preserving-context

Capture structured checkpoints of task progress before context compaction.

2|Updated Jan 29, 2026

Search Tags:#productivity #checkpointing #task-tracking #context-switching #context-preservation #resume-work

Ready to run

npx skills add https://github.com/oryanmoshe/agent-skills --skill preserving-context

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: preserving-context
Source: https://github.com/oryanmoshe/agent-skills/tree/main/skills/preserving-context
Command: npx skills add https://github.com/oryanmoshe/agent-skills --skill preserving-context

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Capture state proactively, not reactively. Before compaction or task switches, write down everything needed to resume seamlessly. If you wait until after compaction, the context is already gone.

Core Features & Use Cases

Checkpoint data that records: current task, file path, progress, completed items, remaining steps, decisions, blockers, and test state.
Supports resuming work across sessions and context switches by loading checkpoints into the agent's context.
Integrates with tracking-tasks to align task status with preserved context.

Quick Start

Create a checkpoint of your current task to persist across context compaction and resume later.

Frequently Asked Questions about preserving-context

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

FAQPage Schema

How do I preserve context and resume work after a session compaction?▼

To preserve context and resume work, you create a structured checkpoint before compaction occurs. This checkpoint captures your current task, file path, progress, completed items, and remaining steps, enabling seamless resumption once the session context is lost.

What is context checkpointing for multi-file tasks?▼

Context checkpointing is the process of proactively saving your task state, including current file, progress, decisions, blockers, and test state. It prevents data loss during context switches across long-running, multi-file software engineering sessions.

When should I create a checkpoint to avoid losing my task progress?▼

You should create a checkpoint proactively before context compaction or task switches. Waiting until after compaction means the context is already gone, so you must capture the state beforehand to resume seamlessly later.

What data do I need to include in a task checkpoint schema?▼

A task checkpoint schema should include the current task, file path, progress, completed items, remaining steps, decisions, blockers, and test state. This structured data ensures the agent can reload the full context.

Can I use checkpointing to track task status alongside preserving context?▼

Yes, you can use checkpointing to track task status by integrating with task-tracking tools. This aligns your task status updates with the preserved context, ensuring progress and remaining steps stay synchronized.