hidden-folder-audit-migrate-agent-os-to-claude
について
このスキルは、従来の`.agent-os`および`.ai`ディレクトリを、エージェントとプロンプト管理のための新しい`.claude`構造へ移行します。ファイルのコピー処理、必要なディレクトリの作成、無効なシンボリックリンクのクリーンアップを含みます。古いClaude Codeプロジェクトを現在の組織標準にアップグレードする際にご利用ください。
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/hidden-folder-audit-migrate-agent-os-to-claude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
Migrate .agent-os to .claude (+4)
Migrate .agent-os to .claude
# Backup first
cp -r .agent-os .agent-os.backup
# Migrate agents
mkdir -p .claude/agents
cp -r .agent-os/agents/* .claude/agents/ 2>/dev/null
# Migrate standards (if applicable)
mkdir -p .claude/standards
*See sub-skills for full details.*
## Migrate .ai to .claude
```bash
# Backup first
cp -r .ai .ai.backup
# Migrate prompts to skills
mkdir -p .claude/skills/prompts
cp -r .ai/prompts/* .claude/skills/prompts/ 2>/dev/null
# Migrate config
cp .ai/config.* .claude/ 2>/dev/null
# Cleanup
git rm -r --cached .ai/ 2>/dev/null
rm -rf .ai
Clean Dead Symlinks
# Find broken symlinks
find . -maxdepth 2 -type l ! -exec test -e {} \; -print
# Remove broken symlinks
find . -maxdepth 2 -type l ! -exec test -e {} \; -delete
# Remove specific dead symlink folder
rm -rf .agent-runtime
Consolidate Runtime Directories
# Create standard runtime directory
# Migrate coordination data
# Remove old directories
rm -rf .coordination .session
Update .gitignore
Add these patterns after consolidation:
# Runtime and state (not tracked)
.coordination/
.session/
# Legacy folders (prevent re-creation)
.agent-os/
.ai/
*See sub-skills for full details.*
GitHub リポジトリ
関連スキル
himalaya-email-manager
コミュニケーションThis Claude Skill enables email management through the Himalaya CLI tool using IMAP. It allows developers to search, summarize, and delete emails from an IMAP account with natural language queries. Use it for automated email workflows like getting daily summaries or performing batch operations directly from Claude.
sglang
メタSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
evaluating-llms-harness
テストThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
cloudflare-turnstile
メタThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
