Skip to content
TrustedSkillsbeta
Back to all skills

Checkpoint

Checked
anortham·vlatest·other

The Checkpoint skill verifies if a user’s response aligns with expected criteria, ensuring accuracy and consistency in 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 anortham/goldfish --skill checkpoint -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

anortham

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 anortham/goldfish at 2d42cf3fbc.

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

Commit
2d42cf3fbc
Manifest
skills/checkpoint/SKILL.md
Scanned
2 files, 212 lines
Copies in repo
2 — all of them scanned
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 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.