minhthang-plugins

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

Commands for git commit workflows including commit, push, and PR creation

Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions

Comprehensive toolkit for developing Claude Code plugins including hooks, MCP integration, commands, agents, and skills

Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics

Architecture review and code modernization with adversarial analysis

Senior security engineer agent for finding vulnerabilities including injection, auth flaws, insecure crypto, SSRF, XSS, and common CWEs

Refactor and simplify code for clarity, consistency, and maintainability while preserving functionality

Systematic debugging workflow: reproduce first, write failing test, then fix

Specialized agents for writing tests and analyzing test coverage quality

Performance profiling, optimization, and dependency audit agents

Documentation engineering and specialized framework development agents

Session management tools for context window monitoring and conversation handoff

Audit, evaluate quality, and improve CLAUDE.md files. Captures session learnings and keeps project memory up to date.

Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.

Skills for designing and building MCP servers that work seamlessly with Claude — guides you through deployment models (remote HTTP, MCPB, local), tool design patterns, auth, and interactive MCP apps.

Build high-quality MCP servers using FastMCP or the MCP SDK

Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis.

Build, debug, and optimize Claude API and Anthropic SDK applications

Test local web applications with Playwright, taking screenshots, checking console logs, and automating browser interactions

Build complex HTML artifacts (React, Tailwind, shadcn/ui) with state management for inline rendering in Claude

Generates a visual HTML report summarizing Claude Code session activity, time spent, and usage anomalies

Automated code review for pull requests using multiple specialized agents with confidence-based scoring

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Create, read, edit, and manipulate PowerPoint presentations (.pptx files)

Open, read, edit, and create spreadsheets (.xlsx/.csv/.tsv)

Toolkit for styling artifacts (slides, docs, HTML) with themes. 10 pre-set themes with custom color palettes, typography, and design patterns.

Guide users through a structured workflow for co-authoring documentation, proposals, technical specs, and decision docs.

Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)

Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.

Audit plan files against codebase — gap detection, dead code verification, test coverage checks. Sub-commands: gaps, verify, tests.

Multi-round independent quality audit for Claude Code plugins: deep 7-criteria review with self-updating criteria, finding validation, user-gated fixes, fresh-reviewer convergence loop with hard cap, optional headless benchmark.

Prevents common subagent failure modes via task partitioning, output auditing, checkpoint management, and convention injection

Universal 8-phase implementation plan workflow with human approval gates for any plan type: feature, bug fix, refactoring, migration, security.

Systematic logic audit workflow: read every line of source code, find logic bugs, fix, update tests and docs, commit. Language and framework agnostic.

Draw UML/architecture diagrams from a codebase with minimal error through a 3-tier hard-gated pipeline (code-is-business-correct -> diagram-matches-code -> notation + readability), anchored on out-of-model oracles and human gates. Ships a skill, a guided slash command, and an adversarial diagram-verifier subagent.