Cloudflare Workers projects can fail through outdated APIs, incorrect bindings, and unsafe runtime patterns. This skill guides code reviews and implementation using current documentation and focused production checks.

Slow pages reduce engagement and hide complex loading bottlenecks. This skill records Chrome traces, evaluates Core Web Vitals, and prioritizes measurable fixes.

Bot protection often fails when frontend widgets and server checks are configured separately. This skill coordinates creation, integration, secret handling, and validation.

Cloudflare Sandbox projects can fail when stable and preview packages, images, or APIs are mixed. This skill keeps implementation aligned with the stable release.

Preview SDK changes make Cloudflare Sandbox applications difficult to implement correctly. This skill provides version-specific contracts, examples, and official documentation routes.

Stable Sandbox applications require coordinated API, image, and deployment changes for SDK 1.0. This skill performs the migration and validates the result.

Moving Next.js applications to Cloudflare Workers requires current compatibility and deployment guidance. This skill selects vinext workflows for new projects, migrations, development, and deployment.

Stateful Workers applications can fail when storage, concurrency, and routing patterns are unclear. This skill provides practical Durable Objects patterns for implementation, review, configuration, and testing.

Legacy security policies often lack direct Cloudflare One equivalents. This skill builds an accountable migration map, staged rollout, validation plan, and rollback path.

Transactional email setup is easy to misconfigure across Workers, REST APIs, and routing. This skill provides current patterns for sending, receiving, authentication, and deliverability.

Cloudflare 项目涵盖许多产品、API 和配置格式。此技能帮助 Claude、Codex 和 Claude Code 选择合适的 Cloudflare 服务，并使用有针对性的参考资料进行实现。

Building durable, real-time agents on Cloudflare Workers requires several coordinated APIs. This skill provides focused patterns for the Agents SDK and related Cloudflare services.

当必需字段缺失时，结构化 AI 输出可能会导致下游工作流失败。此技能会指导 Claude、Codex 和 Claude Code 在发布前完成 schema 验证。

大型 AI 任务在独立工作被逐步处理时会变慢。此技能帮助团队将可安全并行的工作拆分为有边界的子代理任务，并提供清晰的输出。

实现工作可能在遗漏失败的情况下结束。此技能会引导 Claude、Codex 和 Claude Code 在完成前执行测试、lint 和类型检查。

开发者需要一种一致的方式来验证代码更改。此技能为 Claude、Codex 和 Claude Code 提供项目特定的测试命令。

团队会丢失已完成 AI 编码任务中的经验教训。此技能引导 Claude、Codex 和 Claude Code 在工作后返回简洁的反思字段。

在 AI 辅助工作中，项目结构可能很难理解。此技能会指导 Claude、Codex 和 Claude Code 阅读架构、约定、模式和注意事项。

当生成的代码忽略既有仓库约定时，团队会浪费时间。此技能帮助 Claude、Codex 和 Claude Code 在实现前加载项目模式指南。

开发者需要一种一致的方式在交付前验证代码。此技能会指导 Claude、Codex 和 Claude Code 执行项目 lint 和 typecheck 命令。