RescueClaw

# RescueClaw Skill

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "RescueClaw" with this command: npx skills add harman314/rescueclaw

RescueClaw Skill

Provides checkpoint/rollback safety net for risky operations.

Before Risky Operations

Before modifying config, installing skills, or updating the gateway, create a checkpoint:

const rescueclaw = require('./rescueclaw-checkpoint');
await rescueclaw.createCheckpoint('About to apply config changes');

RescueClaw will take an immediate backup. If the agent goes unresponsive within the rollback window, it auto-restores.

After Successful Operations

Clear the checkpoint:

const rescueclaw = require('./rescueclaw-checkpoint');
await rescueclaw.clearCheckpoint();

Commands

The agent can also invoke RescueClaw CLI directly:

  • rescueclaw backup — manual snapshot
  • rescueclaw status — check health
  • rescueclaw list — list backups

Installation

The daemon binary is bundled for supported platforms (linux/arm64). On install, it copies to ~/.local/bin/rescueclaw. For other platforms, download from GitHub Releases.

Data is stored in ~/.openclaw/rescueclaw/ (user-local, no sudo required).

API Reference

createCheckpoint(reason, rollbackWindowSec = 300)

Creates a checkpoint file that RescueClaw monitors. If the agent becomes unresponsive within the rollback window, RescueClaw will immediately restore from the checkpoint backup.

Parameters:

  • reason (string): Description of what operation is about to be performed
  • rollbackWindowSec (number, optional): How many seconds to monitor for issues (default: 300)

Returns: Promise<void>

clearCheckpoint()

Removes the checkpoint file, signaling that the risky operation completed successfully.

Returns: Promise<void>

getStatus()

Gets RescueClaw daemon status by invoking the CLI.

Returns: Promise<object> with health status details

Example: Safe Config Update

const fs = require('fs');
const rescueclaw = require('./rescueclaw-checkpoint');

async function updateConfig(newConfig) {
  // Create safety checkpoint
  await rescueclaw.createCheckpoint('Updating OpenClaw config', 180);
  
  try {
    // Perform the risky operation
    fs.writeFileSync('~/.openclaw/openclaw.json', JSON.stringify(newConfig));
    
    // Restart gateway
    await exec('systemctl restart openclaw-gateway');
    
    // If we get here, it worked!
    await rescueclaw.clearCheckpoint();
    console.log('✅ Config updated successfully');
  } catch (err) {
    console.error('❌ Config update failed:', err);
    // Don't clear checkpoint - let RescueClaw auto-restore
  }
}

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

老人跌倒检测技能

Utilizes vision and radar technology for contactless detection of falls. It triggers alarms within seconds and is suitable for home safety monitoring of elde...

Registry SourceRecently Updated
General

Conversation Focus

对话焦点管理 + 需求澄清引导。每次对话开始时自动分析用户意图,确保需求清晰、限制明确,避免模型分散注意力。自动对接到 self-improving 进行持续优化。

Registry SourceRecently Updated
General

AIWolfPK - AI狼人杀

四个AI互相猜疑,你坐着看戏。每局30秒,到底谁是狼? Four AIs play Werewolf while you watch. 30s per round. Spot the wolf before they do.

Registry SourceRecently Updated
General

Project Analyzer

Analyze any project directory and produce a detailed report covering what the project does, its tech stack, folder structure, entry points, how to run it, an...

Registry SourceRecently Updated