테스트·보안 스킬

Guides feature development and bug fixes by writing tests before implementation. It confirms each test fails for the expected reason, adds only enough code to pass, and checks the full test suite before completion.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing a new feature from tests
• Reproducing a bug in a test before fixing it
• Refactoring while keeping tests passing

Build features or fix bugs by writing one failing test, then the smallest implementation that passes it. Tests check behavior through public interfaces, the entry points callers use, so they remain useful when internal code changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a feature one test at a time
• Fixing a bug with a failing test first
• Planning integration tests at agreed public interfaces

Replace TypeScript type assertions in tests with functions from @total-typescript/shoehorn. Use partial objects when only a few properties matter, or deliberately invalid data for error tests, then run a type check to verify the migration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Replace as assertions in TypeScript tests
• Build test objects with only the properties you need
• Pass deliberately invalid data for error tests

Set up Claude Code hooks that block Git commands such as push, hard reset, and forced deletion before execution. Choose project-wide or global settings, customize the blocked commands, and verify that the hook rejects a test command.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Block Git pushes from Claude Code
• Prevent commands that discard changes or delete branches
• Apply Git restrictions to one project or all projects

Inventory existing tests and identify gaps. Link requirements, business rules, risks, and bugs to stable test identifiers and executable evidence, maintaining a test registry that shows what is covered and what still needs verification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inventory existing tests and identify gaps
• Link bug fixes to regression evidence
• Check client and server behavior against one shared contract

Track module dependencies and verification commands in REGRESSION.md. After a change, check the affected module and downstream consumers, then report command exit codes as evidence that existing behavior still works or needs attention.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check downstream effects of a module change
• Organize existing test commands by module
• Audit dependency evidence and verification scope

Check the full connection between a local agent API and a remote sandbox through a temporary tunnel. Run a task that needs no connected tools, verify its response, and restore the web app’s original API connection.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a local agent API from end to end
• Investigating tasks stuck after dispatch
• Verifying gateway callbacks reach the local API

Review MCP configuration without running its servers. Identify npm, Python, and Docker references that may fetch different code later, classify their version settings, and recommend pinning versions or image contents that the team has reviewed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing MCP configuration before approval
• Checking latest tags and version ranges
• Adding a deterministic configuration check to CI

Plan and verify security controls for AI agents that read untrusted content and use tools. Review permissions, file boundaries, network destinations, and credentials, then test that rejected actions leave no unintended changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing security boundaries in an agent runtime
• Checking isolation between tenants and workspaces
• Testing credential cleanup and tool output limits

Review authentication, payments, and APIs for security risks using implementation examples and a predeployment checklist. Covers input validation, access permissions, secret storage, request limits, and checks for sensitive information in logs and errors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing login and access permissions
• Checking API input and file uploads
• Reviewing secrets and sensitive logs

Develop Spring Boot features and fixes by writing tests before implementation. Guides unit, web, persistence, and integration testing with JUnit 5, Mockito, MockMvc, and Testcontainers, plus JaCoCo measurement of how much code tests cover.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding Spring Boot endpoints with tests first
• Writing regression tests for bug fixes
• Testing database persistence and retrieval

Make Swift code easier to test by separating file access, networking, and external APIs behind small protocols. Replace those dependencies with mocks, controlled test substitutes, to check normal behavior and error handling with Swift Testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test Swift file operations without reading or writing real files
• Check error handling with simulated failures
• Share modules across apps, tests, and SwiftUI previews

Build end-to-end tests that operate Windows desktop apps through pywinauto and Windows UI Automation, an interface for accessing screen controls. Covers stable element selection, waits, failure screenshots, test isolation, and CI setup for native applications.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building automated tests for Windows desktop workflows
• Diagnosing intermittent GUI test failures
• Adding stable identifiers to screen controls

Review security measures in Java Spring Boot services, including identity checks, access permissions, input validation, and secret storage. Provides configuration examples and a release checklist covering API request limits, browser protections, logging, and dependency vulnerabilities.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding authentication and access permissions
• Reviewing API input validation and SQL queries
• Checking browser protections such as CSRF and CORS

Verify completed code changes in six stages: build, type checks, lint, tests with coverage, searches for possible secrets, and diff review. Produces a pass/fail report with issues to fix and readiness for a pull request.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Verifying code after completing a feature
• Checking for problems after refactoring
• Reviewing readiness before creating a pull request

Develop features and fix bugs by running a failing test first, making the smallest passing change, then refactoring. Check at least 80% test coverage and preserve evidence of failures, successful fixes, and verified behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing a new feature from tests
• Reproducing a bug before fixing it
• Refactoring code while keeping tests passing

Check whether coding agents follow their assigned skills and rules across three levels of prompt support. Generate test scenarios, inspect tool call sequences, and get reports showing compliance scores and the order of observed actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether a newly added rule is followed
• Testing compliance without explicit reminders
• Reviewing tool call order and missed steps

Find remotely reachable security flaws in repository code and assess whether they warrant a vulnerability report. The workflow checks scope, traces attacker-controlled input, confirms impact with a minimal proof of concept, and structures findings for disclosure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding vulnerabilities reachable through external requests
• Assessing exploitability of static analysis findings
• Preparing minimal reproduction steps and impact details

Audit Claude Code configuration with AgentShield to find exposed secrets, excessive permissions, unsafe hooks, and prompt injection risks, where malicious instructions influence an agent. Generate reports, apply supported automatic fixes, or create a security-focused starter configuration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking configuration when starting a Claude Code project
• Auditing permission and MCP configuration changes
• Reviewing existing configuration in a newly joined repository

Verify Spring Boot changes through builds, static analysis that checks code without running it, tests, coverage checks, and security scans. Review the diff and produce a pass/fail report showing readiness and issues to fix.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a Spring Boot service before opening a pull request
• Verifying changes after refactoring or dependency upgrades
• Checking test coverage against the target

Verify Quarkus services before pull requests or deployment through builds, code analysis, tests, coverage reports, and security scans. The workflow also checks native executables, containers, performance, health endpoints, configuration, and documentation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a Quarkus service before a pull request
• Verifying refactoring or dependency upgrades
• Checking native executable compatibility

Write and run Perl tests with Test2::V0 or Test::More, replace external dependencies with controlled test substitutes, and measure coverage—the code exercised by tests. Guidance covers test-first development, failure diagnosis, and migration between testing modules.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Writing Perl tests before implementation
• Migrating tests from Test::More to Test2::V0
• Testing API and database interactions in isolation

Adds checks before an agent runs destructive commands and restricts file edits to a chosen directory. Offers separate or combined protection modes for production work, autonomous sessions, migrations, deployments, and data changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking dangerous commands before production work
• Restricting edits to a specific directory
• Combining protections for autonomous agent sessions

Review prediction-market and trading-agent workflows before they handle account access, portfolio data, or trade planning. Produces structured findings on venue rules, data quality, security, privacy, and execution risks, with required safeguards and a safe next step.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review workflows before adding venue authentication
• Check how portfolio data and API keys are handled
• Review market data quality and source labels