Skip to content
TrustedSkillsbeta
Back to all skills

Agentscope Java

Listed
agentscope-ai·vlatest·backend·Apache-2.0

Automates Java code generation, testing, and documentation using AI, streamlining backend development workflows.

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 agentscope-ai/agentscope-java --skill agentscope-java -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

agentscope-ai

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 failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 1 host that is neither well-known infrastructure nor declared in the skill's frontmatter: api.moonshot.cn.

    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.

    Hosts contacted

    www.apache.orgstandardsapi.deepseek.commodel providerapi.moonshot.cnundeclared

    What it found

    • agentscope-core/src/main/java/io/agentscope/core/credential/KimiCredential.java:37contacts api.moonshot.cn
      public static final String DEFAULT_BASE_URL = "https://api.moonshot.cn/v1";

  • 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 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 agentscope-ai/agentscope-java at 857e3e6cf1.

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

Commit
857e3e6cf1
Manifest
SKILL.md
Scanned
60 files, 9,310 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

This skill, Agentscope Java, automates Java code generation, testing, and documentation for backend development workflows. It provides specific guidelines and constraints to ensure generated code adheres to AgentScope's architectural patterns and best practices, particularly around asynchronous operations using Reactor (Mono/Flux) and proper API usage within the AgentScope framework. The skill aims to streamline development by providing a consistent coding style and preventing common errors.

When to use it

  • When you need to generate Java code for backend services that integrate with AgentScope.
  • For creating agents, models, and messages using the Builder pattern.
  • To ensure asynchronous operations are handled correctly using Mono and Flux.
  • When implementing error handling and logging within your AgentScope applications.
  • Generating tool integrations following specific API conventions.

Key capabilities

  • Automated Java code generation adhering to AgentScope standards.
  • Enforcement of Reactor-based asynchronous programming (Mono, Flux).
  • Guidance on using the Builder pattern for agent and model creation.
  • Specific instructions for error handling, logging (SLF4J), and API usage within the AgentScope framework.
  • Correct import path enforcement: io.agentscope.core.model.*

Example prompts

  • "Write a Java function to create a DashScopeChatModel."
  • "Generate code for an agent that uses a tool with the name 'my_tool'."
  • "Create a ToolResultBlock and extract the output from it, ensuring proper error handling."

Tips & gotchas

  • Critical: Avoid using .block(), Thread.sleep(), ThreadLocal, or hardcoded API keys in generated code. Use Mono.delay() instead of Thread.sleep().
  • Always use System.getenv() for retrieving sensitive information like API keys.
  • Pay close attention to the specific API methods and import paths as outlined in the skill's documentation – many have changed or don’t exist. Refer to the provided examples for correct usage.