Skip to content
TrustedSkillsbeta
Back to all skills

Loop Agent

Checked
d-o-hub·vlatest·agents·MIT

Loop-Agent automates repetitive tasks by continuously executing workflows until a defined goal is achieved.

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 d-o-hub/rust-self-learning-memory --skill loop-agent -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

d-o-hub

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 d-o-hub/rust-self-learning-memory at da7210f59b.

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

Commit
da7210f59b
Manifest
.agents/skills/loop-agent/SKILL.md
Scanned
6 files, 285 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 loop-agent skill enables an AI agent to repeatedly execute a task, accumulating knowledge and improving performance over time. It leverages Rust's self-learning memory capabilities to retain information from each iteration. This allows for complex workflows that require iterative refinement or learning from experience.

When to use it

  • Data Enrichment: Repeatedly query an API with slightly modified parameters to gather a more complete dataset.
  • Iterative Refinement: Generate content (e.g., code, writing) and then refine it based on feedback received in subsequent loops.
  • Adaptive Learning: Train a model by repeatedly presenting examples and adjusting the training process based on observed performance.
  • Complex Research Tasks: Break down large research projects into smaller, iterative steps where each step builds upon the previous one.

Key capabilities

  • Rust-based implementation for efficiency and reliability.
  • Self-learning memory to retain information across iterations.
  • Iterative task execution with feedback loops.
  • Adaptable workflow based on accumulated knowledge.

Example prompts

  • "Run this script 5 times, saving the results of each run."
  • "Generate a poem and then rewrite it three times, improving its structure each time."
  • "Train this classification model for 10 epochs, adjusting the learning rate after each epoch."

Tips & gotchas

The skill's effectiveness depends on clearly defining the task and feedback mechanism within each loop. Ensure that the agent has sufficient memory capacity to store information from multiple iterations.