Checkpoint
The Checkpoint skill verifies if a user’s response aligns with expected criteria, ensuring accuracy and consistency in interactions.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add anortham-checkpoint npx -- -y @trustedskills/anortham-checkpoint
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"anortham-checkpoint": {
"command": "npx",
"args": [
"-y",
"@trustedskills/anortham-checkpoint"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The anortham-checkpoint skill allows AI agents to pause their current task and save their progress. It creates a snapshot of the agent's state, including memory and context, enabling resumption later from that exact point. This is useful for long or complex tasks that may be interrupted.
When to use it
- Long processes: If an agent is performing a lengthy calculation or data analysis, checkpointing ensures progress isn’t lost if the process is interrupted.
- Complex workflows: For multi-step tasks with dependencies, checkpoints provide reliable recovery points in case of errors.
- Experimentation: Allows for easy rollback to previous states when testing different approaches within a task.
- Resource constraints: If an agent needs to be paused due to resource limitations (e.g., memory), checkpointing preserves its state for later continuation.
Key capabilities
- Save current state
- Resume from saved state
- Create checkpoints at specific points in a workflow
- Manage multiple checkpoints
Example prompts
- "Checkpoint my progress here."
- "Save the current state as 'draft_v1'."
- "Resume from checkpoint 'draft_v1'."
Tips & gotchas
The effectiveness of this skill depends on the agent's ability to accurately capture and restore its internal state. Ensure sufficient memory is available for storing checkpoints, especially for complex tasks with large context windows.
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.