AvinashP

Refactors code safely with test verification. Use when asked to refactor, restructure, clean up, or improve code organization.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use before any creative work - creating features, building components, adding functionality. Explores requirements and design through collaborative dialogue before implementation.

Creates quality git commits with conventional commit format. Use when asked to commit changes or create a commit message.

Use when encountering any bug, test failure, error, or unexpected behavior - before proposing fixes. Requires root cause investigation first.

Explains code with diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when asked "how does this work?"

Creates pull requests with quality descriptions, to be used when asked to create a PR, open a pull request, or ship code for review. Requires test verification before PR creation.

Create distinctive, production-grade frontend interfaces with high design quality. This skill generates creative, polished code and UI design for web components, pages, and applications, avoiding generic AI aesthetics.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Use when receiving code review feedback or corrections - before implementing suggestions. Requires technical verification and reasoned evaluation, not blind agreement or performative responses.

Generates boilerplate following project conventions. Use when asked to create a new component, module, service, or scaffold code.

Use when implementing any feature or bugfix, before writing implementation code. Write the test first, watch it fail, then implement.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. It requires running verification commands and confirming output before any success claims.

Audits code for security vulnerabilities. Use when asked to check security, find vulnerabilities, or audit for OWASP issues.

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Initialize project with CLAUDE.md, STATE.md, and ROADMAP.md by following the canonical init command doc.

Review code changes and capture learnings for CLAUDE.md by following the canonical review command doc.

Complete the current milestone and prepare next work by following the canonical complete command doc.

Execute the current plan (from STATE.md -> PLAN.md) by following the canonical execute command doc. Make code changes and run necessary checks.

Creates an executable plan for the current phase (3-5 tasks). It reads the canonical plan command document and produces/updates the current PLAN.md, referenced from STATE.md. No implementation is included.

Check project progress and suggest the next action by following the canonical status command doc.

Restore project context after clear/new session by following the canonical sync command doc.

Pull and triage issues from external sources for planning by following the canonical triage command doc.