테스트·보안 스킬

Create Vitest tests for Mastra playground features using MSW to simulate network responses. Exercise the real client SDK, React Query cache, and components with typed sample data to check loading, access conditions, redirects, and errors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test loading, empty, and error states
• Check requests controlled by permissions or feature flags
• Verify pagination and query parameters

Create a dedicated test project linked to the current worktree and check Agent Builder through APIs and browser interactions. It covers agent and skill management, permissions, defaults, and related features, with selectable test sections.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Validate an Agent Builder feature branch before review
• Check role-based permissions and authentication
• Test agent and skill management through APIs and the UI

Create a Mastra project at a specified version and check its Studio in Chrome. Test page loading, agent chat, tool execution, and workflows, then report passed and failed checks, encountered errors, and screenshots.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a newly created Mastra project
• Testing initialization with a specified version or package manager
• Checking Studio chat, tools, and workflows

Create and improve Playwright end-to-end tests for Studio changes. Check complete user actions, including whether settings affect requests, data survives reloads, tools return expected results, and workflows pass data correctly.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing whether agent settings affect actual requests
• Checking that saved data survives page reloads
• Verifying tool outputs and workflow data flow

Write integration tests for core error processors by simulating API failures with a mock model. Check retry attempts, changes to conversation messages, and streamed responses, with guidance on test setup and diagnosing empty output.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check retries and message changes after API errors
• Diagnose empty output in streaming tests
• Verify unrelated errors pass through unchanged

Reproduce Mastra Code bugs with a real model and compare timestamped logs across network, streaming, execution, and terminal interface layers. Use the evidence to locate timing problems, incorrect token rates, flicker, or stuck status displays.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating incorrect token rate displays
• Reproducing intermittent bugs with a real model
• Tracing flicker or stuck status displays

Explore an existing Vitest 3.2 JSON test report to count results, search failed tests, and inspect file errors. Review original diagnostic details and keep tentative explanations separate from evidence, without launching tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check failure counts in an existing test report
• Search failures by file path or diagnostic text
• Inspect file errors separately from failed assertions

Verify a qwen-code pull request in an isolated environment by comparing its behavior with a control build and running focused tests. Produce a report and machine-readable verdict that distinguish measured results from areas left untested.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Verify the central behavior changed by a pull request
• Compare results between the PR and a control build
• Recheck earlier findings after a PR update

Stabilize a test that fails and then passes on the same commit. Apply a minimal fix to timing, randomness, clock behavior, or shared resources while preserving assertions, then verify it through repeated runs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fixing tests that pass only after a rerun
• Improving timeout budgets and condition-based waiting
• Making clock-dependent or random tests deterministic

Compare a feature implemented in Qwen Code with Codex or Claude Code under the same scenario. Capture communication and terminal records, inspect tool definitions and outputs, and guide fixes toward matching observable behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a reproduced feature against its reference agent
• Comparing tool definitions and required arguments
• Investigating differences in terminal output

Test Qwen Code through realistic keyboard interactions in tmux, a terminal session tool. Capture readable screen snapshots at each step and produce a report documenting dialogs, commands, outcomes, and observed side effects.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing authentication dialogs and keyboard navigation
• Checking slash command interactions
• Reviewing intermediate screens for regressions

Test Qwen Code CLI behavior from model requests through tool execution. Reproduce bugs, check terminal interactions and MCP tool connections, and inspect API logs using real models or mock servers for controlled scenarios.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reproduce reported CLI bugs and verify fixes
• Test MCP tool connections through the CLI
• Check terminal rendering and keyboard interactions

Classify outstanding pull request CI failures, automated checks run on code changes, using logs and changed files. Produce JSON decisions recommending a rerun, a comment, or no action, and identify specific nondeterministic tests when evidence supports it.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sorting outstanding CI failures on pull requests
• Identifying transient failures suitable for reruns
• Checking whether PR changes caused a failure

Automate terminal interactions and capture screenshots before and after commands run. Define scenarios in TypeScript to review CLI appearance, document command flows, or record changing output such as progress bars, with optional animated GIFs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review CLI appearance changes in a pull request
• Capture slash command interactions
• Create screenshots for usage documentation

Verify a bug with a test that fails before the fix, passes afterward, and fails again when the fix is temporarily removed. Record actual results to show that the test detects the defect and the change addresses it.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reproducing a suspected bug before changing code
• Checking whether a regression test detects the defect
• Investigating an incident with recorded test evidence

Compare repeated agent evaluations before and after a change to distinguish performance drops from random variation. Scripts check tool calls, identify inconsistent cases, and provide a CI gate that blocks merging when specified regression conditions are met.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare results before and after prompt or model changes
• Identify evaluation cases with inconsistent results
• Check required and forbidden tool calls

Set up Playwright browser tests, generate cases from specifications or URLs, and review coverage gaps. Diagnose tests that fail inconsistently, migrate Cypress or Selenium suites, and optionally connect TestRail and BrowserStack for results and browser testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up Playwright tests and CI
• Generate and review tests from user stories
• Diagnose tests that fail inconsistently

Review Playwright browser tests against 20 quality checks to find unreliable patterns and missing coverage. Get scores for each file, prioritized findings, and corrected code for critical issues.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a specific Playwright test file
• Auditing test quality across a project
• Finding causes of unreliable test runs

Set up Playwright, a browser testing tool, for an existing web project. Generate configuration, test folders, an example test, and applicable CI automation, then run the test and address setup failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding browser tests to an existing web project
• Configuring tests for the project's framework
• Running browser tests automatically in CI

Create Playwright tests from a user story, page URL, component path, or feature description. The skill follows existing project conventions, covers expected behavior and error cases, creates supporting files when needed, and runs the tests to check results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding tests for login behavior
• Testing checkout and form submission flows
• Checking search filters and component interactions

Plan ISO 27001 information security audits, review evidence that security controls work, and document findings. The skill also helps classify failures, track corrective actions, and prepare documentation for certification audits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning an annual internal audit
• Reviewing evidence for Annex A controls
• Documenting findings and corrective actions

Run Playwright tests on BrowserStack to check behavior across browsers and devices. Configure cloud connections, compare results by browser, inspect session videos and logs, and set up a tunnel for testing local or restricted environments.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking browser compatibility with Playwright tests
• Configuring BrowserStack cloud test connections
• Investigating failures through session videos and logs

Prepare SaaS teams for SOC 2 audits by mapping evaluation criteria to controls, the measures used to manage risk. Build control matrices, track supporting evidence, identify gaps, and assess readiness for Type I or Type II.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a matrix of controls, owners, and evidence requirements
• Identify gaps in Type I or Type II audit preparation
• Track evidence collection for each control

Diagnose failing or intermittent Playwright tests by reproducing errors and examining execution traces. Classify the cause, apply a targeted fix, and run the test ten times to check stability, with recommendations to prevent recurrence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fixing a Playwright test that fails consistently
• Investigating tests that pass only sometimes
• Debugging failures limited to CI