Stats
Actions
Tags
How this skill is triggered — by the user, by Claude, or both
Slash command
/bluecore:guardThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- 本番環境作業・エージェント自律実行・特定ディレクトリ制限・機密性高い操作(マイグレーション/デプロイ/データ変更)
rm -rf (/, ~, プロジェクトルート)git push --force / git reset --hard / git checkout .DROP TABLE / DROP DATABASEdocker system prune / kubectl deletechmod 777 / sudo rm / npm publish--no-verify を含む任意コマンド検知時→コマンド内容提示・確認要求・安全な代替案提案。
PreToolUse フックで Bash/Write/Edit/MultiEdit を検知。コマンド・パスを有効ルールと照合後、実行許可。
search: guard block prevent dangerous / {command_pattern} block risk
record: {"event_type": "guard-block", "content": "Blocked: {command}. Reason: {reason}. Alternative: {alternative}"}
npx claudepluginhub aokumablue/bluecore --plugin bluecoreGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.