테스트·보안 스킬

Check the appearance and interaction states of web pages, terminal interfaces, and paginated documents. Uses captured images, light and dark themes, viewport comparisons, and independent reviews to produce evidence-backed verdicts for each checklist item.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a UI after implementation changes
• Comparing a page with a design reference
• Finding Japanese text clipping and awkward wrapping

Verify documents, spreadsheets, presentations, and web deliverables before sharing them. Combine file checks with inspection of freshly rendered output, and scan for unfinished text to catch clipped content, layout problems, and leftover placeholders.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check documents before delivery
• Inspect rendered pages for layout problems
• Find leftover placeholders and sample text

Check password-manager warnings for exposed passwords and prepare official reset pages for affected accounts. The user enters and submits each replacement, while the skill tracks password changes, authorized saves, and fresh sign-in checks separately.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review current exposed-password warnings
• Prepare official password reset pages
• Check saved replacements and fresh sign-ins

Add or update a focused, reusable test when fixing bugs or changing behavior. Keep it in the project's existing test structure, verify the relevant change, and maintain coverage as the expected behavior evolves.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a regression test for a bug fix
• Updating tests when expected behavior changes
• Delivering a reusable test suite required by a specification

Review pending code changes for newly introduced security vulnerabilities with clear exploitation paths. Focus on concrete, significant risks and filter likely false alarms, then report affected files, line numbers, severity, attack scenarios, and recommended fixes in Markdown.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a PR for newly introduced security vulnerabilities
• Check authentication and authorization changes
• Trace user input for injection risks

Check whether a code change works by running the app and using its real interface. Exercise the intended flow and nearby error cases, capture outputs or screenshots, and report observed behavior with a clear verdict.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking changed behavior before committing code
• Probing invalid inputs and repeated operations
• Preparing verification reports with captured evidence

Test a changed website or desktop app by operating it directly. Use browser and desktop control tools to compare states before and after actions, checking visible results such as text, input values, selections, and status indicators.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test a website after changing its interface
• Reproduce a bug through real browser interactions
• Check state changes in a native desktop app

Plan and write tests for changes to agent behavior, favoring integration tests that check components together. Identify key logic changes and user-visible behavior to cover, reuse existing helpers, and keep unit tests in dedicated files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Identify test coverage for changes to agent logic
• Add integration tests for user-visible behavior
• Organize unit tests in dedicated files

Test agent features across local and remote execution environments using integration tests, which check components working together. Covers Docker and Wine setups, test helpers, and configuration-specific skips for the app-server and exec-server split.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run core integration tests with a Docker remote executor
• Test a Windows exec-server under Wine
• Adapt app-server tests for remote execution

Test changes interactively in Codex's terminal interface. The skill explains how to launch it, save detailed logs for debugging, and send test messages programmatically with text and Enter submitted separately.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check changes in the Codex terminal interface
• Save detailed logs for debugging
• Send test messages programmatically

Investigate a video that is not working by downloading it, setting it as the source in a sample component, and running a Remotion render with verbose logs to examine the behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a video reported as not working
• Setting up a sample with the affected video
• Rendering a video with verbose logs

Maintain visual snapshot tests, which compare rendered images, for Remotion’s web renderer. Update existing tests after implementation changes, or add explicitly requested tests with sample components, preview registration, and documentation updates for supported properties.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Updating existing tests after renderer changes
• Adding an explicitly requested rendering test
• Registering a test fixture for preview

Guide test writing, updates, and reviews in Remotion by checking observable user outcomes. Choose integration, unit, visual, or end-to-end tests that detect broken workflows, and verify that bug fixes address the original regression.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a test boundary for a feature
• Review whether existing tests detect broken workflows
• Verify a regression test fails before the fix and passes after it

Investigate intermittent Remotion CI failures, record their error patterns in a tracking issue, and increment counts for repeated failures. Find failed checks even without a supplied pull request, then rerun affected GitHub Actions jobs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate a CI failure that may pass on retry
• Find failed checks without a pull request number
• Record recurring failures and update their counts

Create integration tests for syncable metadata entities in Twenty itself. Cover invalid inputs, validation errors, and successful data operations, using reusable GraphQL request helpers, error snapshots, and cleanup routines to organize the test suite.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add integration tests for a new syncable entity
• Test required fields, duplicates, and invalid references
• Verify successful creation, updates, and deletion

Check a Twenty pull request through real browser scenarios derived from its changes. Verify database effects and server logs alongside visible results, then produce screenshots, a structured verdict, and a report of any failures or uncertainty.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Validate user flows before or after merging a Twenty pull request
• Check database writes and timeline activity after saving records
• Investigate backend errors hidden behind a successful screen

Manage WireMock from the command line to create mock HTTP responses, inspect and count received requests, change scenario states, and record real backend traffic. These operations support integration tests with controlled responses.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create mock API responses for integration tests
• Check request counts and unmatched requests
• Switch states in a multi-step test scenario

Evaluate 3D point clouds and movement trajectories against reference data with CloudAnalyzer. Prepare inputs, measure differences, apply quality thresholds, inspect results visually, and track baseline history for mapping, localization, and perception workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare a generated point cloud with reference data
• Measure errors in estimated movement trajectories
• Check ground segmentation against quality thresholds

Design evaluation tasks that check whether agents actually complete work. Define requests, simulated user behavior, starting conditions, and verifiable success criteria, then plan difficulty levels, training-data leakage checks, and ongoing maintenance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating evaluation tasks for real business workflows
• Reviewing success criteria and verification logic
• Designing checks for evaluation data leakage into training

Add end-to-end tests, which check complete usage flows, and API tests for features that already work. Follow the project's existing test setup to extend automated coverage without introducing a separate testing approach.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding automated tests to an existing feature
• Testing complete usage flows with E2E tests
• Adding API tests using the existing test setup

Evaluate BMad skills using your agent's configured runner. Compare results with the model alone or another version, grade outputs against criteria, and test whether descriptions trigger correctly, preserving transcripts and evidence for each run.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare a skill with the model alone
• Compare an edited skill with a previous version
• Grade outputs against defined criteria

Review an Anthropic Cookbook notebook for clear explanations, code quality, technical accuracy, and practical usefulness. It combines automated checks, including exposed credential detection, with a scored report and specific recommendations tied to sections and lines.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a Cookbook notebook before publication
• Check introductions and conclusions against learning objectives
• Scan for hardcoded API keys and credentials

Plan and document studies that assess whether an analytical procedure suits its intended use. Select the governing framework, evaluate calibration, accuracy, precision, and detection limits, and compare methods using acceptance criteria defined before data collection.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning analytical validation studies and acceptance criteria
• Evaluating calibration, accuracy, and precision
• Estimating and confirming detection and quantitation limits

Run repeatable tests of Cherry Studio’s key workflows with Playwright, which checks application behavior through automated interactions. Collect results on macOS and Windows and produce English reports for release acceptance or development validation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking key workflows before a release
• Validating application behavior on a development branch
• Running regression tests for a specific task