skills.rest
bobby-andris
bobby-andrisCOMMUNITY
Explore all skills by this author →
GitHub

checkpoint

Create persistent session checkpoints in Markdown files under .claude/checkpoints.

1|Updated Jan 23, 2026
Search Tags:#automation#workflow#context#resume#checkpoint#session
One-click install
npx skills add https://github.com/bobby-andris/Allied-FeedOps --skill checkpoint-bobby-andris
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: checkpoint
Source: https://github.com/bobby-andris/Allied-FeedOps/tree/main/.claude/skills/checkpoint
Command: npx skills add https://github.com/bobby-andris/Allied-FeedOps --skill checkpoint-bobby-andris

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Save session state proactively to prevent context overflow and enable seamless resumption across long AI sessions.

Core Features & Use Cases

  • Create checkpoints at key milestones to prevent loss of context during long, multi-turn workflows.
  • Resume work quickly by reloading the last checkpoint and continuing where you left off.
  • Organize checkpoints in .claude/checkpoints with clear metadata for quick restoration.

Quick Start

Create a checkpoint of the current session by writing a Markdown file under .claude/checkpoints.

Frequently Asked Questions about checkpoint

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

FAQPage Schema
How do I save AI session state to prevent context overflow during long workflows?▼

To prevent context overflow, you can create a persistent checkpoint of the current AI session. This proactively saves session state into a Markdown file, allowing you to resume long-running, multi-turn workflows seamlessly.

When do I need to create a checkpoint for my AI session?▼

You need to create a checkpoint at key milestones during long-running, multi-turn tasks where session continuity is critical. This prevents the loss of context and enables quick restoration of your work.

What do I need to set up before creating session checkpoints?▼

You need a writable .claude/checkpoints directory in your environment. The checkpoint is saved as a standardized Markdown file containing metadata for status, date, and context usage.

How do I resume work after reaching a context limit in a multi-turn task?▼

To resume work after reaching a context limit, reload the last saved checkpoint from the .claude/checkpoints directory. This restores the previous session state so you can continue exactly where you left off.

What is the best way to organize AI session checkpoints for quick restoration?▼

The best way to organize session checkpoints is to save them as standardized Markdown files within a dedicated .claude/checkpoints directory. Including clear metadata for status, date, and context usage ensures quick restoration.

Why does my AI lose context in long-running multi-turn workflows?▼

Your AI loses context in long-running workflows due to context overflow limits. Automatically creating persistent checkpoints at key milestones prevents this loss by saving session state externally.

Related Skills

Explore More Content & Communication Skills→
hlibkovalhlibkoval
1

plugins-doc

Deliver official Claude Code plugins documentation covering component schemas and marketplace integration.

Community
Advanced
yashs33244yashs33244
1

context-restore

Restore the latest saved working context from /context-save into the active workflow.

Community
Intermediate
e-stpierree-stpierre
1

af-create-checkpoint

Store and index structured workflow checkpoints with workflow-id, step, status, and context.

Community
Intermediate
maslennikov-igmaslennikov-ig
243

save-session-context

Save current health orchestrator workflow state to a context file.

Community
Basic