测试设计、漏洞检测、质量保证（1.3万 个）
Review and write Solidity smart contracts with security in mind. Address reentrancy, where external calls trigger repeated execution, along with numeric overflow and access control issues, using implementation patterns, security tests, and documentation for audit preparation.
中文简介正在准备中。当前显示英语简介。
Build Solidity contract tests with Hardhat and Foundry. Check individual functions, contract interactions, gas usage, and varied inputs, and use a local copy of mainnet state to test against existing contracts.
中文简介正在准备中。当前显示英语简介。
Guide web app testing with screen readers such as VoiceOver, NVDA, and JAWS. Check forms, dialogs, keyboard navigation, and spoken update notifications to identify accessibility problems across desktop and mobile browser combinations.
中文简介正在准备中。当前显示英语简介。
Configure a Claude Code hook that checks shell commands before execution and blocks flags that skip Git checks or commit signing. It helps preserve existing commit quality checks while documenting the guard's limits.
中文简介正在准备中。当前显示英语简介。
Identify a project's existing test tools and conventions, then run the smallest useful test suite for a specific change. Add or update tests when authorized, and report commands, results, and remaining gaps without overstating coverage.
中文简介正在准备中。当前显示英语简介。
Test a local web app in a real browser, checking the page structure, console messages, and network activity. Follow controls observed on the page and record evidence showing whether the tested flow passes or fails.
中文简介正在准备中。当前显示英语简介。
Review concrete code for exploitable security defects, including missing access checks, unsafe input handling, and exposed secrets. Report verified issues with file locations, reachable attack paths, severity, and suggested fixes.
中文简介正在准备中。当前显示英语简介。
Check that an actual app, API, or command-line tool works by exercising its real entry point with realistic inputs. Collect observable evidence such as outputs, logs, exit codes, or screenshots, and report remaining uncertainty.
中文简介正在准备中。当前显示英语简介。
Verify Codewhale changes with checks matched to their scope and risk. Collect actual test counts, automated limit checks, and command output to show what passed, what failed, and what remains unverified.
中文简介正在准备中。当前显示英语简介。
Check Codewhale release readiness through ordered tests, builds, version checks, and manual terminal checks. Record command results and observed behavior, including responsiveness, route isolation, and follow-up input handling, while explicitly identifying any skipped checks.
中文简介正在准备中。当前显示英语简介。
Builds and installs Codewhale with a source revision identifier, then verifies the installed version in a fresh shell. It guides hands-on runtime checks for interface behavior, routing, approvals, and other changes that automated tests may miss.
中文简介正在准备中。当前显示英语简介。
Verify changes to Office add-in administration scripts using a temporary home directory. It covers syntax checks, cache-clearing behavior, identifier handling, and storage comparisons to check that removing add-in manifests preserves chat history.
中文简介正在准备中。当前显示英语简介。
Write and fix Java integration tests using Testcontainers 2.x to run real databases and other dependencies in containers. Covers startup checks, container lifecycles, test data isolation, CI setup, and migration from version 1.x.
中文简介正在准备中。当前显示英语简介。
Audit and repair existing Cypress tests that fail intermittently. The skill identifies fixed delays, fragile command chains, shared state, and version compatibility issues, then guides targeted changes and repeated test runs to check the results.
中文简介正在准备中。当前显示英语简介。
Migrate existing PowerShell Pester tests through major versions from v3 to v6. The skill guides assertion updates, setup restructuring, mock changes, and execution configuration, using before-and-after test results to investigate failures while preserving what each test checks.
中文简介正在准备中。当前显示英语简介。
Turn a browser scenario into a Playwright TypeScript test by first performing its steps through Playwright MCP. The skill saves the generated test in the tests directory, runs it, and revises it until it passes.
中文简介正在准备中。当前显示英语简介。
Update Pester test assertions, checks of expected results, from classic v5 syntax to v6 Should-* commands. Identify behavior changes involving booleans, empty values, and collections, then verify the suite and report conversions needing human judgment.
中文简介正在准备中。当前显示英语简介。
Explore a website with Playwright MCP by interacting with three to five key features or user flows. Document actions, interface elements and how to locate them, then generate test cases from the findings.
中文简介正在准备中。当前显示英语简介。
Analyzes one .NET project to plan integration tests for an Oracle-to-PostgreSQL migration. Identifies database access methods, prioritizes migration risks, and documents test cases, seed data, and coverage, including empty strings, NULL values, and timezone behavior.
中文简介正在准备中。当前显示英语简介。
Check an MCP server before release through a real client session. Compare available features with source code and documentation, test invalid requests and installation, and produce a verdict backed by reproducible commands and responses.
中文简介正在准备中。当前显示英语简介。
Write focused Java unit tests with JUnit 5, including tests that repeat checks across different inputs. Covers clear test structure, exception checks, mock objects that replace dependencies, and ways to organize test suites.
中文简介正在准备中。当前显示英语简介。
Review MCP configurations for exposed credentials, risky command patterns, and package versions that can change unexpectedly. Produce a report with severity levels and suggested fixes without running the commands defined in the configuration.
中文简介正在准备中。当前显示英语简介。
Write JavaScript and TypeScript tests with Jest using consistent structure, dependency mocking, and checks for asynchronous code. Includes guidance for snapshots and React components, focusing on user interactions, accessibility, and choosing appropriate assertions for expected results.
中文简介正在准备中。当前显示英语简介。
Review source code for MCP, a protocol connecting AI applications to tools. Check authentication, input validation, unsafe execution, and other security risks, then report findings with file and line references and separate manual follow-ups.
中文简介正在准备中。当前显示英语简介。