories with --ignore

No repositories specified:

Provide repository paths as arguments
Or use -f flag with JSON config file

MARKETPLACE (`docs/MARKETPLACE.md`)

ClaudeKit Skills Marketplace

ClaudeKit Skills is now available as a Claude Code Plugin Marketplace, enabling seamless installation and automatic updates.

Quick Start

1. Add Marketplace

bash

/plugin marketplace add mrgoonie/claudekit-skills

2. Install Plugins

Install specific plugin categories based on your needs:

bash

# AI & ML Tools
/plugin install ai-ml-tools@claudekit-skills

# Web Development
/plugin install web-dev-tools@claudekit-skills

# DevOps & Infrastructure
/plugin install devops-tools@claudekit-skills

# Backend Development
/plugin install backend-tools@claudekit-skills

# Document Processing
/plugin install document-processing@claudekit-skills

# Debugging Frameworks
/plugin install debugging-tools@claudekit-skills

# Problem Solving Techniques
/plugin install problem-solving-tools@claudekit-skills

# Platform Integrations
/plugin install platform-tools@claudekit-skills

# Meta Development
/plugin install meta-tools@claudekit-skills

# Media Processing
/plugin install media-tools@claudekit-skills

# Research Tools
/plugin install research-tools@claudekit-skills

# Specialized Skills
/plugin install specialized-tools@claudekit-skills

3. Update Plugins

bash

# Update specific plugin
/plugin update ai-ml-tools@claudekit-skills

# Update all plugins
/plugin update --all

Available Plugins

🤖 ai-ml-tools

AI and ML capabilities with Google Gemini API integration

Includes:

ai-multimodal - Process images, videos, audio, and documents with Gemini API
google-adk-python - Google's Agent Development Kit for building AI agents

Dependencies:

Python 3.8+
google-genai, pypdf, python-docx, Pillow
Environment: GEMINI_API_KEY

🌐 web-dev-tools

Comprehensive web development skills

Includes:

frontend-development - React/TypeScript patterns with Suspense, TanStack Router
frontend-design - Production-grade UI/UX with creative, polished code
ui-styling - shadcn/ui components with Tailwind CSS
web-frameworks - Next.js App Router, Turborepo monorepos
aesthetic - Design principles and visual hierarchy
web-testing - Playwright, Vitest, k6 for E2E/unit/integration/load/security/a11y testing

Dependencies:

Node.js 18+
npm/pnpm/yarn
Playwright (for E2E)
k6 (for load testing)

☁️ devops-tools

DevOps and infrastructure management

Includes:

devops - Cloudflare Workers, Docker, Google Cloud Platform
databases - MongoDB and PostgreSQL administration
chrome-devtools - Browser automation with Puppeteer

Dependencies:

Docker (optional)
Cloudflare Wrangler (optional)
Google Cloud CLI (optional)
PostgreSQL client (optional)
MongoDB Shell (optional)

💻 backend-tools

Backend development frameworks

Includes:

backend-development - Node.js, Python, Go, REST/GraphQL APIs
better-auth - TypeScript authentication framework

Dependencies:

Node.js 18+ (for better-auth)
Python 3.8+ (for backend patterns)

📄 document-processing

Document creation and processing

Includes:

document-skills/docx - Word documents with tracked changes
document-skills/pdf - PDF extraction, creation, merging
document-skills/pptx - PowerPoint presentations
document-skills/xlsx - Excel spreadsheets and financial modeling

Dependencies:

Python 3.8+
pypdf, python-docx, python-pptx, openpyxl

🐛 debugging-tools

Systematic debugging frameworks

Includes:

debugging/defense-in-depth - Multi-layer validation
debugging/root-cause-tracing - Backward call stack analysis
debugging/systematic-debugging - Four-phase debugging process
debugging/verification-before-completion - Evidence-based completion

🧠 problem-solving-tools

Advanced problem-solving techniques

Includes:

problem-solving/collision-zone-thinking - Force unrelated concepts together
problem-solving/inversion-exercise - Flip core assumptions
problem-solving/meta-pattern-recognition - Spot universal principles
problem-solving/scale-game - Test at extremes
problem-solving/simplification-cascades - Find eliminating insights
problem-solving/when-stuck - Dispatch to right technique

🛍️ platform-tools

Platform and payment integrations

Includes:

shopify - Build apps, extensions, and themes
payment-integration - SePay (Vietnamese VietQR), Polar (SaaS MoR), Stripe, Paddle, Creem.io
mcp-management - Manage MCP servers
mcp-builder - Build MCP servers in Python/TypeScript

Agents:

mcp-manager - MCP server management agent

Commands:

/use-mcp - MCP integration command

Dependencies:

Node.js 18+
Shopify CLI (optional)
Environment: SEPAY_*, POLAR_*, STRIPE_* (for payment integrations)

🔧 meta-tools

Meta development tools

Includes:

skill-creator - Create new Claude Code skills
code-review - Review workflows and quality gates

Commands:

/git/* - Git workflow commands
/skill/* - Skill management commands

🎬 media-tools

Media processing capabilities

Includes:

media-processing - FFmpeg (video/audio) and ImageMagick (images)

Dependencies:

FFmpeg
ImageMagick

Installation:

bash

# macOS
brew install ffmpeg imagemagick

# Ubuntu/Debian
sudo apt-get install ffmpeg imagemagick

# Windows
choco install ffmpeg imagemagick

📚 research-tools

Research and documentation

Includes:

docs-seeker - llms.txt documentation discovery
repomix - Package repositories for AI analysis

Dependencies:

Node.js 18+ (for repomix)
repomix CLI tool

⚡ specialized-tools

Specialized capabilities

Includes:

sequential-thinking - Step-by-step reasoning with extended thinking
mermaidjs-v11 - Diagram generation (flowcharts, sequence, etc.)

Auto-Enable in Projects

Add to your project's .claude/settings.json:

json

{
  "extraKnownMarketplaces": {
    "claudekit-skills": {
      "source": {
        "source": "github",
        "repo": "mrgoonie/claudekit-skills"
      }
    }
  },
  "enabledPlugins": {
    "ai-ml-tools@claudekit-skills": true,
    "web-dev-tools@claudekit-skills": true,
    "devops-tools@claudekit-skills": true
  }
}

Version Pinning

Pin to specific version for stability:

json

{
  "extraKnownMarketplaces": {
    "claudekit-skills": {
      "source": {
        "source": "github",
        "repo": "mrgoonie/claudekit-skills",
        "ref": "v1.0.0"
      }
    }
  }
}

Enterprise Configuration

Restrict to approved marketplaces in managed settings:

json

{
  "strictKnownMarketplaces": [
    {
      "source": "github",
      "repo": "mrgoonie/claudekit-skills",
      "ref": "v1.0.0"
    }
  ]
}

Manual Installation (Legacy)

For users who prefer manual installation:

bash

git clone https://github.com/mrgoonie/claudekit-skills
cp -r claudekit-skills/.claude/* /path/to/your/project/.claude/

Note: Manual installation is deprecated. Marketplace installation is recommended for automatic updates and version management.

Troubleshooting

Plugin Not Found

bash

# Refresh marketplace
/plugin marketplace remove claudekit-skills
/plugin marketplace add mrgoonie/claudekit-skills

Update Not Working

bash

# Force update
/plugin uninstall ai-ml-tools@claudekit-skills
/plugin install ai-ml-tools@claudekit-skills

Dependencies Missing

Each plugin documents its dependencies. Install required system tools and Python packages as needed. See INSTALLATION.md for detailed dependency installation instructions.

Support

GitHub Issues: https://github.com/mrgoonie/claudekit-skills/issues
Documentation: https://claudekit.cc
Substack: https://faafospecialist.substack.com/

License

MIT License - see LICENSE for details.

--- METRICS ---

Files Extracted: 10
Estimated Token Budget: ~15586 tokens
Canonical Reference: https://codewiki.google/github.com/mrgoonie/claudekit-skills

Technical Documentation: mrgoonie/claudekit-skills

Overview (`README.md`) Copy Section

ClaudeKit - Agent Skills

My other projects Copy Chapter

🎉 NEW [Dec 2025]: Claude Code Marketplace! Copy Chapter

Update [Nov 2025]: No more context bloat with "mcp-manager" subagent + "mcp-management" skills! Copy Chapter

✨ Skills just got refactored! Copy Chapter

Skills catalog Copy Chapter

🔐 Authentication & Security Copy Section

🤖 AI & Agent Development Copy Section

💻 Backend Development Copy Section

🧠 AI & Machine Learning Copy Section

🎨 Design & Aesthetics Copy Section

🌐 Web Development Copy Section

🌐 Browser Automation & Testing Copy Section

☁️ Cloud Platforms & DevOps Copy Section

🗄️ Databases Copy Section

🛠️ Development Tools Copy Section

📚 Documentation & Research Copy Section

🧪 Code Quality & Review Copy Section

🐛 Debugging & Quality Copy Section

📄 Document Processing Copy Section

🛍️ E-commerce & Platforms Copy Section

💳 Payments & Billing Copy Section

🧠 Problem-Solving Frameworks Copy Section

🧠 Advanced Reasoning Copy Section

📊 Visualization & Diagramming Copy Section

🔧 Meta Skills (from Anthropic) Copy Section

Getting started Copy Chapter

🚀 Marketplace Installation (Recommended) Copy Section

📦 Manual Installation (Legacy) Copy Section

🎯 Usage Copy Section

Star History Copy Chapter

Extend beyond the free tier Copy Chapter

Overview (`.claude/skills/README.md`) Copy Section

Skills

About This Repository

Disclaimer Copy Chapter

Example Skills

Creative & Design Copy Chapter

Development & Technical Copy Chapter

Enterprise & Communication Copy Chapter

Meta Skills Copy Chapter

Document Skills

Try in Claude Code, Claude.ai, and the API

Claude Code Copy Chapter

Claude.ai Copy Chapter

Claude API Copy Chapter

Creating a Basic Skill

Partner Skills

Overview (`.claude/skills/common/README.md`) Copy Section

Common Skill Utilities

API Key Helper Copy Chapter

Usage in Skills Copy Section

API Key Lookup Order Copy Section

Vertex AI Support Copy Section

Using get_client() Helper Copy Section

Using get_vertex_config() Helper Copy Section

Error Handling Copy Section

Overview (`.claude/skills/mcp-management/README.md`) Copy Section

MCP Management Skill

Overview Copy Chapter

Features Copy Chapter

Quick Start Copy Chapter

1. Install Dependencies Copy Section

2. Configure MCP Servers Copy Section

3. Test Connection Copy Section

Usage Patterns Copy Chapter

Pattern 1: Discover Available Tools Copy Section

Pattern 2: LLM-Driven Tool Selection Copy Section

Pattern 3: Execute MCP Tools Copy Section

Pattern 4: Use with Subagent Copy Section

Architecture Copy Chapter

File Structure Copy Chapter

Scripts Reference Copy Chapter

mcp-client.ts Copy Section

cli.ts Copy Section

Configuration Copy Chapter

Environment Variables Copy Section

MCP Config Format Copy Section

Overview (`README.md`)

My other projects

🎉 NEW [Dec 2025]: Claude Code Marketplace!

Update [Nov 2025]: No more context bloat with "mcp-manager" subagent + "mcp-management" skills!

✨ Skills just got refactored!

Skills catalog

🔐 Authentication & Security

🤖 AI & Agent Development

💻 Backend Development

🧠 AI & Machine Learning

🎨 Design & Aesthetics

🌐 Web Development

🌐 Browser Automation & Testing

☁️ Cloud Platforms & DevOps

🗄️ Databases

🛠️ Development Tools

📚 Documentation & Research

🧪 Code Quality & Review

🐛 Debugging & Quality

📄 Document Processing

🛍️ E-commerce & Platforms

💳 Payments & Billing

🧠 Problem-Solving Frameworks

🧠 Advanced Reasoning

📊 Visualization & Diagramming

🔧 Meta Skills (from Anthropic)

Getting started

🚀 Marketplace Installation (Recommended)

📦 Manual Installation (Legacy)

🎯 Usage

Star History

Extend beyond the free tier

Overview (`.claude/skills/README.md`)

Disclaimer

Creative & Design

Development & Technical

Enterprise & Communication

Meta Skills

Claude Code

Claude.ai

Claude API

Overview (`.claude/skills/common/README.md`)

API Key Helper

Usage in Skills

API Key Lookup Order

Vertex AI Support

Using get_client() Helper

Using get_vertex_config() Helper

Error Handling

Overview (`.claude/skills/mcp-management/README.md`)

Overview

Features

Quick Start

1. Install Dependencies

2. Configure MCP Servers

3. Test Connection

Usage Patterns

Pattern 1: Discover Available Tools

Pattern 2: LLM-Driven Tool Selection

Pattern 3: Execute MCP Tools

Pattern 4: Use with Subagent

Architecture

File Structure

Scripts Reference

mcp-client.ts

cli.ts

Configuration

Environment Variables

MCP Config Format

Common MCP Servers

Integration with mcp-manager Agent

Troubleshooting

"Config not found"

"Server connection failed"

"Tool not found"

Resources

License

Overview (`.claude/skills/payment-integration/README.md`)

Features

SePay Integration