← Browse

@smallnest/hello-world

A

A fundamental skill that demonstrates the basic execution of a Python script. It serves as a "Hello, World!" example for the skill system, verifying that the environment is correctly set up and that the agent can execute scripts.

skillclaude

Install

agr install @smallnest/hello-world --target claude

Writes 1 file into .claude/skills/, pinned to git-55576c32.

  • .claude/skills/hello-world/SKILL.md

Document


name: hello_world description: A fundamental skill that demonstrates the basic execution of a Python script. It serves as a "Hello, World!" example for the skill system, verifying that the environment is correctly set up and that the agent can execute scripts. version: 1.0.0 license: MIT

Overview

The hello_world skill is the simplest possible skill in the ecosystem. Its primary purpose is to validate the operational status of the skill runner and the agent's ability to invoke tools.

Functionality

When invoked, this skill executes a Python script that prints a greeting message to the standard output. This confirms:

  1. Script Execution: The agent can successfully locate and run a Python script.
  2. Output Capture: The system can capture the standard output from the script and return it to the agent.
  3. Tool Integration: The skill is correctly registered and accessible as a tool.

Usage

This skill is typically used in the following scenarios:

  • System Health Check: To verify that the agent and skill runner are functioning correctly.
  • Onboarding: As a first step for developers learning how to create and use skills.
  • Debugging: To isolate issues with script execution or tool invocation.

Example Command

To use this skill, the agent can execute the following command:

scripts/hello.py

Implementation Details

The skill consists of a single Python script hello.py which performs a simple print operation. No external dependencies or complex logic are involved, ensuring that any failure is likely due to the environment or configuration rather than the skill itself.

Trustgrade A

  • passBody integrity

    Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.

  • passType matchnot applicable to this artifact type

    Whether the artifact is really the kind of thing its metadata claims it is.

  • passFreshness

    How long since the source repository was last pushed to.

  • passPrompt injection

    Scans the artifact's own text for instructions aimed at your agent rather than at you.

  • passLicense

    Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

  • Aevery check passed
  • Bone warning
  • Ctwo warnings
  • Dprompt injection or body integrity failed, or three warnings
  • Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

  • git-55576c32a96c2026-07-31