
Test Master
Writes test suites, mocking strategies, test plans and defect reports across unit, E2E, performance and security testing.
- Repository
- Jeffallan/claude-skills
- Stars
- 12,176
- Licence
- MIT
- Files
- 11 files
What it does
Once installed, the agent approaches testing work with a structured QA specialist's playbook. It can write unit, integration and end-to-end tests with meaningful descriptions and specific assertions, plan mocking and test architecture, analyse coverage gaps, and produce test plans and defect reports with severity ratings. It also follows reference guides covering topics such as k6 load testing, OWASP-style security checks, flaky-test debugging, and test-first development.
Great for
- Software developers who want help writing or reviewing Jest, Vitest or pytest test suites
- QA engineers building test strategies, regression plans or defect reports
- Teams trying to diagnose flaky tests or close coverage gaps before a release
Skip it if
- Non-technical users with no codebase to test, since most guidance assumes code and a test runner
- Production security audits: the skill provides checklists and methods, not a substitute for a professional penetration test
- Running load or security tests against systems you do not own or have permission to test
Try asking
- “Write Jest unit tests for my calculateDiscount function, including error and boundary cases”
- “Review our flaky E2E tests and suggest how to stabilise them”
- “Create a test plan and quality gate for our checkout feature”
- “Draft a k6 load test script for our login API and explain the thresholds”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 11 original files, the MIT licence and an attribution note.
test-master.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip test-master.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip test-master.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Point the agent at a specific module or feature so it can read the real code before writing tests
- Ask for both happy-path and error-path cases explicitly, and state which framework your project uses
- Run any generated tests yourself in a non-production environment before merging, and review performance or security scripts before pointing them at any live system
What's inside
- references/automation-frameworks.md
- references/e2e-testing.md
- references/integration-testing.md
- references/performance-testing.md
- references/qa-methodology.md
- references/security-testing.md
- references/tdd-iron-laws.md
- references/test-reports.md
- references/testing-anti-patterns.md
- references/unit-testing.md
- SKILL.md
Redistributed unmodified from Jeffallan/claude-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.