Custom agents, skills, and commands for software development workflows.
# Add the marketplace
/plugin marketplace add https://github.com/mintuz/claude-plugins
# Install plugins
/plugin install core@mintuz-claude-plugins
/plugin install web@mintuz-claude-plugins
/plugin install typescript@mintuz-claude-plugins
/plugin install system-design@mintuz-claude-plugins
/plugin install product-management@mintuz-claude-plugins
/plugin install app@mintuz-claude-plugins
/plugin install life@mintuz-claude-plugins| Plugin | Description |
|---|---|
| core | Core workflows: commits, learning, code review, prompts, PRs, writing, and persistent memory |
| web | Web development with CSS, React, Tailwind, TDD, testing, and design patterns |
| typescript | TypeScript strict mode, schema-first development, and best practices |
| system-design | Architecture visualization with Mermaid diagrams |
| product-management | PRDs, task management with Task Master MCP, and status updates |
| app | Swift iOS development with App Intents, Swift Testing, and SwiftUI architecture |
| life | Personal life management with GPS method for goal achievement |
| Skill | Description |
|---|---|
commit-messages |
Conventional commit messages that explain the "why" not just the "what" |
expectations |
Working expectations and documentation practices |
learn |
Document learnings and capture insights into CLAUDE.md |
pr |
PR descriptions, sizing, and creation with gh CLI |
writing |
Developer-focused writing: tutorials, how-tos, docs with clear structure |
prompt-master |
Transform simple prompts into comprehensive, XML-tagged instructions with roles and examples |
| Skill | Description |
|---|---|
css |
CSS best practices for maintainable, scalable styles |
react |
Production-ready React architecture and patterns |
react-testing |
React Testing Library patterns for components, hooks, and context |
frontend-testing |
DOM Testing Library patterns for behavior-driven UI testing |
tdd |
Test-Driven Development principles and Red-Green-Refactor workflow |
refactoring |
Refactoring assessment and patterns after tests pass |
web-design |
Visual hierarchy, spacing, typography, and UI polish |
tailwind |
Design systems with Tailwind CSS, design tokens, and component libraries |
eyes |
Visual feedback loop with Playwright screenshots for UI iteration |
chatgpt-app-sdk |
Build ChatGPT apps using OpenAI Apps SDK and MCP with conversational UX |
| Skill | Description |
|---|---|
swift-testing |
Swift Testing framework: @Test macros, #expect/#require patterns |
app-intent-driven-development |
Build features as App Intents first for Siri, Shortcuts, widgets, and SwiftUI |
swiftui-architecture |
Modern SwiftUI patterns: @Observable, state management, no ViewModels |
debug |
Structured feedback loop for debugging iOS simulator issues and UI problems |
local-ai-models |
On-device AI with Foundation Models and MLX Swift: LLMs, VLMs, embeddings, and image generation |
app-store-scraper |
Scrape iOS/macOS App Store data using iTunes/App Store APIs |
| Skill | Description |
|---|---|
typescript |
Schema-first development, strict typing, functional patterns, and Zod |
| Skill | Description |
|---|---|
gps-method |
Evidence-based goal achievement framework using Goal, Plan, and System methodology |
No standalone skills; see the mermaid-generator agent below.
| Skill | Description |
|---|---|
status-updates |
Team updates and stakeholder comms with scannable structure and honest tone |
| Agent | Plugin | Description |
|---|---|---|
code-reviewer |
web | Expert code review specialist focusing on quality, security, performance, and maintainability |
refactorer |
web | Refactoring coach to guide code improvement decisions and assess opportunities after tests pass |
senior-web-engineer |
web | Expert UI engineer for building robust, scalable React components with focus on standards compliance |
test-runner |
web | Runs tests with auto-detection and returns concise pass/fail summaries |
mermaid-generator |
system-design | Generates Mermaid diagrams from code to visualize architecture and flows |
orchestrator |
product-management | Master coordinator for complex multi-step tasks requiring delegation and architectural planning |
product-manager |
product-management | Creates complete PRDs with structure, requirements, risks, and measurable success criteria |
| Command | Plugin | Description |
|---|---|---|
/init [path-to-CLAUDE.md] |
core | Initialize a session, load the Expectations skill, and ensure CLAUDE.md references it |
/remember <topic> |
core | Store knowledge in persistent memory for future sessions |
/recall <topic> |
core | Recall memories into the current session |
Some plugins include MCP server configurations:
- core - Memory MCP for persistent knowledge storage across sessions
- product-management - Task Master MCP for task management workflows
The .dist folder contains individual skill zip files ready for upload to Claude web (claude.ai). Each skill is packaged as a separate zip file that can be uploaded independently to the skills section in your Claude web conversations.
Run the packaging script from the repository root:
# Create individual skill zips in .dist directory
go run scripts/package-skills.go
# This creates files like:
# .dist/commit-messages.zip
# .dist/react.zip
# .dist/swift-testing.zip
# etc.- Visit claude.ai
- Navigate to the skills section
- Upload the individual zip files from
.dist - Access the skills in your web conversations
See scripts/README.md for more options including custom output directories and skill name prefixing.
Skills can also be synced to the OpenAI Codex CLI format, making them available for use with Codex.
Run the sync script from the repository root:
# Sync all skills to ~/.codex/skills (user-level)
go run scripts/codex-sync.go
# Sync to .codex/skills in current project (project-level)
go run scripts/codex-sync.go --project
# This syncs skills like:
# commit-messages
# react
# swift-testing
# etc.After syncing, invoke skills in Codex CLI using the $skill-name syntax (e.g., $commit-messages, $react).
See scripts/README.md for more options including custom output directories, skill name prefixing, and dry-run mode.