Skip to content
TrustedSkillsbeta
Back to all skills

Agentscope

Checked
changxubo·vlatest·agents·MIT

Agentscope helps you analyze and refine your AI agent’s behavior by providing a structured framework for defining goals & constraints, boosting performance.

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 changxubo/agentscope-python --skill agentscope -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

changxubo

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 changxubo/agentscope-python at bb2ec86500.

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

Commit
bb2ec86500
Manifest
SKILL.md
Scanned
21 files, 5,178 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 agentscope skill provides a way to define and manage the scope of an AI agent's actions. It allows you to restrict what tools or functions an agent can access, preventing unintended consequences and improving safety. This is achieved through configuration files that specify allowed resources for the agent to utilize during its operation.

When to use it

  • Restricting Access: Limit an agent’s ability to interact with sensitive data or systems (e.g., financial accounts) by defining a narrow scope of permitted actions.
  • Sandboxing Experiments: Safely test new tools or functionalities within a controlled environment, preventing the agent from impacting other parts of your system.
  • Role-Playing Scenarios: Define specific roles for agents with limited capabilities to simulate realistic interactions and workflows.
  • Controlled Environments: Ensure an agent only operates within predefined boundaries when deployed in production environments.

Key capabilities

  • Scope definition via configuration files.
  • Resource restriction based on defined scopes.
  • Agent action limitation.

Example prompts

  • "Apply the 'finance_only' scope to this agent."
  • "What tools are available within the 'marketing' scope?"
  • "Enforce the 'read_only' scope for this task."

Tips & gotchas

The effectiveness of agentscope relies on accurate and comprehensive configuration files. Ensure that all necessary resources are explicitly listed to avoid unexpected behavior or errors during agent execution.