查找技能

结合Sentry事件详情与代码调查WorldMonitor生产环境错误，区分噪声、已修复问题、产品缺陷等，并可按请求继续修复和测试。

• 通过Sentry链接或短编号调查错误
• 盘点未解决及已静音的问题
• 测试噪声过滤与缺陷修复

在浏览器中操作WorldMonitor仪表板，通过现有测试或手动步骤检查面板、地图、搜索与设置，保存截图和日志，并确认设置保存状态及网址变化。

• 检查修改后的仪表板启动情况
• 验证面板设置与布局保存
• 检查地图、搜索和国家简报

审查运行缓慢、不稳定或重复的测试，结合其保护的行为与执行、维护负担，判断应增加、合并还是删除测试，并选择适合修改范围的验证。

• 审查缓慢或不稳定的测试
• 为修改的行为选择测试
• 提交或拉取请求前审查测试修改

检测可能阻塞Python异步处理的输入输出调用，并推动修复和补充测试。验证问题重现时测试确实失败、恢复修复后通过，以监测问题再次出现。

• 检查异步Python代码变更
• 排查整个代码库的输入输出阻塞风险
• 补充清理与错误分支的测试

从 DeerFlow 代码更新、环境与配置检查，到本地或 Docker 启动及页面、API 基本验证，按步骤完成测试，并生成包含各项结果、问题和处理建议的报告。

• 确认 DeerFlow 首次安装情况
• 检查代码更新后能否启动
• 验证 Docker 部署

检查现有DeerFlow技能，评估发布准备情况、触发条件和安全边界。整理证据与问题，提供可直接采用的修改文本，并区分检查结论与运行验证。

• 检查技能是否具备发布条件
• 调查误触发或未触发的原因
• 检查附带脚本与安全边界

按测试驱动开发流程推进Rust功能实现和缺陷修复：先确认测试失败，再编写最少代码使其通过，随后重构，并完成格式、静态分析和测试检查。

• 从测试开始添加Rust功能
• 用测试复现缺陷后修复
• 测试无效输入和错误路径

指导你从测试开始开发RTK的Rust过滤器，使用真实命令输出，检查输出格式、异常输入处理和缩减率，并完成格式化、静态检查与测试。

• 为RTK添加新过滤器
• 与保存的预期输出比较
• 测试空输入、错误格式和彩色输出

在本地验证候选代码，与基准版本比较，分别报告阻断性失败、诊断性差异和证据不足，并明确列出尚未完成的CI检查。

• 维护者预先检查候选合并请求
• 将失败与准确的基准版本比较
• 区分阻断性失败与诊断性差异

在明确范围内运行质量检查，不修改产品代码，并记录受检版本、执行日志和结果，分别报告失败、未执行项目及已有未解决问题，为审查和发布准备提供依据。

• 执行临时质量检查
• 收集发布前的检查依据
• 确认快速检查省略的项目

通过命令行筛选OmniRoute的审计日志和请求历史，创建、管理并评估访问策略，比较不同时段的运行数据，并将记录导出到文件。

• 按用户和时段查询审计记录
• 导出记录以备审计
• 创建和评估访问策略

创建并运行自动评测集，按预期答案或评分标准评估大语言模型的回答，查看进度、单条得分与通过情况，也可比较模型，并用评分决定自动检查是否通过。

• 根据输入和预期答案创建评测
• 查看评测运行进度
• 检查失败回答及得分

Check whether an application is ready for production by finding unfinished code and testing real database and API connections. Review performance under load, authentication, environment settings, and deployment behavior to identify gaps before release.

中文简介正在准备中。当前显示英语简介。

• Finding unfinished code before release
• Testing real database and API integrations
• Checking performance under concurrent requests

Benchmark distributed consensus protocols, methods computers use to agree on shared results. Compare processing rates, response times, scaling behavior, and resource usage across Byzantine, Raft, and Gossip, then identify bottlenecks and potential tuning changes.

中文简介正在准备中。当前显示英语简介。

• Comparing Byzantine, Raft, and Gossip performance
• Measuring response times under increasing load
• Finding CPU, memory, or network bottlenecks

在部分参与节点故障或发送虚假信息时，协调分布式系统达成共识。涵盖投票消息认证、恶意参与者检测，以及领导节点故障后的更换。

• 协调存在恶意参与者时的共识
• 检查投票真实性与消息顺序
• 协调故障领导节点的更换

Scan code that handles sign-in, access permissions, payments, or user data for security weaknesses. The skill provides commands for a full security analysis and focused checks of input validation, which checks whether incoming values are acceptable.

中文简介正在准备中。当前显示英语简介。

• Reviewing sign-in and access permissions
• Checking payment and user data handling
• Finding input validation issues

Measure throughput, response times, and resource use for systems and groups of agents. Use baseline comparisons, load tests, and performance criteria to identify slowdowns, assess behavior under pressure, and summarize results with recommendations.

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
• Finding system limits through increasing load
• Checking coordination and load balancing across agents

Check a codebase for known dependency vulnerabilities, hard-coded secrets, and risky code patterns using Ruflo security tools. Choose a scan depth, inspect matching lines, and report verified concerns with a clear account of what was checked.

中文简介正在准备中。当前显示英语简介。

• Checking pull requests for security regressions
• Inspecting authentication and input-handling code for risky patterns
• Running security checks before production deployment

Find code that lacks test coverage and get suggestions for tests to add next. Focus on a chosen path, inspect gaps against a coverage threshold, or use a background worker for recurring checks after feature changes.

中文简介正在准备中。当前显示英语简介。

• Check for missing tests after adding a feature
• Find coverage gaps in a specific directory
• Focus on the most critical coverage gaps

Audit project dependencies for known vulnerabilities and outdated packages. Organize findings by severity, review proposed package changes before optional automatic fixes, and rerun the audit to check whether the reported vulnerability count decreased.

中文简介正在准备中。当前显示英语简介。

• Auditing third-party packages before a release
• Checking dependencies after installation or lockfile changes
• Investigating reported CVE advisories

Review implemented features against their requirements, add missing tests, and check performance constraints. Produce documentation, a table linking requirements to code and tests, and evidence showing whether the feature is ready for deployment.

中文简介正在准备中。当前显示英语简介。

• Review an implementation against its specification
• Add tests for uncovered requirements
• Link requirements to code and passing tests

Investigate failed GAIA benchmark questions by inspecting execution records and classifying causes such as missing tools, reasoning errors, or answer extraction bugs. Follow targeted fixes, verify them through another run, and save findings for future debugging.

中文简介正在准备中。当前显示英语简介。

• Investigate an incorrect answer for a specific task
• Diagnose a question that timed out
• Investigate a drop in benchmark pass rate

Check a Claude Code plugin before publishing. Inspect file placement, required configuration fields, metadata at the start of skill and agent files, and MCP tool references, then report failures with practical suggestions for fixing them.

中文简介正在准备中。当前显示英语简介。

• Check a newly created plugin before publishing
• Review structure after adding skills or agents
• Find missing fields and misplaced files

以只读方式检查MCP连接与操作相关的威胁，按威胁整理发现并报告最高严重程度，可输出表格或JSON，帮助准备发布前的安全审查材料。

• 开展发布前的安全检查
• 准备提交给安全团队的报告
• 在定期审计中检查威胁变化