🧪 Tbench
This skill helps you run, customize, and analyze Terminal-Bench benchmarks for mux agents in CI or Daytona cloud with tailored experiments.
npx playbooks add skill coder/mux --skill tbench
About Tbench
Use Tbench to configure Claude Code, Cursor, or Copilot for testing & qa: it this skill helps you run, customize, and analyze terminal-bench benchmarks for mux agents in ci or daytona cloud with tailored experiments.
This compact 21-word instruction set is purpose-built for testing & qa work in AI coding agents. Install with a single command.
Use Cases
- Writing unit, integration, and end-to-end tests
- Setting up test coverage and CI pipelines
- Refactoring legacy code with confidence using tests
- Creating test plans and QA checklists
Example Prompts
System Prompt (21 words)
This skill helps you run, customize, and analyze Terminal-Bench benchmarks for mux agents in CI or Daytona cloud with tailored experiments.
Frequently Asked Questions
What is Tbench?
Tbench is a free testing & qa skill for AI coding agents. This skill helps you run, customize, and analyze Terminal-Bench benchmarks for mux agents in CI or Daytona cloud with tailored experiments.. It provides a specialized system prompt that configures your agent with testing & qa expertise.
How do I use Tbench with Claude Code?
Run npx playbooks add skill coder/mux --skill tbench in your terminal to install Tbench into your Claude Code session. It works immediately after installation.
Which AI coding agents work with Tbench?
Tbench is compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any AI agent that supports custom system prompts or .cursorrules files.
Is Tbench free to use?
Yes, Tbench is completely free and open source. The full source is available on GitHub at https://github.com/coder/mux/tree/main/.mux/skills/tbench. You only need a subscription to the AI agent you use it with.
