테스트·보안 스킬

Run a single quality-check command before declaring work complete, and report its actual pass count. Address failed checks, rerun verification, and inspect changed HTML for interaction states and responsive behavior, with aesthetic judgment reserved for separate review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Verifying quality before declaring a build complete
• Reporting actual pass counts during review
• Fixing failed checks and rerunning verification

Audit interfaces against WCAG 2.2 accessibility criteria and ARIA patterns for accessible controls. Receive findings with criterion references, severity, and specific fixes, covering measured contrast, keyboard navigation, screen-reader information, focus visibility, and interaction states.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing a screen for accessibility issues
• Measuring contrast across interaction states
• Reviewing keyboard and screen-reader support

Set up checks that catch design regressions before release. Validate shared design values, contrast, accessibility, and visual changes across component states and themes, then complete manual checks for keyboard use, screen readers, and other accessibility needs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding design quality checks to CI
• Checking components before release
• Catching visual changes in dark mode and RTL layouts

Review web security, browser compatibility, and code quality using live page checks and source inspection. Identify specific problems, apply targeted fixes, and repeat the checks to verify changes without treating audit scores as security guarantees.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review security headers and vulnerable dependencies
• Replace deprecated browser APIs
• Fix HTML errors and unhandled exceptions

Audit and improve web accessibility using WCAG 2.2, guidelines for making websites usable by people with disabilities. Check labels, contrast, keyboard navigation, and screen reader support, then verify fixes through automated and manual testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review keyboard navigation and visible focus
• Fix form labels and error announcements
• Check image descriptions and color contrast

Audit website performance, accessibility, SEO, security practices, and how well AI assistants can interact with pages. Combine browser measurements with code inspection to prioritize fixes and report which improvements have been verified.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review website quality before launch
• Prioritize fixes across multiple quality areas
• Check whether AI assistants can use page controls

Audit an AI agent’s memory for invented facts, circular confirmations, and corrupted records. Check actual system outputs before reviewing logs, classify the findings, and quarantine affected memory entries when contamination is detected.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Audit memory after two consecutive task or tool failures
• Run a nightly memory integrity check
• Compare recorded claims with actual system outputs

Select and run local checks that match the changed files before pushing or marking a PR ready. Covers TypeScript, Rust, renderer behavior, release scripts, and verification gates, while reporting failures, skipped checks, and platform limitations accurately.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Selecting focused tests before pushing changes
• Checking types and dependencies across packages
• Verifying renderer changes and release scripts

Check whether a Codex Desktop update affected codexhost controls, connections, or message routing. Compare application internals with the running interface, then report confirmed failures, possible impacts, and checks that remain unverified.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check compatibility after a Codex Desktop update
• Investigate missing or misplaced controls
• Locate the cause of connection or routing regressions

Run code quality checks in grails-core, read Markdown reports grouped by module, and address formatting or analysis findings. The skill explains tool settings, available automatic fixes, manual corrections, and separate test coverage reports.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Read aggregated code quality reports across modules
• Apply automatic fixes to supported CodeNarc findings
• Enable PMD or SpotBugs for selected modules

Run targeted or full tests across grails-core modules and interpret Gradle reports to investigate failures. Diagnose shared-state interference, parallel execution issues, and regressions, then use aggregated unit and integration results to guide fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Rerunning a failing module or test case
• Checking affected modules before a commit
• Investigating regressions after dependency updates

Implement features or fix bugs through test-driven development: write a failing test, add the smallest change that passes it, then clean up the code. Each cycle checks observable behavior and shows the transition from failure to success.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Defining business logic with tests
• Reproducing a bug before fixing it
• Building parsers or state machines in small steps

Add safeguards to Claude Code sessions by requesting approval for recognized dangerous shell commands and restricting file edits to a chosen directory. Use either protection separately or combine them, then clear both when finished.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing dangerous commands in an unfamiliar codebase
• Restricting a module refactor to one directory
• Limiting edits to the code being reviewed

Set up AI checks in Claude Code that review commit messages, coding conventions, destructive commands, and file writes before execution. Operations that fail the checks are blocked with an explanation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Validate commit message formats
• Check conventions beyond automated code checks
• Review commands that delete important directories

Generate pytest tests for Python functions, covering expected behavior, edge cases, errors, and interactions between functions. Organize tests by function, reuse shared setup, and check multiple inputs with parameterized tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating tests for Python functions
• Testing empty inputs, None, and boundary values
• Checking invalid inputs and missing files

Assess and harden a BambooHR integration that handles employee information, credentials, files, or webhooks. Map trust boundaries, review permissions and data flows, identify risks in storage and logging, and document practical fixes and evidence without exposing secrets or employee records.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing access and permissions in a BambooHR integration
• Checking storage and logs for employee data exposure
• Assessing webhook verification and credential handling

Build an offline development and test loop for a BambooHR integration using synthetic employee fixtures and a fake transport. Add contract scenarios and keep any test-tenant reads behind an explicit profile and approval gate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing BambooHR behavior without using employee records
• Adding offline contract tests for an HR integration
• Generating synthetic webhook payloads for local development

Add CI checks for a BambooHR connector using synthetic HR data, pinned API contracts, and secret scans. The checks cover request and schema behavior, redaction, retries, and tenant isolation, with an optional, gated smoke test against an approved test tenant.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding regression checks for a BambooHR connector
• Checking API schema changes before release
• Blocking releases when tests or secret scans fail

Audit a repository’s tests across seven layers, from Git hooks to acceptance checks. Measure coverage and other quality checks, trace requirements to tests, and produce reports that identify gaps for handoff to a separate implementation skill.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding gaps across seven testing layers
• Checking whether requirements have matching tests
• Reviewing changes that weaken test quality rules

Review a cryptocurrency wallet’s token approvals, contract interactions, and transaction patterns. The skill produces a risk score, flags concerning activity, and prioritizes approvals for review in a security report.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking active token approvals for a wallet
• Reviewing transaction history for suspicious patterns
• Getting a wallet security score and risk summary

Inventory and audit agent system files such as skills, plugins, subagents, MCP configurations, hooks, and marketplace catalogs. It selects the relevant specification, runs available checks, and reports evidence, severity, remediation options, and any areas that remain unverified.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a skill or plugin before merging
• Checking a marketplace submission
• Auditing portability or security across agent files

Review Apple Notes automation scripts for appropriate permissions, protected exports, and secure credential handling. Establish local processing and cleanup practices, skip locked notes, and produce review evidence that excludes note content and secrets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing permissions for Notes automation
• Protecting exported notes and temporary files
• Moving script credentials into Keychain

Build automated checks for Attio integration changes using sample responses and response format tests. Produce pull request evidence without changing CRM records, with an optional, explicitly enabled read-only check against the live API.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding automated checks for Attio integration pull requests
• Testing pagination, errors, and retry decisions
• Checking test outputs for exposed secrets or personal data

Audit CORS, the browser rules for requests between different sites, by probing API responses with varied Origin headers. Check origin validation, credential settings, preflight requests, and caching headers, then produce findings in JSON, JSONL, or Markdown.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate failed CORS preflight requests
• Triage reports of reflected Origin headers
• Audit API endpoints before launch