Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Persist agent state across crashes, context deaths, and restarts. Use when you need to save current context, restore after a crash, maintain a memory file ac...
Persist agent state across crashes, context deaths, and restarts. Use when you need to save current context, restore after a crash, maintain a memory file ac...
This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file.
Use the source page and any available docs to guide the install because the item currently does not return a direct package file.
I tried to install a skill package from Yavira, but the item currently does not return a direct package file. Inspect the source page and any extracted docs, then tell me what you can confirm and any manual steps still required.
I tried to upgrade a skill package from Yavira, but the item currently does not return a direct package file. Compare the source page and any extracted docs with my current installation, then summarize what changed and what manual follow-up I still need.
Survive context death. Every autonomous agent eventually hits its context window limit and "dies." This skill ensures you wake up knowing exactly what you were doing.
OpenClaw agents get persistent sessions, but context windows still have limits. When you fill up and restart, you need a reliable handoff mechanism. Wake State gives you: Structured state files β not just raw text, but parseable key-value state Auto-snapshots β save state on every loop iteration automatically Crash detection β know if your last session ended cleanly or crashed Task queue β persistent TODO list that survives restarts Checkpoint/restore β save named checkpoints and roll back to them
python3 {baseDir}/scripts/wakestate.py save --status "Building budget tracker skill" --task "Finish skill #1, then start skill #2" --note "Travis approved new direction at 16:45 UTC"
python3 {baseDir}/scripts/wakestate.py read
python3 {baseDir}/scripts/wakestate.py task-add --task "Build security scanner skill" --priority high
python3 {baseDir}/scripts/wakestate.py task-done --id 1
python3 {baseDir}/scripts/wakestate.py tasks
python3 {baseDir}/scripts/wakestate.py checkpoint --name "pre-migration"
python3 {baseDir}/scripts/wakestate.py restore --name "pre-migration"
python3 {baseDir}/scripts/wakestate.py heartbeat
python3 {baseDir}/scripts/wakestate.py crash-check
python3 {baseDir}/scripts/wakestate.py set --key "moltbook_status" --value "pending_claim"
python3 {baseDir}/scripts/wakestate.py get --key "moltbook_status"
State stored in ~/.openclaw/wake-state/ by default: state.json β current state (status, notes, key-values) tasks.json β persistent task queue checkpoints/ β named checkpoint snapshots heartbeat.json β crash detection timestamps
On startup, your agent should: Run crash-check to see if the last session ended cleanly Run read to get the current state Run tasks to see pending work Resume from where you left off
Call heartbeat every loop iteration β this is how crash detection works Call save at the end of every major task completion Use checkpoints before risky operations (migrations, deploys) Keep status descriptions short but specific The task queue survives restarts β use it instead of mental notes
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.