Claude Skills by HaoNgo232

Structured brainstorming for projects and features. Explores multiple

**MANDATORY:** Use for complex/vague requests, new features, updates.

review code and ensure quality

Reduce AI token usage by **6.8x average** (up to **49x** on monorepos) by giving the AI a structural map of your codebase instead of letting it read everything.

Keep sessions productive by compressing completed work while preserving key decisions.

Advanced multi-agent coordination with parallel dispatch and synthesis.

Distilled from production-proven coordinator patterns. Transforms sequential agent chains into intelligent parallel orchestration.

Create new application command. Triggers App Builder skill and starts

Debugging command. Activates DEBUG mode for systematic problem investigation.

Deployment command for production releases. Pre-flight checks and deployment

Deployment principles and decision-making for safe production releases.

Templates and structure guidelines for common documentation types.

Add or update features in existing application. Used for iterative development.

**Philosophy:** Every pixel has purpose. Restraint is luxury. User psychology drives decisions.

**Orchestrator skill** that provides core principles and routes to specialized sub-skills.

Optimization for AI-powered search engines.

Internationalization (i18n) and Localization (L10n) best practices.

**The AI should act as an intelligent Project Manager**, analyzing each request and automatically selecting the best specialist(s) for the job.

**MANDATORY:** Run appropriate validation tools after EVERY code change. Do not finish a task until the code is error-free.

Principles for building MCP servers.

Enables agents to remember across sessions. Never re-discover what was already learned.

Principles and decision-making for Node.js development in 2025.

Coordinate multiple agents for complex tasks. Use for multi-perspective

Orchestration through AG Kit's built-in Agent Tool

Measure, analyze, optimize - in that order.

Source: obra/superpowers

Create project plan using project-planner agent. No code writing - only

Critical patterns and pitfalls for Windows PowerShell.

Preview server start, stop, and status check. Local development server

Adversary simulation principles based on MITRE ATT&CK framework.

Save information to persistent memory for cross-session recall. Stores

Expert toolkit for rust pro

Principles for search engine visibility.

Server management principles for production operations.

The best code is the code you don't have to write. The second best is the code anyone can read.

Turn repetitive patterns into reusable skills. If you've done it three times, it should be a skill.

Display agent and project status. Progress tracking and status board.

Source: obra/superpowers

Write tests first, code second.

Test generation and test running command. Creates and executes tests

Plan and implement UI

"Code that exists" ≠ "Code that works." This skill ensures changes are verified through execution.

Verify code changes work by running them. Proves through execution, not

Think like an attacker, defend like an expert. 2025 threat landscape awareness.

Expert toolkit for web design guidelines

Discover and test everything. Leave no route untested.

API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.

Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.