autopilot-recovery

Name: autopilot-recovery
Availability: InStock
Author: lorainwings

Scan checkpoints and select a valid resume point for autopilot crash recovery.

3|1|Updated Feb 26, 2026

Search Tags:#automation #git #checkpoints #recovery #autopilot #state-snapshot #recovery-decision

Ready to run

npx skills add https://github.com/lorainwings/claude-autopilot --skill autopilot-recovery

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: autopilot-recovery
Source: https://github.com/lorainwings/claude-autopilot/tree/main/plugins/spec-autopilot/skills/autopilot-recovery
Command: npx skills add https://github.com/lorainwings/claude-autopilot --skill autopilot-recovery

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Crash recovery for the autopilot orchestrator by scanning checkpoints and determining the optimal resume point to minimize downtime and lost progress.

Core Features & Use Cases

Deterministic recovery decisions using the recovery-decision.sh script to evaluate checkpoints
Canonical recovery artifacts around state-snapshot.json, including validity checks and replay data
Multi-path restoration with checks for gaps, git risks, and anchor SHA validity, plus fallback to phase-context snapshots when needed
Context reconstruction from phase-context snapshots and mode-aware restoration to preserve workflow integrity
Guidance for automatic vs. manual recovery decisions and cleanups of artifacts during restore

Quick Start

Initiate the crash recovery workflow to determine the best resume point for the autopilot session.

Frequently Asked Questions about autopilot-recovery

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

FAQPage Schema

How do I recover an automation session after a crash using checkpoints?▼

To recover an automation session after a crash, scan existing checkpoints to evaluate validity and select the optimal resume point. The workflow validates state-snapshot integrity and reconstructs the phase context to minimize lost progress.

How does state-snapshot validation work during orchestrator recovery?▼

State-snapshot validation works by checking the state-snapshot.json file and verifying the anchor SHA during recovery. This deterministic process identifies gaps or git risks before safely restoring the session to a valid resume point.

What is the best way to resume an autopilot workflow from a corrupted state?▼

The best way to resume an autopilot workflow from a corrupted state is to use fallback phase-context snapshots. If the primary state-snapshot fails validation, the recovery logic reconstructs the session context from these phase-specific snapshots.

Can I automate cleanup of recovery artifacts when restoring a session?▼

Yes, you can automate cleanup of recovery artifacts when restoring a session. The mode-aware restoration process includes optional cleanups and user prompts to safely remove obsolete checkpoints and maintain workflow integrity.

When should I use manual recovery decisions instead of automatic restoration?▼

You should use manual recovery decisions instead of automatic restoration when complex git risks or checkpoint gaps are detected. The deterministic recovery logic provides guidance for evaluating these edge cases before safely proceeding.

Does crash-safe orchestration require git anchors for state snapshots?▼

Yes, crash-safe orchestration requires git anchors for state snapshots. The recovery-decision logic validates state-snapshot data against an anchor SHA to ensure checkpoint integrity and prevent replaying corrupted workflow states.