A test skill from a marketplace plugin

An example skill from the mock plugin

Creating Ansible Playbooks

Fuzzing APIs

Automating API Testing

Configuring Auto-Scaling Policies

Building CI/CD Pipelines

Validating API Contracts

Generating Database Seed Data

Splitting Datasets

Planning Disaster Recovery

Managing Environment Configurations

Running Integration Tests

Testing Load Balancers

Deploying Monitoring Stacks

Running Mutation Tests

Building Neural Networks

name: overnight-development

Performing Penetration Testing

Building Recommendation Systems

Tracking Regression Tests

Performing Security Audits

Performing Security Testing

Running Smoke Tests

Managing Snapshot Tests

Analyzing Test Coverage

Generating Test Data

Generating Test Doubles

Managing Test Environments

Generating Test Reports

Adapting Transfer Learning Models

Scanning for XSS Vulnerabilities

conducting-chaos-engineering

Automatically manages marketplace catalog updates, syncs marketplace.json, and handles plugin distribution when user mentions marketplace update, sync catalog, or add to marketplace. Specific to claude-code-plugins two-catalog system.

Automatically creates new Claude Code plugins with proper structure, validation, and marketplace integration when user mentions creating a plugin, new plugin, or plugin from template. Specific to claude-code-plugins repository workflow.

Automatically validates Claude Code plugin structure, schemas, and compliance when user mentions validate plugin, check plugin, or plugin errors. Runs comprehensive validation specific to claude-code-plugins repository standards.

running-load-tests

scanning-for-accessibility-issues

conducting-browser-compatibility-tests

managing-database-testing

generating-end-to-end-tests

automating-mobile-app-testing

performance-testing

orchestrating-test-workflows

performing-visual-regression-testing

Step-by-step guide to writing a SKILL.md file for Claude Code. Learn how to plan, structure, and test auto-activating skills with proper frontmatter, allowed-tools, dynamic context injection, and supporting files.

Shipwright converts a plain-English app description into a fully built, tested, and deployment-ready application. It delegates execution to `product-agent`, an autonomous 9-phase build engine availabl

splitting-datasets

adk-deployment-specialist

adk-engineer