build-fix
01Command
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.
完整的 Claude Code 配置集合(agents, skills, hooks, commands, rules, MCPs)。源自 Anthropic 黑客松获胜者的实战配置,助力中文工程师高效理解与使用 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.
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).
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.
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.
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).
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.
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.
Command
A Go code review command that examines changed Go files for coding conventions, error handling, security, and concurrency problems.
Command
A Go testing command that follows test-driven development, or TDD: write a failing test, implement the smallest change that passes it, then improve the code.
Command
A command that exports learned coding habits, called instincts, into a shareable YAML file. YAML is a human-readable format often used for configuration and structured notes.
Command
A command for importing learned coding and workflow preferences from a local file or web address.
Command
A command that lists learned coding and workflow preferences, grouped by area, with a confidence score for each one.
Command
A command that reviews the current coding session and identifies reusable solutions, debugging methods, workarounds, or project-specific patterns worth saving as skills.
Command
Command "orchestrate" from codelably/harmony-claude-code, covering 编排(orchestrate)命令, 用法, 工作流类型, feature and bugfix.
Command
A planning command that restates a software request, identifies risks, and creates a step-by-step implementation plan. It requires the user to confirm the plan before code changes begin.
Command
A Python code review command that checks changed Python files for style, type, security, and common coding problems.
Command
A cleanup command that finds unused code and dependencies, writes a report, and recommends removals classified by risk. It requires tests before and after each deletion.
Command
A command for detecting and choosing the package manager used by a project. A package manager installs and manages JavaScript dependencies, such as npm, yarn, pnpm, or bun.
Command
A command that examines a repository's Git history and creates a SKILL.md file describing recurring coding patterns and team practices.
Command
Enforce test-driven development workflow. Scaffold interfaces, generate tests FIRST, then implement minimal code to pass. Ensure 80%+ coverage.
Command
A command that examines test coverage reports and creates tests for code paths that are not covered. Test coverage measures which parts of the code tests execute.
Command
A command that scans a codebase and updates short architecture maps describing its main files, dependencies, backend, frontend, and data structures.
Command
A command for synchronizing project documentation from source files that define the project's settings. It reads package scripts and example environment variables, then uses them to produce contributor and operations documents.
Command
Command "verify" from codelably/harmony-claude-code, covering 验证(verification)命令, 指令(instructions), 输出(output) and 参数(arguments).