Browse plugins

This plugin provides a suite of .NET development tools including automatic CSharpier code formatting for C# files, dotnet-run-file for executing C# without projects, and skills for code analysis via Roslyn AST queries, API inspection, and code coverage reports. It hooks into Claude's post-edit workflow to format C# files automatically and exposes 9 skills for inspecting .NET libraries, analyzing code patterns, and diagnosing style violations.

A Claude Code plugin skill that teaches efficient CLI-based codebase search strategies using ripgrep, ast-grep, semgrep, fd, rga, tokei, and scc. It provides tool selection guidance, pattern recipes, and best practices for searching codebases of any size.

This Agent Skill performs automated security audits using OWASP Top 10, CWE Top 25 2025, and CVSS v4.0 standards for any project, with deep PHP/TYPO3 scanning across 80+ checkpoints and 19 reference guides. It integrates via a PreToolUse hook to flag risky commands and provides vulnerability assessment, risk scoring, secure coding guidance, and DevSecOps pipeline security.

This plugin provides Git and GitHub workflow automation through 4 agents and 7 skills, handling commits, pull requests, code reviews, and comment resolution with built-in safety hooks. It integrates validation tools for commit types, visual proof requirements, and AI attribution checks directly into your development workflow.

Ponytail is a Claude Code plugin that enforces minimal, production-ready solutions by prioritizing YAGNI principles, standard library usage, and avoiding unnecessary abstractions. It reduces code bloat, cost, and execution time while maintaining full safety guarantees through session-start and prompt-submit hooks that guide the agent toward simpler implementations.

This plugin provides guardrails and debugging tools for research workflows, catching AI mistakes in paper reproduction and experiment tracking before they become costly. It includes citation validation, LaTeX checking, timezone handling, and evidence-first experiment comparison through shell-based guards and hooks.

This plugin reviews changed code for redundancy, reuse opportunities, and over-engineering, then applies simplification fixes automatically. It runs as a pre-tool-use hook and uses Python to analyze and refactor code.

This plugin intercepts write operations and blocks a predefined list of AI buzzwords before they're used, helping developers maintain more authentic language in their code and documentation. It leverages Python-based hooks to filter and flag overused terminology in real time.

brooks-lint performs AI-driven code reviews grounded in twelve classic software engineering books, diagnosing six decay risk dimensions (cognitive overload, change propagation, knowledge duplication, accidental complexity, dependency disorder, and domain model distortion) with citations and remedies. It offers six analysis modes accessible via commands or natural language: PR review, architecture audit, tech debt assessment, test quality evaluation, health dashboards, and automated fixes.

Claude Octopus is a multi-LLM orchestration plugin that integrates up to ten external AI providers (Codex, Copilot, Qwen, Ollama, Perplexity, OpenRouter, OrcaRouter, OpenCode, Grok) alongside Claude for consensus-gated code review, research, and multi-model workflows. It provides 53 commands, 49 specialized agent personas, 62 reusable skills, and structured four-phase methodology (Discover→Define→Develop→Deliver) with quality gates, persistent memory integration, and autonomous pipeline execution.

This Agent Skill provides expert patterns for Git version control workflows including branching strategies (Git Flow, GitHub Flow, trunk-based), Conventional Commits conventions, collaborative pull request processes, and CI/CD integration with Git hooks for quality gates. It includes a `/pr-finish` command to drive pull requests to a fully-green merged state and works across Claude Code, Cursor, GitHub Copilot, and other skills-compatible AI agents.

dev-flow provides code review, automated fixes, commit management, and linting for development workflows through 2 agents and 6 skills integrated via hooks. It uses local tools (node, bash, python3) to run shell-based linting and code quality checks without external API dependencies.

This plugin provides idiomatic development assistance across eight major programming languages and frameworks: C#/.NET, Go, Java/Kotlin, Python, Rust, TypeScript, shell, and web technologies. It bundles one AI agent with eight skills to help developers follow language-specific best practices and conventions.

This skill automates migration of code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5, updating model strings, beta headers, and configuration details. It helps ensure compatibility with the latest model version and can be used iteratively to refine prompts after migration.

This plugin documents AI-generated codebases and audits them for security/performance gaps by comparing documented intent against actual implementation, producing a reviewer-ready shipping packet. It provides five commands to reverse-engineer architecture, map test coverage, and identify risks that generic scanners miss.

This plugin provides a single skill that encodes Python best practices from PEP 8, Zen of Python, Google style, and Effective Python guidelines. It helps developers write more Pythonic and maintainable code by applying established style and design principles.

This plugin provides a frontend development skill for React, Next.js, TypeScript, and Tailwind CSS projects, offering component scaffolding, bundle analysis, and performance optimization tools. It includes accessibility best practices guidance to help developers build production-ready, performant web applications.

A generic effort model for TYPO3 LTS major version upgrades that provides per-version risk multipliers, breaking-change baselines, compatibility matrices, and a 7-phase assessment workflow to estimate upgrade complexity. Users pair it with their own historical project data to calibrate effort estimates across extensions and versions.

This plugin provides 19 standalone Agent Skills covering architecture, engineering delivery, development discipline, debugging, code review, and AI/automation systems. The skills enable developers to tackle technical challenges across the full development lifecycle without requiring external API keys or third-party services.

This Agent Skill guides TYPO3 extension developers through systematic upgrades to newer LTS versions, covering deprecated API detection, automated PHP and non-PHP code migrations, and static analysis. It supports upgrade paths from TYPO3 v7 through v14 with structured commands, planning agents, and cross-platform compatibility.

This Agent Skill evaluates TYPO3 extensions for conformance to official v12/v13/v14 standards through automated validation of file structure, coding guidelines, PHP architecture, and testing patterns. It orchestrates specialized ecosystem skills for deep testing and documentation analysis, with fallback surface-level checks when specialized skills are unavailable.

This Claude Code plugin provides 14 domain-specific skills for OroCommerce v6.1 development, covering entities, datagrids, APIs, workflows, security, testing (Behat, PHPUnit, k6), and CI/CD pipelines. Each skill delivers version-pinned guidance and awareness of platform-specific pitfalls rather than generic tutorials.

This skill provides AST-native mutations for PHP code through nikic/php-parser, allowing agents to describe syntax changes that are validated and applied structurally rather than via regex or text replacement. Every edit is parsed, pretty-printed, and reparsed before being written atomically, preventing corruption from textual matches that miss syntactic boundaries.

A portable Agent Skill providing production-grade Go development patterns including cron scheduling with resilience wrappers, Docker integration, LDAP/Active Directory support, and comprehensive testing strategies with build tag isolation. This skill automatically triggers when building Go services, job schedulers, Docker clients, or systems requiring retry logic and observability.

An Agent Skill that modernizes PHP applications to PHP 8.x standards with type safety, static analysis (PHPStan, Rector), and PSR/PER-CS compliance through executable Python tools that emit structured verification reports and actionable recommendations. The skill includes binding guardrails against common pitfalls (e.g., no readonly on Doctrine entities, Rector only in dry-run mode) and supports project-archetype detection for Symfony apps, TYPO3 extensions, and monorepos.

This skill provides version-aware TypoScript, TSconfig, and Fluid reference lookup for TYPO3 projects (v12, v13, v14) with local caching and best-practice annotations to prevent hallucinated properties and deprecated syntax. It supports code review, migration guidance, debugging hints, and integration with project-specific lint rules.

This plugin analyzes development tasks and proposes a minimal agent team composition with defined roles, responsibilities, and work isolation, then creates the team after user confirmation. It optionally chains with an ADR-based planning skill to decompose tasks into structured implementation steps with dependencies and completion criteria.

This Agent Skill guides developers through TYPO3 Core contributions via Gerrit, providing workflows for code review, CI/CD debugging, commit message formatting, and quality assurance. It offers step-by-step assistance from account setup through patch submission with automated validation and best practices enforcement.

This skill teaches Claude agents to use Jujutsu (jj) as a safer local change-management layer while keeping Git as the canonical remote and PR interface, avoiding common agent mistakes like destructive resets and unclear commits. It includes runnable evaluations proving jj's advantages for speculative iterative work: reversible discards, non-blocking conflicts, non-interactive history surgery, and whole-repo time travel.

This plugin provides a skill for implementing test-driven development (TDD) workflows using the red-green-refactor cycle. It guides developers through writing failing tests first, then implementing code to pass those tests, and finally refactoring for quality.

This plugin provides a code-reviewer agent that performs systematic reviews against a base branch by analyzing diffs for critical issues and quality. It includes two skill strategies: disposable subagents for quick one-shot reviews and persistent team members for iterative follow-up questions.

This plugin enables Python scripting and AI-powered image generation within Claude using Google's Gemini models, with inline script dependencies managed through uv. It supports image generation, editing, and arbitrary Python script execution through heredoc-based workflows.

Systematically assesses projects against Netresearch checkpoint-enabled skills using scripted mechanical verification and domain-batched LLM review agents. Outputs structured JSON compliance reports with per-checkpoint status (pass/fail/skip/blocked) across domains like repo-health, security, code-quality, and documentation.

This plugin provides a comprehensive skill for building complex HTML artifacts with React, Tailwind CSS, and shadcn/ui components, supporting state management and routing. It enables developers to create elaborate multi-component interactive interfaces directly within Claude.