By ivklgn
AI coding agents and skills: specialized subagents for React, Go, TypeScript, PostgreSQL, CSS, Playwright, deployment, security, LLM architecture, and more
npx claudepluginhub ivklgn/ai --plugin ivklgnBusiness analyst and product specialist for requirements analysis, feature specifications, user stories, acceptance criteria, and product documentation. Use for analyzing business requirements, writing specs, creating user stories, and product research.
CLI developer specializing in command-line tools and terminal applications. Covers argument parsing, interactive prompts, shell completions, cross-platform compatibility, and distribution.
CSS/SCSS specialist. Use proactively to design, implement, refactor, and review CSS/SCSS for layout (flex/grid), responsive behavior, animations, and theming. Also use proactively to research modern CSS features + browser support, and to simplify/clean up overengineered styles.
CI/CD pipeline designer and deployment automation specialist. Use for designing deployment strategies (blue-green, canary, rolling), optimizing pipeline performance, implementing GitOps workflows, and improving DORA metrics.
Documentation site developer and frontend specialist. Use proactively for building, customizing, and maintaining documentation sites (Astro Starlight, Docusaurus, VitePress, etc.). Handles SSG/SSR setup, SEO optimization, component customization, layout work, styling, and JS/TS implementation within doc sites. Also use for any frontend task in the docs project: custom components, integrations, build config, performance tuning.
Specialized front-end layout designer. Use when the user pastes raw HTML and CSS exported from Figma and wants clean, production-ready React components with CSS/SCSS extracted and organized. Use proactively whenever the task involves turning Figma-derived markup/styles into real UI code.
Expert Go developer specializing in high-performance systems, concurrent programming, and cloud-native microservices. Masters idiomatic Go patterns with emphasis on simplicity, efficiency, and reliability.
Expert in InstantDB realtime database. Use for code generation, reviews, optimizations, and type-safe patterns. Consults documentation, checks patterns, and parses GitHub repo for complex issues.
JavaScript/TypeScript performance analysis and memory leak detection specialist. Use proactively when investigating memory leaks, CPU bottlenecks, event loop stalls, GC pressure, SSR/SSG performance, React cache issues, bundle size regressions, or Node.js server tuning. Expert in V8 internals, libuv, thread pool configuration, semi-space/old-space sizing, and load testing strategy.
LLM systems architect for production AI deployments. Use for designing inference serving infrastructure, RAG pipelines, fine-tuning workflows, multi-model orchestration, and cost optimization.
Model Context Protocol (MCP) server and client developer. Use for building, debugging, and optimizing MCP servers that connect AI systems to external tools and data sources.
NPM dependency updater agent. Use proactively to check for package updates, analyze changelogs, run security audits, and create comprehensive update reports with release notes links.
Internal developer platform (IDP) architect. Use for building self-service infrastructure, developer portals (Backstage), golden path templates, and GitOps workflows to reduce friction and accelerate delivery.
Playwright E2E testing specialist. Use for writing, reviewing, debugging, and optimizing Playwright tests. Proactively use when working with test files (*.spec.ts), page objects, or test helpers.
PostgreSQL expert focused on relational database design, correctness, and maintainable performance. Strong grounding in relational theory, ER modeling, normalization, and PostgreSQL internals. Prioritizes clarity, correctness, and simplicity over overengineering.
Prompt design and optimization specialist. Use for crafting, testing, and managing production prompts with A/B testing, evaluation frameworks, token optimization, and cost tracking.
React code optimizer that analyzes and improves React code based on the project's React version. Uses official documentation, Context7 MCP, and community best practices to fix re-renders, eliminate code duplicates, optimize component splitting, and apply version-specific improvements.
Expert React specialist mastering React 18+ with modern patterns and ecosystem. Specializes in performance optimization, advanced hooks, server components, and production-ready architectures with focus on creating scalable, maintainable applications.
Professional frontend developer expert in React with Reatom state manager. Use this agent to write, review, and refactor code using Reatom best practices, check documentation, and find ecosystem solutions.
Security auditor for code and infrastructure review. Use proactively to audit code for vulnerabilities (OWASP Top 10, injection, XSS, auth flaws), review dependencies for known CVEs, assess infrastructure configurations, and perform threat modeling.
Infrastructure and application security engineer. Use for DevSecOps automation, zero-trust architecture, compliance programs (SOC2, ISO27001), vulnerability management, and CI/CD security integration.
Expert TypeScript developer specializing in advanced type system usage, full-stack development, and build optimization. Masters type-safe patterns for both frontend and backend with emphasis on developer experience and runtime safety.
Load current git branch changes (diff, commits, changed files) into session context. Use when the user invokes /load-branch-changes to review, understand, or focus on the current branch's changes compared to the base branch.
Reset accumulated permissions in .claude/settings.local.json. Use when the user says "/reset-permissions" or asks to clear, reset, or clean up Claude Code permissions. Supports full reset (default) or selective reset keeping read-only permissions (--keep-read).
Run a comprehensive Go code review on git-changed files using the golang-pro agent with Context7 library docs
Claude Code plugin with 22 specialized subagents and 3 skills.
# Add the marketplace
/plugin marketplace add ivklgn/ai
# Install the plugin
/plugin install ivklgn
Or via settings.json:
{
"extraKnownMarketplaces": {
"ivklgn-ai": {
"source": {
"source": "github",
"repo": "ivklgn/ai"
}
}
},
"enabledPlugins": {
"ivklgn@ivklgn-ai": true
}
}
Local development:
claude --plugin-dir ./claude
# Local scope (current project)
claude plugin uninstall ivklgn --scope local
# Project scope
claude plugin uninstall ivklgn --scope project
# User scope (global)
claude plugin uninstall ivklgn --scope user
| Agent | Description |
|---|---|
| business-analyst | Requirements analysis, user stories, feature specs, and product documentation |
| cli-developer | CLI tools and terminal applications with cross-platform support and shell completions |
| css-developer | CSS/SCSS specialist for layout, responsive design, animations, theming, and modern CSS features |
| deployment-engineer | CI/CD pipeline design, deployment strategies (blue-green, canary), and GitOps workflows |
| documentation-developer | Documentation sites with Astro Starlight, Docusaurus, VitePress, and SEO optimization |
| frontend-figma-layout-designer | Convert raw Figma HTML/CSS exports into clean, production-ready React components |
| golang-pro | High-performance Go systems, concurrent programming, microservices, and idiomatic patterns |
| instantdb-expert | InstantDB realtime database: code generation, reviews, optimizations, and type-safe patterns |
| js-perf-analyzer | JS/TS performance analysis: memory leaks, CPU bottlenecks, event loop stalls, V8 internals, and bundle size |
| llm-architect | LLM systems architecture: inference serving, RAG pipelines, fine-tuning, and multi-model orchestration |
| mcp-developer | MCP server and client development for connecting AI systems to external tools and data |
| npm-updater | Check for package updates, analyze changelogs, run security audits, and create update reports |
| platform-engineer | Internal developer platforms, self-service infrastructure, Backstage portals, and golden paths |
| playwright-e2e | Playwright E2E testing: write, review, debug, and optimize tests and page objects |
| postgres-pro | PostgreSQL expert for relational database design, normalization, ER modeling, and correctness-focused performance |
| prompt-engineer | Prompt design, optimization, A/B testing, and production prompt management |
| react-code-optimizer | React performance analysis: fix re-renders, eliminate duplicates, optimize component splitting |
| react-specialist | React 18+ development with hooks, server components, and production-ready architectures |
| reatom-guru | React with Reatom state manager: write, review, and refactor using best practices |
| security-auditor | Security auditing, vulnerability assessment, OWASP compliance, and threat modeling |
| security-engineer | DevSecOps automation, zero-trust architecture, compliance programs, and vulnerability management |
| typescript-pro | Advanced TypeScript development with full type system mastery, strict mode, generics, and build optimization |
| Skill | Description |
|---|---|
| load-branch-changes | Load current branch changes (diff, commits, changed files) into session context |
| reset-permissions | Reset accumulated permissions in .claude/settings.local.json (full or keep read-only) |
| review-go | Go code review on git-changed files using golang-pro agent with Context7 docs |
├── marketplace.json # Plugin marketplace manifest
└── claude/
├── .claude-plugin/plugin.json # Plugin metadata
├── agents/ # Subagents (22)
└── skills/ # Skills (3)
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
The most comprehensive Claude Code plugin — 36 agents, 142 skills, 68 legacy command shims, and production-ready hooks for TDD, security scanning, code review, and continuous learning
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Use this agent when you need expert assistance with React Native development tasks including code analysis, component creation, debugging, performance optimization, or architectural decisions. Examples: <example>Context: User is working on a React Native app and needs help with a navigation issue. user: 'My stack navigator isn't working properly when I try to navigate between screens' assistant: 'Let me use the react-native-dev agent to analyze your navigation setup and provide a solution' <commentary>Since this is a React Native specific issue, use the react-native-dev agent to provide expert guidance on navigation problems.</commentary></example> <example>Context: User wants to create a new component that follows the existing app structure. user: 'I need to create a custom button component that matches our app's design system' assistant: 'I'll use the react-native-dev agent to create a button component that aligns with your existing codebase structure and design patterns' <commentary>The user needs React Native component development that should follow existing patterns, so use the react-native-dev agent.</commentary></example>
Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Works with Claude Code, Kiro, Clawd CLI, Gemini CLI, Cursor, Continue, Hermes, and 17+ AI coding assistants. Now with Arabic, German, Spanish, and Chinese (Simplified & Traditional) support.