Checkpoint
The Checkpoint skill verifies if a user’s response aligns with a specified prompt, ensuring accurate and consistent outputs for improved interactions.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add petekp-checkpoint npx -- -y @trustedskills/petekp-checkpoint
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"petekp-checkpoint": {
"command": "npx",
"args": [
"-y",
"@trustedskills/petekp-checkpoint"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill, petekp-checkpoint, provides a mechanism to pause and resume execution within an AI agent workflow. It allows users to save the current state of a process, effectively creating checkpoints that can be revisited later. This is particularly useful for long or complex tasks where interruptions are likely or experimentation requires resetting to specific points in time.
When to use it
- Long-running processes: When an agent task might take a significant amount of time (e.g., generating a large document, training a model).
- Experimentation and debugging: To easily revert to previous states while testing different approaches or troubleshooting issues.
- Interrupted workflows: If an agent's execution is frequently interrupted (due to resource constraints or network instability), checkpoints ensure progress isn’t lost.
- Complex multi-stage tasks: When a workflow involves several distinct steps, checkpoints allow restarting from any stage without redoing prior ones.
Key capabilities
- Save current state
- Resume execution from saved state
- Checkpoint management (create, list, delete)
Example prompts
- "Create a checkpoint named 'initial_draft'"
- "List all available checkpoints"
- "Resume from checkpoint 'model_training_v2'"
Tips & gotchas
The skill relies on the underlying agent framework to properly serialize and deserialize the state. Ensure that any external dependencies or resources used by the agent are also saved or restored appropriately when creating and resuming checkpoints.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.