Testing Skills with Subagents

Use to validate process documentation. Apply TDD to skill writing: RED (run without skill, document failures) → GREEN (write skill) → REFACTOR (close loopholes). Test under pressure: time constraints, sunk cost, exhaustion, authority.

8 stars 3 forksTesting & QA Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add Freddy-CHEN-ux/00_claude_skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Freddy-CHEN-ux/00_claude_skills --skill testing-skills-with-subagents
Manual install
git clone --depth 1 https://github.com/Freddy-CHEN-ux/00_claude_skills.git /tmp/00_claude_skills
mkdir -p ~/.claude/skills
cp -r /tmp/00_claude_skills/skills/testing-skills-with-subagents ~/.claude/skills/testing-skills-with-subagents

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Testing Skills with Subagents

## Core Principle

Skills are process documentation. Like code, they need tests. Use TDD to validate skills actually work under pressure.

## When to Use This Skill

- Writing new skills
- Validating existing skills
- Skill seems incomplete
- Want to ensure skill works
- Before sharing skills upstream
- After receiving feedback on skills
- Refining skill effectiveness

## The Iron Law

**NO SKILL WITHOUT A FAILING TEST FIRST.**

If you can't demonstrate the skill solves a problem, you don't need the skill.

## Why Test Skills?

**Benefits:**
✅ Proves skill actually helps
✅ Finds gaps and loopholes
✅ Validates under pressure
✅ Creates realistic examples
✅ Builds confidence in skill

**Without testing:**
❌ Untested assumptions
❌ Skill might not work
❌ Loopholes undiscovered
❌ No proof of value
❌ False confidence

## TDD for Skills

### RED: Run Scenarios WITHOUT Skill

```
🔴 RED Phase: Establish baseline

Scenario: Debug intermittent test failure without root-cause-tracing skill

Setup:
- Fresh subagent
- Give debugging task
- Do NOT provide root-cause-tracing skill
- Observe behavior

Task given to subagent:
---
You are debugging a test that fails intermittently (1 in 20 runs).

Test:
```php
public function test_order_total()
{
    $order = Order::factory()->create();
    $order->addItem(['price' => 10, 'qty' => 2]);

    $this->assertEquals(20, $order->total());
    // Sometimes fails: Expected 20, got 0
}
Read the full skill on GitHub

Details

Skill name
testing-skills-with-subagents
Path
skills/testing-skills-with-subagents/SKILL.md
Repo updated
10 January 2026

FAQ

What does the Testing Skills with Subagents skill do?

Use to validate process documentation. Apply TDD to skill writing: RED (run without skill, document failures) → GREEN (write skill) → REFACTOR (close loopholes). Test under pressure: time constraints, sunk cost, exhaustion, authority.

How do I install the Testing Skills with Subagents skill?

Claude Code plugin: /plugin marketplace add Freddy-CHEN-ux/00_claude_skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Testing Skills with Subagents popular?

It lives in Freddy-CHEN-ux/00_claude_skills, which has 8 GitHub stars and 3 forks.

Related skills

Add Integration

8

Freddy-CHEN-ux/00_claude_skills

Build a new API integration for Nexus. Load when user mentions "add integration", "new integration", "integrate with", "connect to [service]", or "build [service] integration". Interactive workflow that discovers API endpoints, plans the integration, and creates a project for implementation.

Software Development

AI Agents

8

Freddy-CHEN-ux/00_claude_skills

Production-grade AI agent patterns with MCP integration, agentic RAG, handoff orchestration, multi-layer guardrails, and observability (modern best practices)

AI, LLMs & Agents

AI LLM

8

Freddy-CHEN-ux/00_claude_skills

Production LLM engineering skill. Covers strategy selection (prompting vs RAG vs fine-tuning), dataset design, PEFT/LoRA, evaluation workflows, deployment handoff to inference serving, and lifecycle operations with cost/safety controls.

AI, LLMs & Agents

To Tickets

5

vnovakovits/claude-skills

Break a plan, spec, grilling summary or conversation into a set of tracer-bullet tickets — thin, end-to-end slices that each work and can be demonstrated on their own — with explicit "blocked by" edges, so the work forms a dependency graph and anyone can pick up a ticket whose blockers are done. Covers vertical vs horizontal slicing (Hunt & Thomas's tracer bullets, Cockburn's Elephant Carpaccio, INVEST), prefactoring first ("make the change easy, then make the easy change"), sequencing a wide refactor as expand-migrate-contract (Parallel Change), sizing a ticket to one session and one pull req

Testing & QA

Testing Anti Patterns

8

Freddy-CHEN-ux/00_claude_skills

Use to avoid critical testing mistakes. Five Iron Laws: Never test mock behavior, Never add test-only methods, Never mock without understanding, Always integration test, Always test error paths.

Testing & QA

Unit Testing Principles

5

vnovakovits/claude-skills

Apply Vladimir Khorikov's unit testing framework from "Unit Testing Principles, Practices, and Patterns" (Manning, 2020). Covers the four pillars (protection against regressions, resistance to refactoring, fast feedback, maintainability) and their unavoidable trade-offs, the three styles of unit testing (output-based, state-based, communication-based), observable behavior vs implementation details as the line that separates good and bad tests, mocks vs stubs with strict verification rules, the managed vs unmanaged dependency distinction (the most useful heuristic for deciding what to mock), wh

Testing & QA

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.