Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计通过

eng-codebase-cleanupeng 代码库清理

Agent Skill

eng-codebase-cleanup 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

235

周安装

10

GitHub Stars

2

下载量

82
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:eng-codebase-cleanup(eng 代码库清理)
来源仓库:https://github.com/hungv47/agent-skills
仓库路径:skills/eng-codebase-cleanup
安装命令:
npx skills add https://github.com/hungv47/agent-skills --skill eng-codebase-cleanup
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/hungv47/agent-skills --skill eng-codebase-cleanup

简介

代码库清理用于在不破坏功能的前提下重组和优化代码结构。

  • 适合需要重构或维护遗留系统的工程场景。eng-codebase-cleanup 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 可自动识别入口点、配置文件和技术栈,生成清理方案。
  • 使用前需备份关键配置,避免误删重要依赖项。
  • 建议在隔离分支上操作,确保不影响主分支稳定性。

SKILL.md

Codebase Cleanup

Reorganize and clean codebases without breaking functionality.

Workflow

Phase 1: Analysis

Before touching anything, understand the codebase.

  1. Map the directory structure find. -type f -name "*.py" -o -name "*.js" -o -name "*.ts" -o -name "*.jsx" -o -name "*.tsx" | head -100 tree -L 3 -I 'node_modules|.git|__pycache__|.next|dist|build|venv|.venv' || find. -maxdepth 3 -type d | grep -v node_modules | grep -v.git
  2. Identify entry points and config files

- package.json, pyproject.toml, requirements.txt, Cargo.toml - Main entry files (index.*, main.*, app.*, server.*) - Config files (*.config.js,.env*, tsconfig.json)

  1. Run scripts/analyze_codebase.py to generate dependency report
  2. Ask clarifying questions if needed

- What is the primary tech stack? - Are there specific directories to preserve? - Any files that look dead but are actually used?

Phase 2: Identify Cleanup Targets

Safe to remove without verification:

  • Empty directories
  • .DS_Store, Thumbs.db, desktop.ini
  • Duplicate package lock files (keep one)
  • pycache,.pyc,.pyo files
  • node_modules/.cache
  • Coverage reports, test artifacts
  • Editor configs if inconsistent (.idea,.vscode with personal settings)
  • Backup files (*.bak, *.backup, *~, *.swp)
  • Log files (*.log)
  • Compiled outputs if source exists

Requires dependency check before removal:

  • Unused source files (verify no imports)
  • Orphan test files (verify not in test config)
  • Unused assets/images
  • Old migration files (check if applied)
  • Commented-out code blocks
  • Unused dependencies in package.json/requirements.txt

Never remove without explicit permission:

  • Config files (might be environment-specific)
  • Database files or migrations
  • CI/CD configs
  • License files
  • README or docs

Phase 3: Reorganization Patterns

Standard directory structures by stack:

JavaScript/TypeScript:

src/
  components/    # UI components
  pages/         # Page components or routes
  hooks/         # Custom hooks
  utils/         # Helper functions
  services/      # API calls, external services
  types/         # TypeScript types
  constants/     # Constants, enums
  assets/        # Static files
tests/
  unit/
  integration/

Python:

src/<package_name>/
  __init__.py
  core/          # Core business logic
  api/           # API routes/endpoints
  models/        # Data models
  services/      # Business services
  utils/         # Utilities
tests/
  unit/
  integration/
  fixtures/

File naming conventions:

  • Components: PascalCase (Button.tsx)
  • Utilities: camelCase (formatDate.ts)
  • Constants: UPPER_SNAKE_CASE or kebab-case file
  • Tests: *.test.ts, *.spec.ts, or test_*.py

Phase 4: Execute Changes

  1. Create backup commit before changes git add -A && git commit -m "Pre-cleanup snapshot" 2>/dev/null || echo "No git or nothing to commit"
  2. Remove safe-to-delete files first find. -name ".DS_Store" -delete 2>/dev/null find. -name "*.pyc" -delete 2>/dev/null find. -name "__pycache__" -type d -exec rm -rf {} + 2>/dev/null find. -type d -empty -delete 2>/dev/null
  3. Reorganize file structure

- Move files in batches by category - Update imports after each batch - Run tests or type checks between batches if available

  1. Update import paths

- Check all files for old import paths - Use grep to find remaining references to old paths - Verify build still works after import updates

  1. Remove dead code

- Check for unused functions/variables with the analyzer script - Remove commented-out code older than current work

Phase 5: Validation

  1. Run existing tests if available npm test 2>/dev/null || yarn test 2>/dev/null || pytest 2>/dev/null || echo "No test runner found"
  2. Run type checker if TypeScript npx tsc --noEmit 2>/dev/null || echo "TypeScript check skipped"
  3. Run linter if configured npm run lint 2>/dev/null || npx eslint. 2>/dev/null || echo "No linter found"
  4. Verify the app builds npm run build 2>/dev/null || yarn build 2>/dev/null || echo "Build check skipped"
  5. List manual verification needed for features that lack test coverage

Decision Rules

When to consolidate directories:

  • Fewer than 3 files with no clear growth path
  • Multiple directories with same purpose (utils, helpers, lib)
  • Deeply nested single-file directories

When to split directories:

  • More than 15-20 files in one directory
  • Mixed concerns in same directory
  • Files with different lifecycle

When NOT to reorganize:

  • Active feature development in that area
  • No test coverage for affected code
  • Team conventions exist (ask first)
  • Monorepo with workspace dependencies

Common Pitfalls

  • Moving files breaks dynamic imports (check for require variables, import())
  • Barrel files (index.ts re-exports) can hide dependency issues
  • CSS/SCSS imports may use relative paths
  • Asset paths in code may be hardcoded
  • Environment-specific configs might reference paths

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.36%
按下载量换算30

Claude

29.43%
按下载量换算24

Cursor

17.68%
按下载量换算14

Gemini CLI

9.05%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills