测试与安全技能

在Django发布或提交变更提案前，依次检查环境、代码质量、数据库变更、测试、漏洞及配置，汇总各阶段是否通过和需要修复的问题。

• 提交Django变更提案前检查
• 检查数据库迁移
• 核对测试覆盖率目标

检查Django应用的登录、权限、输入处理和生产配置，梳理恶意查询、脚本注入及非预期请求的防护，并审查文件上传、API保护、密钥管理和安全日志。

• 审查登录与用户权限
• 上线前检查生产配置
• 审查输入处理与请求防护

协助编写和修复C++测试，配置GoogleTest与CTest，调查失败或结果不稳定的原因，并测量测试覆盖范围、配置检测内存误用与并发竞争的运行时检查。

• 编写C++单元测试与集成测试
• 配置GoogleTest和CTest
• 调查测试结果不稳定的原因

Write and review C# and .NET tests using xUnit examples. Covers unit tests, mocks that replace dependencies, API and database integration tests, reusable test data, and project organization to check behavior and outcomes.

中文简介正在准备中。当前显示英语简介。

• Adding tests for C# services
• Testing ASP.NET Core APIs
• Checking database persistence

Have an AI agent assess its completed work for accuracy, completeness, clarity, actionability, and conciseness. Receive a scorecard with evidence, an average score, and prioritized improvements tied to the original request.

中文简介正在准备中。当前显示英语简介。

• Assess code after a multi-file implementation
• Check deliverables after a multi-step workflow
• Evaluate a design document or written analysis

用实际开发任务比较多个编程智能体，记录成功率、可获取的API费用、耗时和重复运行的稳定性，为工具选型及更新后的性能评估提供数据。

• 用实际开发任务比较智能体
• 采用新工具或模型前进行评估
• 检查智能体更新后的性能

通过浏览器检查发布前的网页，测试表单与登录流程，对比三种屏幕宽度下的显示效果，检查速度指标和无障碍问题，并汇总是否可以发布及需要修复的问题。

• 验证测试环境中的新功能
• 发布前检查表单与身份验证
• 对比三种屏幕宽度的布局

为AI修改的代码补充回归测试，自动检查API必需字段和处理分支，并建立先运行测试与构建、再进行AI审查的流程，检测已修复问题是否再次出现。

• 修复缺陷后补充回归测试
• 检查API响应中的必需字段
• 核对测试与生产环境的响应

Measure web page speed, API response times, and build or test duration. Save baseline measurements as JSON tracked in Git, then compare results before and after changes to identify performance regressions and assess launch targets.

中文简介正在准备中。当前显示英语简介。

• Comparing performance before and after a code change
• Investigating reports that a page feels slow
• Checking performance targets before launch

Trace button clicks and form actions through each state change to uncover conflicting updates, unintended resets, and asynchronous timing problems. Report where the final screen behavior differs from what the user expects, with specific fixes.

中文简介正在准备中。当前显示英语简介。

• Investigating buttons that appear to do nothing
• Checking shared state after a major refactor
• Auditing critical user flows before release

Investigate suspected malicious changes in open-source software on GitHub by comparing repository history, APIs, and archives. Attempt to recover deleted evidence, identify signs of compromise, and produce a report separating verified facts from hypotheses.

中文简介正在准备中。当前显示英语简介。

• Investigate suspicious commits or workflow changes
• Attempt to recover commits hidden by rewritten history
• Trace possible credential leaks

Test how API-accessible language models respond to attempts to bypass safety filters. The skill covers prompt templates, input transformations, parallel response comparisons, and Hermes configuration, with automated scoring of refusals, answer quality, and speed.

中文简介正在准备中。当前显示英语简介。

• Evaluating model resistance to safety-filter bypass attempts
• Comparing responses to transformed inputs
• Comparing refusals, answer quality, and speed across models

Find personal information exposed on data brokers and people-search sites, then manage removal requests for consenting individuals. Tracks submissions, checks whether listings disappear, schedules repeat scans, and collects steps that require human help.

中文简介正在准备中。当前显示英语简介。

• Finding sites exposing personal information
• Managing removal requests for a consenting family member
• Checking progress and verifying removals

Test an authorized web application, map its exposed pages and inputs, and verify suspected vulnerabilities with reproducible evidence. Produce a security report covering confirmed findings, their impact, reproduction steps, and suggested fixes.

中文简介正在准备中。当前显示英语简介。

• Check a staging web application for vulnerabilities
• Verify whether a suspected vulnerability is reproducible
• Compile evidence and fixes into a security report

Set up the 1Password CLI and use stored passwords or API keys in commands and configuration templates. Choose an authentication method, retrieve secret references, and pass credentials to processes through environment variables.

中文简介正在准备中。当前显示英语简介。

• Installing and configuring the 1Password CLI
• Running commands with stored API keys
• Filling configuration templates with stored secrets

Test an app from the perspective of a frustrated, less technical user. Find confusing steps and barriers, separate actionable usability problems from personal complaints, and produce screenshots, suggested fixes, and prioritized tickets.

中文简介正在准备中。当前显示英语简介。

• Reviewing usability before a launch or demo
• Checking the experience of a new user
• Finding friction in signup and subscription flows

Guide development through test-driven development (TDD): write a test, confirm it fails, add minimal code, then clean up. Apply this cycle to features and bug fixes while checking that existing behavior still passes its tests.

中文简介正在准备中。当前显示英语简介。

• Adding features with tests written first
• Reproducing a bug in a test before fixing it
• Refactoring while keeping tests passing

Check code changes before committing with security scans, tests, linting, and an independent agent review. Compare failures against the previous baseline, then use a separate agent to fix reported problems and repeat verification.

中文简介正在准备中。当前显示英语简介。

• Checking feature changes before a commit
• Scanning added code for secrets and injection risks
• Separating new test failures from existing failures

Explore a web app in the browser to find functional, visual, and usability issues. The skill organizes screenshots, console errors, and reproduction steps into a Markdown bug report, with findings grouped by severity and category.

中文简介正在准备中。当前显示英语简介。

• Explore key user flows before release
• Check forms with valid, invalid, and empty input
• Document layout issues and JavaScript errors

Independently reviews deliverables handed over through Kanban, checks them against acceptance criteria and test evidence, and records an approval, actionable change request, or escalation when a human decision or external prerequisite is needed.

中文简介正在准备中。当前显示英语简介。

• Reviewing deliverables against acceptance criteria
• Rechecking corrections after a change request
• Returning reproducible defects to the implementer

Test local web applications with Playwright, a browser automation tool. Check frontend functionality, investigate interface behavior, capture screenshots, and inspect browser logs, with a helper script that manages one or more application servers during testing.

中文简介正在准备中。当前显示英语简介。

• Checking buttons and forms in a local web app
• Investigating interface problems with screenshots and logs
• Testing with both frontend and backend servers running

Review a codebase for bugs, security risks, failures under expected load, missing tests, slow paths, and unnecessary code. Receive prioritized findings with concrete failure cases, small proposed fixes, and the consequences of leaving each issue unresolved.

中文简介正在准备中。当前显示英语简介。

• Assess the quality of an inherited codebase
• Find risks under expected concurrent usage
• Identify unnecessary code and dependencies

Plan a paid evaluation with predefined success criteria, comparison groups, decoy items, and stopping rules. Rehearse without spending, then run a three-item paid pilot and use its spending table to inform approval.

中文简介正在准备中。当前显示英语简介。

• Define evaluation criteria before spending
• Rehearse an evaluation at zero cost
• Check spending with a three-item paid pilot

Audit an existing test suite to find low-value or duplicate tests and code kept solely for those tests. Receive findings for review, with changes limited to batches you explicitly approve.

中文简介正在准备中。当前显示英语简介。

• Reviewing the value of existing tests
• Finding duplicate tests
• Finding code kept only for tests