Code changes can hide correctness, security, and maintainability issues before merge. This skill reviews diffs from relevant perspectives and returns prioritized, location-specific fixes.

Large feature specifications can be difficult to sequence and track. This skill creates dependency-ordered waves of small tasks with files and acceptance checks.

当结构、命名和职责逐渐偏移时，大型代码库会变得难以修改。此技能会引导安全的重构步骤，在提升可维护性的同时保留行为不变。

团队经常以模糊目标和缺失需求开始构建功能。此技能可将产品想法转化为结构化 PRD，并包含可衡量标准和技术背景。

Spring Boot 项目在分层、配置、测试和安全方面可能会变得不一致。此技能为使用 Spring Boot 设计可维护的 Java 服务提供简明的最佳实践指导。

GitHub 团队需要针对仓库、议题、拉取请求、Actions 和发布版本的快速命令指导。此技能为 Claude、Codex 和 Claude Code 提供聚焦的 gh CLI 示例和工作流。

复杂的流程和系统很难仅通过文字解释清楚。此技能可将清晰的描述转换为可编辑的 Excalidraw 图表及配套摘要。

团队通常需要与用户意图相匹配的文档，涵盖教程、操作指南、参考页面和解释说明。此技能会指导 Claude、Codex 和 Claude Code 明确范围、提出大纲，并起草结构化 Markdown。

Controller 窗口可能会过早关闭，或在 worker 运行时浪费上下文。此技能会安排低频、ETA 感知的检查，并等待明确的终止状态。

AI 辅助的分支通常包含多余注释、不必要的防御性代码，以及薄弱的类型规避做法。此技能会审查分支差异，并移除不符合周围代码风格的变更。

不安全或缺失的 Claude Code 权限可能会拖慢仓库设置，并造成可避免的风险。此技能会检查项目工具链，并提出与检测到的文件和服务相匹配的设置。

Important project context is easily lost between sessions. This skill stores it in structured files and helps retrieve it later with PARA and qmd.

Creating a new agent requires consistent configuration, a clear role charter, and the correct approval process. This skill guides Paperclip users through discovery, drafting, review, submission, and approval follow-up.

Plans often fail when tasks lack owners, dependencies, or clear starting conditions. This skill turns accepted Paperclip plans into a verified task graph that supports focused and parallel execution.

Managing an AI-agent company can require many API calls and scattered operational checks. This skill turns board requests into structured Paperclip workflows for onboarding, approvals, monitoring, and review.

Teams need a consistent way to coordinate agent work, approvals, and task progress. This skill guides Paperclip API workflows for assignments, updates, routines, and deliverables.

当组件、token 和布局以临时方式创建时，Paperclip UI 工作可能会发生偏移。此技能为 Claude、Codex 和 Claude Code 提供共享设计指南，用于实现一致的前端实现。

Developers may rebuild infrastructure that existing Convex components already provide. This skill identifies matching patterns and suggests one focused alternative after completing the current task.

当提供商接线、环境变量和后端检查不匹配时，Convex 身份验证设置可能会失败。此技能会指导正确的提供商流程，并添加经过验证的 Convex 身份验证模式。

Preparing reliable fixtures and bulk data for Convex can require repetitive schema checks and careful reruns. This skill guides idempotent internal mutations and CLI imports.