master-recovery

Analyze blocking reasons and apply recovery strategies to stalled AI agent tasks.

5|1|Updated Feb 4, 2026
One-click install
npx skills add https://github.com/Disaster-Terminator/RewardsCore --skill master-recovery
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: master-recovery
Source: https://github.com/Disaster-Terminator/RewardsCore/tree/main/.trae/archive/multi-agent/skills/master-recovery
Command: npx skills add https://github.com/Disaster-Terminator/RewardsCore --skill master-recovery

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a structured process for recovering AI tasks that have become blocked or stalled, ensuring that progress can be made even when unexpected issues arise.

Core Features & Use Cases

  • Automated Recovery Logic: Intelligently determines the type of blockage and applies a specific recovery strategy.
  • Contextual Resumption: Recovers tasks by gathering necessary context (e.g., DOM structure) or escalating to human intervention when logic is unimplementable.
  • Use Case: If an AI agent fails because it cannot find a specific element on a webpage, this Skill can automatically trigger a targeted search for that element and re-attempt the task, or flag it for human review if the problem is more complex.

Quick Start

Use the master-recovery skill to resume a blocked task by reading the .trae/blocked_reason.md file.

Frequently Asked Questions about master-recovery

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I resume stalled AI agent tasks automatically?

Automated recovery logic handles stalled AI agent tasks by analyzing blocking reasons and applying predefined strategies to gather missing context or re-attempt execution.

What is the workflow for recovering a blocked task after exhausted retries?

Recovering a blocked task after exhausted retries involves reading the `.trae/blocked_reason.md` file to determine the failure type and applying a targeted strategy like escalating to human operators.

How does error handling work for external service call failures in AI automation?

Error handling for external service call failures works by categorizing the blockage and applying specific recovery strategies, which may include interacting with other agents like `test-agent` or escalating to human operators.

How do I fix an AI task blocked by missing context or logic implementation failures?

To fix an AI task blocked by missing context or logic failures, the recovery process gathers necessary context such as DOM structure for targeted searches, or flags the issue for human review if the logic is unimplementable.

When should I escalate a blocked task to human operators instead of automated resumption?

You should escalate a blocked task to human operators when automated recovery strategies determine the logic implementation is unimplementable or missing context cannot be resolved through agent interactions.