codelably

codelably/harmony-claude-code

Plugin Claude Code

Plugin marketplace listing 1 plugin: everything-claude-code.

codelably/harmony-claude-code

Plugin Claude Code

Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use.

codelably/harmony-claude-code

Skill Claude CodeCodex

A Chinese-language meta-manager skill for finding, installing, updating, and mapping other skills. A skill is a reusable set of instructions that extends an agent's working environment.

codelably/harmony-claude-code

Agent

A software-architecture agent for designing systems, planning large refactors, and recording technical decisions and trade-offs.

codelably/harmony-claude-code

Agent

A coding agent focused on fixing TypeScript, compiler, dependency, configuration, and build errors with the smallest practical code changes.

codelably/harmony-claude-code

Agent

A general code-review assistant that examines recent changes for code quality, security, maintainability, performance, testing, and accessibility. It focuses on modified files and organizes findings by critical issues, warnings, and suggestions.

codelably/harmony-claude-code

Agent

An AI reviewer focused on PostgreSQL databases, which are systems for storing and querying structured application data. It reviews queries, database structure, security, connections, concurrency, and monitoring, including Supabase practices.

codelably/harmony-claude-code

Agent

A documentation assistant that examines a codebase and keeps its README, guides, and code maps aligned with the actual structure. A code map is a written overview of modules, entry points, dependencies, routes, data models, and background workers.

codelably/harmony-claude-code

Agent

An end-to-end testing specialist for checking complete user journeys in a web browser. End-to-end tests operate the application like a user, using Vercel Agent Browser first and Playwright as a fallback.

codelably/harmony-claude-code

Agent

A Go troubleshooting specialist for build failures, compiler errors, vet findings, and linter warnings. It favors small code changes while checking dependencies and common type or interface problems.

codelably/harmony-claude-code

Agent

A Go code-review agent for checking Go changes, including style, concurrency, error handling, performance, and security issues.

codelably/harmony-claude-code

Agent

A specialist guide for building native HarmonyOS apps with ArkTS and ArkUI, which are Huawei's programming language and user-interface framework for apps. It requires specific modern approaches to state management and screen navigation.

codelably/harmony-claude-code

Agent

A planning assistant for new features, architecture changes, and large refactors. It turns a broad request into ordered implementation steps with affected files, dependencies, risks, tests, and acceptance criteria.

codelably/harmony-claude-code

Agent

Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.

codelably/harmony-claude-code

Agent

A code-cleanup assistant that finds unused code, duplicate logic, unused exports, imports, files, and npm packages, then helps remove or combine them.

codelably/harmony-claude-code

Agent

A security review assistant for web application code, configurations, and dependencies. It looks for exposed secrets, unsafe input handling, access-control problems, vulnerable packages, and common OWASP Top 10 issues, which are widely recognized web security risks.

codelably/harmony-claude-code

Agent

A test-driven development assistant that follows the practice of writing a failing test before the implementation, then making it pass and improving the code. TDD means test-driven development, commonly described as the red-green-refactor cycle.

codelably/harmony-claude-code

Command

A command that runs a TypeScript project build, explains its errors, fixes them one at a time, and runs the build again to verify the fixes.

codelably/harmony-claude-code

Command

Command "checkpoint" from codelably/harmony-claude-code, covering 检查点（checkpoint）指令, 用法, 创建检查点（create checkpoint）, 验证检查点（verify checkpoint） and 列出检查点（list checkpoints）.

codelably/harmony-claude-code

Command

A command that reviews uncommitted code changes for security, quality, maintainability, performance, testing, and accessibility issues. It reports each finding with a severity, file location, explanation, and suggested fix.

codelably/harmony-claude-code

Command

A command for creating and running end-to-end tests with Playwright. End-to-end tests imitate complete user journeys, such as logging in, searching, or paying, across the application’s interface and backend.

codelably/harmony-claude-code

Command

Command "eval" from codelably/harmony-claude-code, covering 评测命令（eval command）, 用法（usage）, 定义评测（define evals）, eval: feature-name and 能力评测（capability evals）.

codelably/harmony-claude-code

Command

A command that groups related learned instincts—short rules about recurring coding behavior—into higher-level skills, commands, or agents. It can analyze all instincts or limit the analysis to a named domain.

codelably/harmony-claude-code

Command

A command for diagnosing and fixing Go build errors, vet warnings, and linter problems in small, incremental changes. Go is a programming language, and these tools check whether Go code builds and follows common rules.