obsidian-sync
Obsidian Sync
State file: ~/.openclaw/skill-state/obsidian-sync/state.yaml
Your agent's memory should be readable by you, not just by the agent.
When to Use
- On 10pm nightly cron wakeup
- When the user asks to sync notes to Obsidian
- After a major task completion worth archiving
Setup (First Run)
On first run, ask the user for their vault path and write it to state as vault_path. Do not proceed until this is set.
The Sync Process
Step 1: Read Agent Memory
- Read today's
memory/YYYY-MM-DD.md - Read
MEMORY.md(long-term memory)
Step 2: Write to Vault
- Copy
memory/YYYY-MM-DD.md→<vault_path>/OpenClaw/Daily/YYYY-MM-DD.md - Copy
MEMORY.md→<vault_path>/OpenClaw/Memory.md - Create
<vault_path>/OpenClaw/directory if it doesn't exist
Step 3: Update State
Write last_sync_at, notes_written (count of files written), vault_path to state.
Cron Wakeup Behavior
On 10pm wakeup:
- Check
vault_pathin state — if empty, skip and notify user to set it - Check
last_sync_at— if today, skip - Otherwise run sync
Key Principles
- Never overwrite vault files the user has manually edited — append-only to Daily notes
- If the vault path doesn't exist, warn the user rather than creating it silently
- Keep the OpenClaw folder structure flat and simple
More from archieindian/openclaw-superpowers
context-window-management
Prevents context overflow on long-running OpenClaw sessions. Use when approaching context limits.
26heartbeat-governor
Enforces per-skill execution budgets for scheduled cron skills — pauses runaway skills that exceed their token or wall-clock budget before they drain your monthly API allowance.
25using-superpowers
Bootstrap skill — teaches the agent how to find and invoke skills. Use when starting any new task or session.
20long-running-task-management
Breaks multi-hour tasks into checkpointed stages with resume capability. Use when a task is expected to take more than 30 minutes or multiple sessions.
19fact-check-before-trust
Triggers a secondary verification pass for any agent output containing factual claims, numbers, dates, or named entities before the output is acted on
19agent-self-recovery
Detects when the agent is stuck in a loop and escapes systematically. Use when you notice repeated failures or loss of direction.
18