테스트·보안 스킬

Test Ralph workflow presets using shell scripts and collect logs, completion status, iteration counts, and event metrics. Use the results to investigate configuration failures, timeouts, and problems with how work passes between roles.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check presets after configuration changes
• Validate a newly added preset
• Audit the full preset collection

Set up, repair, or migrate bot verification in an existing frontend and backend using Cloudflare Turnstile. The skill adds the widget, verifies tokens on the server, handles secret storage, and checks successful requests and token replay rejection.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add bot verification to signup or contact forms
• Migrate from reCAPTCHA or hCaptcha
• Connect an existing Turnstile widget to a backend

Review application code, dependencies, configuration, and APIs for common security weaknesses. Check authentication, access permissions, exposed credentials, and known package vulnerabilities, then classify findings by severity and organize fixes, follow-up tasks, and an audit report.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a new feature or pull request for security issues
• Reviewing dependency vulnerabilities before deployment
• Inspecting credentials and permissions in configuration

Review Python, FastAPI, and React code for security weaknesses in access checks, input handling, secrets, and dependencies. Produce a report with severity levels, file locations, explanations, and recommended fixes, supported by scanning patterns.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review pull requests for security weaknesses
• Audit authentication and access checks
• Check user input and file handling

Plan and build tests for ReactJS, NextJS, and NodeJS applications. Included Python scripts support test suite scaffolding, coverage analysis, and end-to-end test setup, helping teams organize quality checks and identify areas that need testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning an application's testing strategy
• Generating a starting set of tests
• Analyzing which code is covered by tests

Helps test Microsoft 365 Copilot declarative agents using the public evaluation CLI. Creates test datasets, runs single-turn or multi-turn checks, and analyzes scores to identify likely causes of failures and suggest focused improvements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create evaluation prompts and expected responses
• Test conversations across multiple turns
• Analyze failed evaluations and likely causes

Audit Azure resource configurations and policy compliance, and check expiration dates for Key Vault keys, secrets, and certificates. Summarize findings with priorities and suggested fixes to support security reviews and ongoing maintenance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing Azure resource configurations and compliance
• Checking Key Vault items for upcoming expiration
• Prioritizing security findings and suggested fixes

Run TypeScript Playwright tests across cloud-hosted browsers in Azure Playwright Workspaces. Configure parallel execution, connect automated build pipelines, publish results to the Azure portal, and migrate settings from the retired package.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run browser tests in parallel on Azure
• Integrate tests with GitHub Actions or Azure Pipelines
• Publish test results to the Azure portal

Implement cryptographic key management in Java with Azure Key Vault and Managed HSM, a hardware-based key protection service. Covers key creation, encryption, decryption, signing, verification, rotation policies, backups, and recovery of deleted keys.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating and managing RSA or EC keys
• Implementing encryption, decryption, signing, and verification
• Configuring automatic key rotation

Compose IRQL queries for security investigations in Kusto using existing functions for selecting events, extracting fields, and adding context. Build pipelines to investigate failed logins, suspicious emails, process activity, and network traffic alongside employee information.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate repeated login failures with employee context
• Prioritize suspicious emails by recipient roles
• Identify employees linked to suspicious outbound traffic

Helps capture Windows debug output from applications and kernel drivers using DbgViewCli. Covers process filters, automatic stopping by time or line count, file output, boot logging, and remote monitoring for scripted troubleshooting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Capture debug output from a specific process
• Record kernel driver debug messages
• Collect debug output during Windows startup

Helps you implement cryptographic key management in .NET with Azure Key Vault and Managed HSM, a hardware-based key protection service. Includes key creation, rotation, backup, encryption, decryption, and digital signature verification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create and manage RSA or EC keys
• Add encryption and decryption to a .NET application
• Implement digital signatures and verification

Build and improve tests for Vue 3 applications using Vitest, Vue Test Utils, and Playwright. Covers component behavior, simulated dependencies, asynchronous updates, and end-to-end tests that check complete user flows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up tests for a Vue 3 project
• Reviewing tests that break after refactoring
• Investigating intermittent asynchronous test failures

Evaluate how well a vision-language model, an AI that interprets images and text, detects household hazards in static camera images. Run 40 tests across five categories and review an HTML report.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Evaluate indoor hazard detection across five categories
• Run a quick check with ten tests
• Review benchmark results in an HTML report

Evaluate language models and vision-language models, which interpret images and text, for home security tasks. Test threat classification, tool use, alert routing, and scene analysis, then review JSON results and HTML reports with model comparisons.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing AI models for home security
• Testing threat classification and alert routing
• Checking resistance to prompt injection

Check enabled cloud language model providers for working connections, authentication, chat responses, JSON output, and streaming responses delivered in chunks. Test all providers or selected ones, and save results for reviewing behavior after changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking cloud LLM connections and authentication
• Testing chat and JSON output after configuration changes
• Verifying streamed response chunks

Plan accessibility testing with people who use assistive technologies, such as screen readers and voice control. Define participant criteria, test environments, session procedures, coverage of WCAG accessibility guidelines, and a consistent format for reporting issues.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning test sessions with assistive technology users
• Defining participant recruitment criteria
• Mapping key user flows to test environments

Plan click tests to check whether people can find information and features. Define tasks, target areas, participant criteria, and measures such as first-click accuracy, time, confidence, and where clicks cluster across a screen.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether settings and features are easy to find
• Comparing navigation across alternative designs
• Planning analysis of first-click accuracy and hesitation

Assess an existing interface against WCAG 2.2 accessibility guidelines. Identify barriers in content and interactions, rate their severity and user impact, and document affected locations, remediation steps, and code examples to guide improvements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing accessibility in an existing design or build
• Checking keyboard access and assistive technology compatibility
• Prioritizing fixes by severity and user impact

Create a usability study plan for designs and prototypes. Define research questions, participant criteria, realistic tasks, success measures, session scripts, and analysis methods, with a pilot checklist to prepare for the actual sessions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a usability study for a design or prototype
• Defining participant criteria and recruitment plans
• Preparing session scripts and observation templates

Create a checklist for checking whether an implemented interface matches its design specifications. Cover visual details, responsive layouts, interactions, content, accessibility, and required devices, then organize issue reporting, severity priorities, and verification of fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a developer's design self-review
• Checking layouts across screen sizes
• Reviewing keyboard access and assistive technology support

Run an app on a remote iOS or Android simulator hosted by EAS. Control screens, capture screenshots and video, or connect a development build for live updates when a suitable local simulator is unavailable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking an iOS app from Linux or a cloud environment
• Having an agent navigate screens and capture screenshots
• Checking animations and transitions with screen recordings

Evaluate Expo skills by checking whether relevant requests activate them, validating generated code, and capturing app screenshots on simulators or emulators. Compare runs with and without a skill, including tests against a reference screenshot.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether relevant requests activate an Expo skill
• Comparing generated code with and without a skill
• Verifying rendered screens on iOS and Android

Review local hook records to see whether recent UI editing sessions followed the kit’s rules. Report verification results, unresolved findings, and blocked completion attempts, with session timelines that show where a rule was broken.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check rule compliance in recent UI editing sessions
• Inspect a session timeline for a broken rule
• Review records for a specific period or across projects