repo-cleanup
について
repo-cleanupスキルは、ビルド成果物、一時ファイル、重複ファイルなどのリポジトリの不要物を体系的に削除し、散在するディレクトリを整理・統合します。リポジトリのメンテナンスを目的として設計されており、安全なクリーンアップ操作を実行し、.gitignoreファイルを更新します。開発者は、このスキルを使用して追跡されていないファイルをクリーンアップし、プロジェクト構造を整理することができます。
クイックインストール
Claude Code
推奨npx skills add vamseeachanta/workspace-hub/plugin add https://github.com/vamseeachanta/workspace-hubgit clone https://github.com/vamseeachanta/workspace-hub.git ~/.claude/skills/repo-cleanupこのコマンドをClaude Codeにコピー＆ペーストしてスキルをインストールします
ドキュメント
Repo Cleanup
When to Use
- Repository has accumulated build artifacts and temp files
- Multiple agent/coordination directories scattered in root
- Log files and coverage reports cluttering the workspace
- Need to consolidate prototype code and test outputs
- Preparing for a clean commit or release
- After major refactoring work
Related Skills
- module-based-refactor - For restructuring after cleanup
- session-start-routine - Session initialization
References
- Git clean documentation: https://git-scm.com/docs/git-clean
- Git rm documentation: https://git-scm.com/docs/git-rm
- Gitignore patterns: https://git-scm.com/docs/gitignore
Version History
- 2.2.0 (2026-01-20): Added Benchmark Cleanup and Plan File Archival patterns
- Added Benchmark Artifacts section for handling benchmark directories
- Added Plan Files section for archiving completed specifications
- Added benchmark patterns to .gitignore recommendations
- Updated checklist with benchmark and plan archival items
- 2.1.0 (2026-01-20): Added Final Cleanup Checklist and README Update Checklist
- Added Final Cleanup Checklist with verified DELETE/CONSOLIDATE/KEEP tables
- Confirmed .drcode/ as safe to delete (legacy AI config)
- Added .slash-commands/ consolidation to .claude/docs/commands/
- Added .git-commands/ consolidation to scripts/git/
- Added .benchmarks/ as safe to delete if empty
- Added README Update Checklist for structure documentation
- Added example README structure section template
- Added references to remove checklist
- 2.0.0 (2026-01-20): Major update with hidden folder cleanup learnings
- Added Hidden Folder Cleanup section with legacy AI folder patterns
- Added Consolidation Merge Strategies for conflict resolution
- Added File Count Verification for tracking consolidation progress
- Updated Cleanup Checklist with hidden folder review items
- Documented patterns for .agent-os, .ai, .agent-runtime, .common, .specify, .drcode, .slash-commands
- 1.0.0 (2025-01-20): Initial release based on digitalmodel repository cleanup session
Sub-Skills
Sub-Skills
- Version Metadata
- 1. Build Artifacts (+5)
- Agent Directories (+4)
- Common Hidden Folders (+2)
- Conflict Resolution Patterns (+2)
- Progress Tracking Commands (+1)
- List Untracked Files (+3)
- For Tracked Files (Use git rm) (+2)
- Gitignore Updates
- Pre-Cleanup (+7)
- Folders to DELETE (Confirmed Safe) (+3)
- Structure Section Updates (+1)
- References to Remove
GitHub リポジトリ
関連スキル
legal-sanity-review
その他This mandatory workflow scans code for legal risks like client names or proprietary references before cross-review. It blocks the review cycle if violations are found, requiring fixes first. Use it as a pre-gate for PR creation, code porting, or any cross-review trigger.
brainstorming
その他The brainstorming skill transforms initial ideas into detailed specifications through iterative questioning and collaborative dialogue. It helps developers explore design options, evaluate trade-offs, and create shared understanding before implementation. This prevents rework by systematically refining concepts into actionable plans.
repo-cleanup-progress-tracking-commands
その他This sub-skill provides shell commands for tracking file counts during repository cleanup operations, specifically for hidden folders like `.claude` and `.agent-os`. It includes verification scripts to ensure no files are lost after merging changes. Use it when consolidating or reorganizing project directories to monitor progress and validate results.
brainstorming-metrics
その他This skill provides structured metrics for evaluating brainstorming sessions, including targets for questions per design, validation rates, and stakeholder alignment. It helps developers measure brainstorming effectiveness and implementation quality. Use it to establish clear success criteria and track rework during project planning phases.