skills.rest
cuelight
cuelightOFFICIAL
Explore all skills by this author →
GitHub

agent-skill-test

Isolate CLI agent skill tests in self-contained workspaces.

Updated Aug 23, 2026
Search Tags:#isolated-workspace#agent-skill-testing#cli-agent-validation#runner-commands#skill-regression#multi-runner-testing
One-click install
npx skills add https://github.com/cuelight/agent-skills --skill agent-skill-test
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-skill-test
Source: https://github.com/cuelight/agent-skills/tree/main/agent-skill-test
Command: npx skills add https://github.com/cuelight/agent-skills --skill agent-skill-test

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Testing agent skills in shared or unstandardized environments causes cross-test contamination, inconsistent results across different CLI agents, and difficulty reproducing failures. This Skill eliminates that friction by providing a standardized, isolated workspace setup for skill testing.

Core Features & Use Cases

  • Portable Isolated Workspaces: Creates self-contained test directories that copy skills under test to a universal skills-under-test/ path, with optional runner-native mirrors for Codex, Claude Code, Qoder CLI, and OpenCode.
  • Runner-Agnostic Command Generation: Builds correct, runner-specific execution commands for multiple popular CLI agents, handling shell quoting, output capture, and permission flags automatically.
  • Generic Validation & Evidence Capture: Includes scripts to capture runner events, transcripts, and final messages, plus validate required files, regex patterns, and forbidden artifacts to ensure test outcomes meet acceptance criteria.
  • Use Case: Use this Skill to smoke test new skills, run regression tests after skill updates, validate skill behavior across different agent runners, or prepare portable skill copies for distribution.

Quick Start

Use the agent-skill-test skill to create an isolated test workspace for your target agent skill, run it with your preferred CLI agent, and validate the produced artifacts against your expected requirements.

Frequently Asked Questions about agent-skill-test

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I isolate CLI agent skill tests to prevent cross-test contamination?▼

You can isolate agent skill tests by creating self-contained workspaces that copy skills under test to a universal path, eliminating cross-test contamination and environment inconsistency across different CLI agents.

Does agent skill testing work with Codex, Claude Code, and OpenCode runners?▼

Yes, agent skill testing supports validating behavior across Codex, Claude Code, OpenCode, Qoder CLI, and custom command-line agent runners. Runner-native mirrors and runner-specific execution commands are generated automatically.

How do I validate required files and regex patterns after running an agent skill test?▼

Validating agent skill test outputs involves capturing runner events, transcripts, and final messages, then checking produced artifacts against required files, regex patterns, and forbidden artifacts to ensure acceptance criteria are met.

What's the best way to run regression tests for agent skills across multiple CLI runners?▼

Running regression tests across multiple CLI runners is best handled by generating runner-agnostic commands that handle shell quoting, output capture, and permission flags automatically within a standardized isolated workspace setup.

Why do my CLI agent skill tests fail when run in shared or unstandardized environments?▼

CLI agent skill tests fail in shared environments because cross-test contamination and inconsistent setups prevent reliable behavior reproduction. Isolating tests in self-contained workspaces with portable skill copies eliminates this friction.

Related Skills

Explore More Software Engineering Skills→
agentic-inagentic-in
577

Inference

Select inference paths, serving stacks, and benchmarking plans for ML models.

Official
Intermediate
atopileatopile
3.6k

Dev

Coordinate Zig builds, orchestrated tests, and test artifact consumption.

Official
Advanced
JingyueCongJingyueCong

posix-shell-pro

Review shell scripts for POSIX compliance and portability improvements.

Community
Advanced
manuelbrandner85manuelbrandner85

seatbelt-sandboxer

Generate minimal macOS Seatbelt sandbox configurations for process isolation.

Community
Advanced