terminal-bench-task-reviewer
CommunityQuality and compliance for Terminal-Bench tasks.
AuthorRutulPatel007
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill helps teams ensure Terminal-Bench task directories are structured correctly, pass quality checks, and comply with project standards before submission.
Core Features & Use Cases
- Validates the presence and correctness of SKILL.md at the task root, ensuring mandatory fields exist (name and description) and that the body provides actionable guidance.
- Checks for common Terminal-Bench task structure elements (e.g., Dockerfile, task.yaml, solution.sh, tests) and flags missing or misnamed components.
- Performs a quick quality audit of the task by cross-referencing the instructions, timeout settings, and test coverage against best practices.
Quick Start
Review a Terminal-Bench task directory and generate a concise compliance report highlighting any critical findings and suggested fixes.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: terminal-bench-task-reviewer Download link: https://github.com/RutulPatel007/Airdawgs/archive/main.zip#terminal-bench-task-reviewer Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.