Skip to content
TrustedSkillsbeta
Back to all skills

Tbench

Checked
coder·vlatest·testing·AGPL-3.0

Tbench automatically generates diverse test cases for your code, improving reliability and catching edge-case bugs quickly.

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 coder/xum --skill tbench --full-depth -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

coder

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 coder/mux at 54082e00e3.

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

Commit
54082e00e3
Manifest
.xum/skills/tbench/SKILL.md
Scanned
1 file, 364 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 tbench skill provides a simple benchmarking tool for AI agents. It allows users to run predefined tests and measure performance metrics, offering insights into an agent's capabilities. This helps evaluate and compare different agent configurations or track improvements over time.

When to use it

  • Performance Evaluation: Assess the speed and accuracy of your AI agent on specific tasks.
  • Regression Testing: Ensure new changes don’t negatively impact existing functionality by running benchmarks before and after updates.
  • Configuration Tuning: Experiment with different settings or parameters to optimize an agent's performance.
  • Comparison Across Models: Compare the effectiveness of various AI models in a standardized environment.

Key capabilities

  • Predefined benchmark tests
  • Performance metric measurement
  • Standardized testing environment

Example prompts

  • "Run the 'basic_math' benchmark."
  • "Execute all available benchmarks and report results."
  • "Compare the performance of agent A versus agent B on the 'logic_puzzle' test."

Tips & gotchas

The tbench skill requires a properly configured AI agent environment to function correctly. Results are only meaningful when compared within the same testing conditions; variations in hardware or software can skew results.