테스트·보안 스킬

Turn the current branch diff or a specified pull request into an actionable testing plan. It summarizes the changes, assesses risk, and selects relevant checks for critical behavior, regression, edge cases, accessibility, and visual changes so a team can review PR readiness.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a QA checklist from branch changes
• Planning tests for a pull request
• Checking regression risks before merging

Use browser commands to navigate websites, interact with page elements, fill forms, and inspect results. The skill can also capture screenshots or PDFs, record videos, and extract page information for testing and documentation workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Filling and checking a web form
• Testing a web application flow
• Capturing a page or extracting its content

Review UI files against Web Interface Guidelines to find design, UX, and accessibility issues. The skill reports findings in a concise file-and-line format, helping you locate areas that may need changes. It fetches the latest guidelines before each review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a site's accessibility
• Reviewing UI code for design issues
• Auditing UX against current guidelines

Run authorized security assessments through YAML workflows that coordinate AI agents and security tools. The skill supports reconnaissance, vulnerability scanning, analysis, and reports in Markdown, HTML, or JSON, with findings linked to captured execution evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a permitted web security assessment
• Scanning an authorized network range
• Reviewing findings from an existing session

Create a test client for an MCP server, a program that exposes tools to clients. The examples launch the server over standard input and output, connect through the MCP SDK, call a named tool with arguments, and close the process after testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing an MCP server's tool calls
• Sending sample arguments to a server tool
• Connecting to a server over standard input and output

Set up snapshot tests for command-line output. The skill provides a pattern that saves expected output, compares future runs against it, and supports updating snapshots when output changes, helping teams review differences in CLI behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether CLI output changed unexpectedly
• Updating saved snapshots after an intentional output change
• Adding output checks to CLI integration tests

Compare algorithm implementations using shared test cases to check outputs, benchmark runtime and memory, and stress-test with random inputs. When solutions disagree, narrow the discrepancy to a minimal failing case for easier debugging.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking multiple implementations against a known-correct solution
• Benchmarking runtime and memory across algorithms
• Stress-testing solutions with large random inputs

Create mock standard input streams for testing interactive command line tools. The skill provides patterns for supplying scripted answers to a command, running it with temporary mocked input, and restoring the original input afterward.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test a CLI command that asks interactive questions
• Provide scripted answers through mocked standard input
• Build unit or integration tests for prompt flows

Generate edge cases, random inputs, and large stress tests to check algorithm solutions. Compare results with a brute-force reference, then find and minimize counterexamples when outputs differ, making failures easier to reproduce and debug.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking an algorithm against boundary inputs
• Stress testing a solution with large datasets
• Comparing outputs with a brute-force reference

Set up an end-to-end test harness for command-line applications. It launches a CLI process, captures standard output and error, records its exit code, and provides assertions for expected output, snapshots, and exit status.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing a CLI command from start to finish
• Checking command output and exit codes
• Capturing CLI output for snapshot assertions

Create a BATS test scaffold for shell scripts, including test files, fixtures, setup and teardown routines, assertions, and mock helpers. It helps organize isolated tests for command behavior, input handling, expected output, and generated files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up BATS tests for a shell script
• Create reusable test fixtures and helpers
• Mock commands used by a script

Find personally identifiable information in conversational or other text and choose ways to protect it, such as masking, pseudonymization, tokenization, or encryption. It also covers configurable detection, compliance logging, and audit trails for handling sensitive data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Redacting personal details from conversation data
• Choosing an anonymization method for sensitive fields
• Setting up PII detection and audit logging

Check an MCP App before deployment with a structured verification workflow. It covers runtime behavior, handler order, text fallbacks, resource links, single-file builds, host styling, content security policy, and leftover migration patterns.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking an MCP App before deployment
• Finding missing text fallbacks or resource links
• Verifying an OpenAI-to-MCP migration

Audit an MCP App running in a sandboxed iframe by finding its network destinations in build output and source code. Classify origins for resources, connections, and nested frames, then prepare matching Content Security Policy settings for `registerAppResource`.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Audit network destinations used by an MCP App
• Find origins missing from a CSP configuration
• Prepare CSP entries for conditional API URLs

Use this skill to detect prompt injection attempts in LLM applications and plan layered defenses. It covers input sanitization, detection methods such as classifiers and canary tokens, output validation, logging, and alerting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Detecting instruction override attempts
• Adding input sanitization to an LLM app
• Designing layered prompt defenses

Review an implementation against coding, test coverage, specification, performance, and security criteria, along with project-specific checks. The skill assigns a weighted score and gives actionable fixes for failed items, then can recheck after remediation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether an implementation meets project standards
• Finding specification requirements not yet covered
• Running project-specific quality checks

Verify claims that work is complete, fixed, or passing by running the full relevant command, reading its output and exit code, and checking that the evidence supports the claim before reporting it or creating a commit or pull request.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a fix before reporting it
• Verifying a passing command result
• Confirming work before committing

Guide feature and bug fix work through test-driven development: write a failing test first, add the simplest code that makes it pass, then refactor while keeping tests green. It emphasizes verifying each stage before moving on.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Start a feature with a failing test
• Fix a bug using a test-first workflow
• Refactor code while keeping tests passing

Formalize a bug as a testable behavior contract: specify the conditions that trigger it, the correct behavior after a fix, and existing behaviors that must remain intact. The resulting assertions guide bug-fix tests and help check the change preserves those invariants.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Specifying a bug's triggering conditions
• Defining expected behavior after a fix
• Recording behaviors that regression tests must preserve

Check that planned success criteria, automated tests, manual checks, code review, and security review are complete before declaring work finished. The skill records verification failures and treats unresolved failures as a reason to halt completion.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking acceptance criteria before closing a task
• Confirming tests and reviews are complete
• Recording verification failures before completion

Use this skill for an independent, evidence-based code review focused on whether an implementation meets its specification. It returns a clear PASS or FAIL verdict with file and line references, using a fresh reviewer for each re-review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether code meets a specification
• Running a final cross-unit code review
• Re-reviewing a change after it failed

Use this skill to assess security risks in untrusted inputs and agent-generated code. It covers input validation, vulnerability scanning, isolated execution, output sanitization, and STRIDE threat modeling, with configurable levels for routine, pre-release, or critical-system audits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing code generated by an agent
• Checking how untrusted input is handled
• Preparing a security review before release

Review code changes for common security risks, including OWASP categories, injection, authentication and authorization flaws, data exposure, and dependency issues. Findings are grouped by severity and include file locations and practical remediation steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing user-facing code changes before merging
• Checking authentication and authorization changes
• Finding data exposure or injection risks

Run automated tests, linting, formatting, and coverage checks, then report quality metrics and gaps against project-specific thresholds. It helps teams apply strict, configurable checks during feature development.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking test coverage before a feature is finished
• Finding code paths or files that lack tests
• Running lint and formatting checks