test-master
An agent skill by Jeffallan, from Jeffallan/claude-skills. Tags: automation, debugging, evaluation, performance, testing.
What it does
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation frameworks; analyzing coverage gaps; performance testing with k6 or Artillery; security testing with OWASP methods; debugging flaky tests; or working on QA, regression, test automation, quality gates, shift-left testing, or test maintenance.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add Jeffallan/claude-skills --skill test-master
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/Jeffallan/claude-skills
cp -r claude-skills/skills/test-master ~/.claude/skills/test-master
Safety box score
Grade C, moderate risk: 35 of 100 risk points, rated 2026-10-06. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a documentation-only testing helper: it generates test plans, test reports, and example unit/integration/E2E/performance/security test code. The main risks come from the example workflows themselves, which can run browser automation, execute `npx`-based tooling, and mutate test data or simulate checkout/login flows if pointed at the wrong environment.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 2 (moderate) | The skill’s core workflow says to "Execute — Run tests and collect results," and the references include runnable tooling like `npx playwright install --with-deps` and `npx playwright test --shard=...`. |
| Network access | 2 (moderate) | Several references send HTTP requests to apps and services (`http.get(...)`, login requests, `page.request.post('/api/test/seed')`), so it can generate networked test traffic against whatever environment is configured. |
| Filesystem reach | 1 (low) | It is aimed at writing test files and reports, but the shipped files do not show broad filesystem access beyond project-scoped test artifacts. |
| Secrets & credentials | 1 (low) | The examples handle auth tokens and passwords (`Authorization: Bearer ...`, login with email/password), but there is no evidence of reading secret stores or keychains. |
| Privilege & persistence | 1 (low) | The references show install/setup commands such as `npx playwright install --with-deps`, which may require elevated privileges in some environments, but no explicit sudo or service registration is present. |
| Instruction hijack surface | 0 (none) | The content is prescriptive testing guidance, not prompt-injection content; it does not tell the agent to hide actions, ignore higher-priority instructions, or follow remote instructions. |
| Irreversible actions | 2 (moderate) | It includes state-changing test flows and cleanup actions like `test('complete purchase'...)`, `await db.query('DELETE FROM users');`, and API seed/cleanup calls, which can have real effects if mispointed at non-test systems. |
| Transparency | 0 (none) | All shipped material is readable markdown and code snippets; there are no binaries, obfuscated blobs, or hidden runtime downloads in the skill files themselves. |
Before installing
- Check that any `DELETE FROM ...`, seed, or cleanup steps only point at disposable test databases.
- Confirm checkout/payment examples are wired to a sandbox processor and test cards, not a live merchant account.
- Review any `npx playwright ...` commands and run them in an isolated CI/container first.
- Use synthetic auth tokens/passwords only; do not paste production credentials into test fixtures or reports.
Rated 2026-10-06 by an automated review of 11 files from the skill's repository.
Source
- Repository
- Jeffallan/claude-skills (all skills from this repository)
- Path
- skills/test-master/SKILL.md
- Branch
- main
- Updated
- 2026-09-19
Related skills
- control-cli — Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services.
- control-ui — Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI.
- mutation-testing — Configures mewt or muton campaigns, analyzes surviving mutants, and investigates bugs exposed by testing gaps.
- reproduce-and-fix-issues — Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes.
- cpp-pro — Writes, optimizes, and debugs C++ applications using modern C++20/23 features, template metaprogramming, and high-performance systems techniques.
- embedded-systems — Use when developing firmware for microcontrollers, implementing RTOS applications, or optimizing power consumption.