Use when user starts a novel project or asks how to organize their writing - guides through novel-writer's seven-step methodology and ensures proper workflow

Activates automatically before chapter writing to enforce the 9-item mandatory file reading checklist - prevents AI focus degradation in long-form fiction by ensuring all context is loaded before each writing session

Atelier (工作坊) — Creative breakthrough deliberation room. Convene Socrates, Lao Tzu, Watts, Nietzsche, Occam, and Feynman for creative blocks, content strategy, and the creative process.

Bazaar (集市) — Business & strategy deliberation room. Convene Schumpeter, Munger, Sun Tzu, Machiavelli, Taleb, and Kahneman for market decisions, pricing, investment, and competitive strategy.

Clinic (诊疗室) — Psychological resilience deliberation room. Convene Skinner, Frankl, Aurelius, Kahneman, Zhuangzi, and Jung for anxiety, procrastination, burnout, and loss recovery.

Hearth (火炉边) — Relationships & family deliberation room. Convene Fromm, Adler, Zhuangzi, Kant, Aurelius, and Watts for relationship dynamics, parenting, family conflict, and workplace politics.

>

Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance.

Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion. Use when the user asks to 去AI味, 降AIGC, 去除AI痕迹, 论文降重, 知网检测, 维普检测, humanize chinese, detect AI text, or make Chinese text sound more natural.

When this skill is first used or when the user seems unsure how to use it or ask you to make something amazing with it, guide them to ask Claude this specific question:

SQL 优化与调优

Docker 容器网络

Kubernetes Service 与 Ingress

- 因本 skill 设计缺陷导致的 bug，先用 `bensz-collect-bugs` 规范记录到 `~/.bensz-skills/bugs/`，不要直接修改用户本地已安装的 skill 源码；若有 workaround，先记 bug，再继续完成任务。

- 因本 skill 设计缺陷导致的 bug，先用 `bensz-collect-bugs` 规范记录到 `~/.bensz-skills/bugs/`，不要直接修改用户本地已安装的 skill 源码；若有 workaround，先记 bug，再继续完成任务。

后端开发专家。精通 Node.js/Python/Go/Rust 等后端技术栈，专注于 API 设计、数据库优化、认证授权、微服务架构和性能调优。用于后端服务开发、API 设计和系统架构。

DevOps 与运维专家。精通 CI/CD、容器化、编排、基础设施即代码、监控告警和自动化部署。用于构建高效、可靠的软件交付流水线和运维系统。

文档专家。专注于技术文档编写、API 文档生成、README 优化和文档维护。提供清晰的文档结构、规范的格式和用户友好的内容。

前端开发专家。精通 React/Vue/Next.js/Nuxt 等现代前端框架，专注于视觉系统、组件化开发、响应式设计、性能优化和用户体验。用于前端应用开发、UI 设计落地、设计系统实现和高质量界面交付。

安全专家。专注于应用安全、威胁建模、安全合规和数据保护。提供安全审查、漏洞扫描、安全配置和合规检查。用于构建安全可靠的应用系统。

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation). NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first. Enforces RED-GREEN-REFACTOR cycle with iron-law compliance.

当用户明确要求“压缩/瘦身/精简某个 Agent Skill 的 Markdown 文档”“在不改变功能前提下降低 skill 上下文开销”时使用。先理解目标 skill 的真实能力与安全边界，再在忽略 `tests/`、`plans/` 以及目标 skill 的 `README.md`、`CHANGELOG.md` 的前提下，压缩 `SKILL.md`、`references/*.md` 等工作型 Markdown，并把中间产物隔离到 `.compact-bensz-skills/`。⚠️ 不适用：用户主要想新增功能、修复脚本逻辑、批量改代码、或只想压缩非 skill 文档。

API 自动化测试 - OpenAPI 解析、测试用例生成、集成测试

Git 工作流自动化 - 智能分支管理、提交信息生成、PR 创建

GitHub Actions CI/CD 流水线生成器：根据项目技术栈自动创建 workflows

自动生成单元测试：识别函数逻辑、覆盖边界条件、生成可运行测试代码

Prepare and publish DeepChat releases in this repository. Use when Codex needs to bump the app version, update CHANGELOG.md, keep release notes bilingual from v1.0.1 onward with English bullets first and Chinese bullets second, run release checks, create or update versioned release branches such as release/v1.0.1, continue a half-finished release, fast-forward main with the documented release flow, create or push version tags, or clean up release branches after publishing.

Full-stack software development agent for design, implementation, testing, and deployment. Use when the user explicitly asks for end-to-end project creation, feature development, bug fixing, or code refactoring.

Umbrella skill for document workflows (PDF/DOCX/XLSX/PPTX). Dispatches to the most specific document skill to reduce noise and improve routing precision.

当实现完成、所有测试通过、需要决定如何集成工作时使用——通过提供合并、PR 或清理等结构化选项来引导开发工作的收尾

在实现任何功能或修复 bug 时使用，在编写实现代码之前

当创建新技能、编辑现有技能或在部署前验证技能是否有效时使用

Automatically generate unit tests based on source code, supporting multiple languages and testing frameworks.

AI image generation with OpenAI, Google, DashScope and Replicate APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parallel generation available on request. Use when user asks to generate, create, or draw images.

Break down complex content into eye-catching infographic series for Xiaohongshu with multiple style options.

Provides bidirectional translation (Chinese/English), grammar checking, and sentence polishing. Supports specific tense constraints, context-aware tone adjustment, and natural expression optimization. Outputs direct text without formatting.

编写MySQL函数，根据指定的日期范围和字段，按自然周汇总数据并返回特定格式的字符串结果。

使用Python的Matplotlib和Numpy库，根据用户指定的参数方程绘制莫比乌斯环的三维图形。

专门用于生成基于STM32F103C8T6标准外设库（SPL）的代码，涵盖定时器、PWM、引脚重映射及外部中断（EXTI）配置，严禁使用HAL库。

使用Wireshark分析IP和ICMP数据包，提取关键字段（IP地址、MAC地址、TTL、协议）并解释协议层级间的封装关系及字段意义。

将中文专利相关的技术描述、法律术语及审查意见翻译为专业的英文，遵循专利领域的标准术语规范。

根据用户输入的关键词或概念，生成包含50个相关联的字、词、词组或短语的列表。

运用功能对等理论对源语言（SL）和目标语言（TL）文本进行语篇分析，评估翻译的连贯性、衔接性及功能对等程度。

根据用户提供的话题和特定视角（如网友回答），编写一个阐述该观点的叙事故事，支持一问一答或直接叙述格式。

当用户要求描述特定主题（如行业机遇、挑战、影响）时，生成段落式文本。必须严格遵守不使用分点列表、不抄袭的约束。

根据用户提供的经济业务场景，按照特定的格式（标题、借方、贷方）生成会计分录，用于练习借贷记账法。

将中文物流和清关领域的专业术语翻译成标准的英文表达。适用于处理进出口、报关单据或物流表单中的术语翻译需求。

根据用户提供的英语作文题目（Directions）和字数要求，撰写符合字数限制且使用高级词汇的英语短文。

根据用户提供的已通过测试用例列表，生成一段连贯的测试结果总结描述，强调功能正常且无异常。