Skip to content
TrustedSkillsbeta
Back to all skills

Checkpoint

Checked
htlin222·vlatest·other·MIT

This "Checkpoint" skill verifies if a prompt adheres to specific constraints, ensuring consistent and reliable outputs for your AI interactions.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add htlin222/dotfiles --skill checkpoint --full-depth -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

htlin222

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned htlin222/dotfiles at b7604b0cf6.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
b7604b0cf6
Manifest
claude.symlink/archived-skills/checkpoint/SKILL.md
Scanned
1 file, 88 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The checkpoint skill allows an AI agent to save its current state and later restore that state. This is useful for long-running tasks or when an agent needs to resume work after interruption. It enables the agent to remember previous steps, decisions, or data, ensuring continuity in complex workflows.

When to use it

  • Long Task Resumption: If a task might be interrupted (e.g., due to network issues), checkpointing allows resuming from where it left off.
  • Experimentation & Rollback: An agent can create checkpoints before trying risky actions, allowing for easy rollback if things go wrong.
  • Complex Workflows: For multi-stage processes, checkpoints ensure that the agent doesn't lose progress in any stage.
  • Debugging: Checkpoints provide snapshots of the agent’s state which are useful when troubleshooting unexpected behavior.

Key capabilities

  • State saving and restoration
  • Workflow continuity
  • Rollback functionality
  • Snapshot creation

Example prompts

  • "Create a checkpoint before I start generating this report."
  • "Restore my last checkpoint."
  • "Save the current state as 'draft_v1'."
  • “Go back to the ‘planning’ checkpoint.”

Tips & gotchas

The effectiveness of checkpoint depends on how well the agent's internal state is captured. Ensure that any external dependencies or resources are also saved or restored alongside the agent's core state for complete recovery.