ワンクリックで
memory-backup
Backup CLAUDE.md, TASKS.md, and memory/ to a private Git repo using `bash .claude/skills/memory-backup/backup.sh`.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Backup CLAUDE.md, TASKS.md, and memory/ to a private Git repo using `bash .claude/skills/memory-backup/backup.sh`.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Build today's mapped ZEP time-log plan from Google Calendar, preview it against ZEP, and enter it through guarded Playwright automation only after explicit approval.
Help users create structured decision matrices by suggesting criteria, options, and weights — output as comparison tables
Pull recent Notion Journal entries into memory/journals/YYYY/month_YYYY-MM_text.txt.
Fetches live prices for equities and forex for investment portfolio.
Sync work context from external sources, update tasks and memory, and report changes
Process pasted meeting notes, infer context, extract candidate tasks and memory updates, and ask for confirmation before making changes.
| name | memory-backup |
| description | Backup CLAUDE.md, TASKS.md, and memory/ to a private Git repo using `bash .claude/skills/memory-backup/backup.sh`. |
Run the backup script for the current workspace. It syncs only:
CLAUDE.mdTASKS.mdmemory/Use Bash to run the script directly:
bash .claude/skills/memory-backup/backup.sh # push local memory to backup repo
bash .claude/skills/memory-backup/backup.sh --pull # pull latest backup into this workspace
bash .claude/skills/memory-backup/backup.sh --sync # pull latest, then push local memory
bash .claude/skills/memory-backup/backup.sh --dry-run # preview push
Do not run memory-backup itself as a shell command; it is just the skill name.
Set MEMORY_BACKUP_DIR in your workspace .env file to the local path of a separate Git clone for your private backup repo.
Example:
MEMORY_BACKUP_DIR=/your/path/to/memory-backups/
Requirements for MEMORY_BACKUP_DIR:
The script is the only thing that should perform the backup. Do not manually reconstruct the copy, add, commit, or push flow with ad hoc shell commands unless the user explicitly asks to debug the script itself.
MEMORY_BACKUP_DIR from the environment or workspace .envCLAUDE.md, TASKS.md, and memory/ into the backup repo, commits only if changed, then pushesgit pull --ff-only in the backup repo, then copies those files into the workspaceCLAUDE.md, TASKS.md, or memory/TASKS.md or memory/ do not exist, the script skips them cleanly.