AIDotNet

自动分析B站视频内容，下载视频并拆解成帧图片，使用AI分析并生成详细的专题文档或实操教程。

设计RESTful API并生成OpenAPI/Swagger规范文档，遵循行业最佳实践。包括端点命名、请求/响应模式和错误处理模式。

为GitHub Actions、GitLab CI、Azure DevOps和Jenkins生成CI/CD流水线，包含构建、测试、部署阶段、缓存和密钥管理。

全面的代码审查技能，分析代码质量、识别问题、安全漏洞，并提供带严重性评级的改进建议。

设计和优化数据库模式，支持PostgreSQL、MySQL、SQLite和MongoDB。包括ER建模、规范化、索引优化和迁移脚本生成。

创建和管理多容器应用的Docker Compose配置，包含生产级设置、健康检查和网络配置。

生成全面的文档，包括README文件、API文档、代码注释（JSDoc、docstrings、XML）和架构文档。

生成Express.js REST API，包含TypeScript、中间件、验证、错误处理和认证模式。

Create or modify OpenCowork Custom Extensions. Use when the user asks to build a custom extension/plugin for OpenCowork that adds Agent tools, declarative HTTP tools, sandboxed JavaScript handlers, extension configuration fields, network allowlists, or custom…

Explore a supplied product, service, venue, or offer across a diverse 25-family image-ad prompt library. Use when the user wants Ads Explorer, ad directions, image ad prompts, paid social ideas, broad campaign ad exploration, or a review wall before final…

Use when a broad business creative brief needs the Creative Production Explore front door: a compact chooser for Positioning, Mood boards, Scenes, Offers, Ads, Shots, Logos, or active production Assets.

Create publish-safe generative polish for business visuals. Use when the user asks to make a selected asset, social card, carousel, launch visual, chart card, or creative pack visually stronger while preserving exact text, data, logos, dimensions, safe zones,…

Use when a brand brief needs identity concepts, wordmarks, lockups, identity-system routes, or a logo review board before vector production or final brand polish.

Use when a user asks Creative Production to generate several concept images, image options, visual directions, mood boards, visual territories, audience feel, campaign references, or brand direction before mood-board remixing, asset production, or polish.

Use when a product, digital product, service, venue, experience, or campaign brief needs 25-family offer-led prompt exploration, contact sheets, review galleries, or coverage checks before remix, asset production, or polish.

Explore commercially useful positioning routes before visual generation. Use when the user needs to clarify audience, occasion, growth goal, proof, or market angle before mood boards, scenes, business assets, ads, menus, cards, one-pagers, listings, or social…

any input (code, docs, papers, images, videos) to knowledge graph. Use when user asks any question about a codebase, documents, or project content - especially if graphify-out/ exists, treat the question as a /graphify query.

Deliberate reasoning skill: enforce multi-step analysis, hypothesis testing, and option evaluation before answering complex questions