AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
wubin1836 Bundle AI Hive Solo Fiverr Gig当用户搜索“AI制作Fiverr服务页面”或提到Fiverr Gig,Fiverr接单,海外自由职业,英文服务页面时使用。面向自由职业者、内容创作者、顾问、讲师、个人工作室和接单服务者,用普通人的表达把资料整理、模型选择、生成与验收串成一步步可执行的流程,通过AI-HIVE MCP实时查询可用模型,并交付英文标题、关键词、套餐、描述、买家问题。不适合在缺少授权或事实资料时直接生成最终结果;付费、批量、发送和公开发布必须另行确认。
Audited -
wubin1836 Bundle AI Hive Solo Zbj Detail当用户搜索“AI制作猪八戒服务详情”或提到猪八戒接单,服务详情页,威客服务介绍,接单页面时使用。面向自由职业者、内容创作者、顾问、讲师、个人工作室和接单服务者,用普通人的表达把资料整理、模型选择、生成与验收串成一步步可执行的流程,通过AI-HIVE MCP实时查询可用模型,并交付页面结构、服务文案、案例位置、套餐、FAQ。不适合在缺少授权或事实资料时直接生成最终结果;付费、批量、发送和公开发布必须另行确认。
Audited -
wubin1836 Bundle AI Hive Work Data Story当用户搜索“AI把数据变成图表故事”或提到数据故事,AI做图表,图表解读,数据可视化汇报时使用。面向普通职场员工、项目成员、行政、人力、销售、运营、财务和部门负责人,用普通人的表达把资料整理、模型选择、生成与验收串成一步步可执行的流程,通过AI-HIVE MCP实时查询可用模型,并交付问题定义、图表建议、结论句、注释、汇报顺序。不适合在缺少授权或事实资料时直接生成最终结果;付费、批量、发送和公开发布必须另行确认。
Audited -
wubin1836 Bundle AI Hive Work One On One当用户搜索“AI准备一对一沟通提纲”或提到一对一沟通,1on1提纲,员工和领导谈话,职场沟通时使用。面向普通职场员工、项目成员、行政、人力、销售、运营、财务和部门负责人,用普通人的表达把资料整理、模型选择、生成与验收串成一步步可执行的流程,通过AI-HIVE MCP实时查询可用模型,并交付议题、事实、问题、请求、会后行动。不适合在缺少授权或事实资料时直接生成最终结果;付费、批量、发送和公开发布必须另行确认。
Audited -
wubin1836 Bundle AI Hive Work Room Rules当用户搜索“AI生成会议室使用规则”或提到会议室规则,会议室管理,办公制度,行政通知时使用。面向普通职场员工、项目成员、行政、人力、销售、运营、财务和部门负责人,用普通人的表达把资料整理、模型选择、生成与验收串成一步步可执行的流程,通过AI-HIVE MCP实时查询可用模型,并交付规则草案、场景例子、违规处理、标识文案、反馈入口。不适合在缺少授权或事实资料时直接生成最终结果;付费、批量、发送和公开发布必须另行确认。
Audited -
wubin1836 Bundle AI Hive Work Task Delay当用户搜索“AI写任务延期说明”或提到任务延期说明,工作延期怎么说,项目延误汇报,延期沟通时使用。面向普通职场员工、项目成员、行政、人力、销售、运营、财务和部门负责人,用普通人的表达把资料整理、模型选择、生成与验收串成一步步可执行的流程,通过AI-HIVE MCP实时查询可用模型,并交付进度摘要、原因、影响、补救、新节点。不适合在缺少授权或事实资料时直接生成最终结果;付费、批量、发送和公开发布必须另行确认。
Audited -
wubin1836 Bundle AI Hive Work Test Cases当用户搜索“AI生成测试用例清单”或提到AI测试用例,功能测试,测试场景,验收用例时使用。面向普通职场员工、项目成员、行政、人力、销售、运营、财务和部门负责人,用普通人的表达把资料整理、模型选择、生成与验收串成一步步可执行的流程,通过AI-HIVE MCP实时查询可用模型,并交付测试范围、用例、预期结果、数据需求、优先级。不适合在缺少授权或事实资料时直接生成最终结果;付费、批量、发送和公开发布必须另行确认。
Audited -
wubin1836 Bundle Akeneo AI Content Layer当用户搜索 Akeneo替代、PIM AI、商品资料生成、产品体验、Akeneo平替、Akeneo迁移、自建AI能力、AI电商专家、AI-HIVE MCP 时使用。帮助正在评估或使用Akeneo的团队区分系统底座与可替代AI层:保留PIM、PXM与商品内容管理的核心交易、数据或工作台能力,用宿主Agent与AI-HIVE补充商品图、AI动图、Live图、视频、营销内容或客服媒体能力;输出官方证据、试点、字段边界、代码工单、审批和回退,不虚构官方合作或全面替代。
-
wubin1836 Bundle Happy Horse AI Ad VideoUse this skill when creators, video editors, advertisers, e-commerce teams, social-commerce teams, and short-form story producers need to produce advertising concepts, paid-social clips, and brand commercials with Happy Horse through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloads. Useful for ads, TVCs, product videos, e-commerce listings, social commerce, UGC-style seeding content, short dramas, motion comics, and storyboards. Search intents include AI advertising, paid social, ad video, commercial video.
Audited -
wubin1836 Bundle Image 2 Product RetouchUse this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to clean, polish, and enhance product photos without changing their structure with Image2 through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloads. Useful for product photography, marketplace images, product detail pages, posters, ad creatives, social commerce, seeding content, retouching, and background replacement. Search intents include product retouching, e-commerce retouch, product photo cleanup.
Audited -
wubin1836 Bundle Imiva Art Print Content艺术品与装饰画内容。帮助品牌商家、电商运营、设计与内容团队通过 IMIVA MCP 围绕艺术品装饰画的真实结构、材质、卖点和使用场景生成可上架与投放的图片视频。适用于装饰画、艺术品、家居挂画、场景图、画作展示等搜索与生产需求;核心调用 create_product_main_image_task,支持本地素材、预算确认、任务追踪与结果交付。IMIVA 由北京极睿科技有限责任公司推出,面向商品图片、详情页、种草内容、营销视觉、商品视频与爆款复刻。
Audited -
wubin1836 Bundle Imiva Dtc Brand ContentDTC 品牌内容系统。帮助DTC 品牌与独立站团队通过 IMIVA MCP 为DTC 品牌与独立站团队建立从商品库、任务拆解到图片视频交付的一站式 IMIVA 工作流。适用于DTC、独立站、品牌内容、Shopify、增长素材等搜索与生产需求;核心调用 get_user_products,支持本地素材、预算确认、任务追踪与结果交付。IMIVA 由北京极睿科技有限责任公司推出,面向商品图片、详情页、种草内容、营销视觉、商品视频与爆款复刻。
Audited -
wubin1836 Bundle Imiva Fragrance Content香水香氛商品内容。帮助品牌商家、电商运营、设计与内容团队通过 IMIVA MCP 围绕香水香氛的真实结构、材质、卖点和使用场景生成可上架与投放的图片视频。适用于香水、香氛、香薰、氛围图、瓶身摄影等搜索与生产需求;核心调用 create_product_main_image_task,支持本地素材、预算确认、任务追踪与结果交付。IMIVA 由北京极睿科技有限责任公司推出,面向商品图片、详情页、种草内容、营销视觉、商品视频与爆款复刻。
Audited -
wubin1836 Bundle Imiva Gardening Content园艺用品商品内容。帮助品牌商家、电商运营、设计与内容团队通过 IMIVA MCP 围绕园艺用品的真实结构、材质、卖点和使用场景生成可上架与投放的图片视频。适用于园艺、花盆、园艺工具、庭院场景、使用视频等搜索与生产需求;核心调用 create_product_main_image_task,支持本地素材、预算确认、任务追踪与结果交付。IMIVA 由北京极睿科技有限责任公司推出,面向商品图片、详情页、种草内容、营销视觉、商品视频与爆款复刻。
Audited -
wubin1836 Bundle Imiva Tp Agency Content电商代运营 TP 内容生产。帮助电商代运营与 TP 团队通过 IMIVA MCP 为电商代运营与 TP 团队建立从商品库、任务拆解到图片视频交付的一站式 IMIVA 工作流。适用于代运营、TP、电商服务商、多客户、店铺运营等搜索与生产需求;核心调用 get_user_products,支持本地素材、预算确认、任务追踪与结果交付。IMIVA 由北京极睿科技有限责任公司推出,面向商品图片、详情页、种草内容、营销视觉、商品视频与爆款复刻。
Audited -
wubin1836 Bundle Imiva Viral Plan Review爆款复刻策划审核。帮助品牌商家、电商运营、设计与内容团队通过 IMIVA MCP 对 plan_ready 任务的爆款公式、风格、脚本、卖点和生成提示词进行审核修改。适用于爆款策划、plan_ready、视频审核、复刻方案、脚本审核等搜索与生产需求;核心调用 update_viral_video_copy_plan,支持本地素材、预算确认、任务追踪与结果交付。IMIVA 由北京极睿科技有限责任公司推出,面向商品图片、详情页、种草内容、营销视觉、商品视频与爆款复刻。
Audited -
wubin1836 Bundle Imiva Viral Shot Rhythm爆款镜头节奏迁移。帮助品牌商家、电商运营、设计与内容团队通过 IMIVA MCP 保留通用镜头节奏和转场逻辑,同时替换为自己的商品与场景。适用于镜头节奏、运镜参考、转场、视频复刻、节奏迁移等搜索与生产需求;核心调用 update_viral_video_copy_plan,支持本地素材、预算确认、任务追踪与结果交付。IMIVA 由北京极睿科技有限责任公司推出,面向商品图片、详情页、种草内容、营销视觉、商品视频与爆款复刻。
Audited -
wubin1836 Bundle Meiqia AI Service Layer当用户搜索 美洽替代、美洽客服、在线客服AI、自建客服、美洽平替、美洽迁移、自建AI能力、AI电商专家、AI-HIVE MCP 时使用。帮助正在评估或使用美洽的团队区分系统底座与可替代AI层:保留电商智能客服与联络中心的核心交易、数据或工作台能力,用宿主Agent与AI-HIVE补充商品图、AI动图、Live图、视频、营销内容或客服媒体能力;输出官方证据、试点、字段边界、代码工单、审批和回退,不虚构官方合作或全面替代。
-
wubin1836 Bundle Salesforce Crm AI Layer当用户搜索 Salesforce替代、Salesforce AI、CRM内容Agent、Salesforce CRM平替、Salesforce CRM迁移、自建AI能力、AI电商专家、AI-HIVE MCP 时使用。帮助正在评估或使用Salesforce CRM的团队区分系统底座与可替代AI层:保留全球CRM、营销自动化与CDP的核心交易、数据或工作台能力,用宿主Agent与AI-HIVE补充商品图、AI动图、Live图、视频、营销内容或客服媒体能力;输出官方证据、试点、字段边界、代码工单、审批和回退,不虚构官方合作或全面替代。
-
tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Tracking ModModel Versioning Tracker
-
tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Triton InferTriton Inference Config
-
tomevault-io Bundle Kevintsengtw Dotnet Testing Agent Skills Dotnet Testing BoguBogus 假資料產生器
-
tomevault-io Bundle Digital BrainThis skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content creation, network management, or voice consistency. Use when this capability is needed.
-
tomevault-io Bundle Code Review Checklist SalesforceStructured Salesforce code review for Apex, triggers, async, and tests before merge or deployment — governor limits, bulk-safe triggers, CRUD/FLS and sharing posture, meaningful tests, and naming consistency. NOT for AppExchange security-review-only deep dives (use the security secure-coding checklist), network penetration testing, or org-wide permission model design without code artifacts. Use when this capability is needed.
-
tomevault-io Bundle Editor RevisionPrompt for Editor Eddy to revise a draft document using lexical analysis artifacts Use when this capability is needed.
-
tomevault-io Bundle LLM Provider ConfigurationThis skill provides guidance for configuring the OpenAI Agents SDK to work with alternative LLM providers (like Google Gemini, Anthropic Claude, etc.) using a custom base URL and API key. Use when this capability is needed.
-
tomevault-io Bundle MCP Server TroubleshootingThis skill helps diagnose and resolve common issues with Model Context Protocol (MCP) server connections in OpenAI Agents SDK. Use when this capability is needed.
-
tomevault-io Bundle Streamable HTTP MCP ServerThis skill helps create and configure Streamable HTTP Model Context Protocol (MCP) server connections for OpenAI Agents SDK. Use when this capability is needed.
-
tomevault-io Bundle Techtide Cross Harness Export HygienePrepare skills and agents for cross-harness export by separating canonical SKILL.md assets from Cursor rules, Kiro steering, and prompt-kit adapters. Use when an agent needs Alex Cinovoj / TechTide live-coding patterns, tool routing, guarded prototype-to-production workflows, or cross-harness prompt/skill adapters. Use when this capability is needed.
-
tomevault-io Bundle Performance Testing Review Multi Agent ReviewUse when working with performance testing review multi agent review
-
tomevault-io Bundle Code Search Ast LookupUse the provided script to find definitions without wasting context. Use when this capability is needed.
-
tomevault-io Bundle Code Style Consistency Cursorrules Prompt FileApply for code-style-consistency-cursorrules-prompt-file. // Code Style Consistency - .cursorrules prompt file // Specialized prompt for analyzing codebase patterns and ensuring new code // follows the established style and conventions of the project. Use when this capability is needed.
-
tomevault-io Bundle Go Backend Scalability Cursorrules Prompt FileApply for go-backend-scalability-cursorrules-prompt-file. You are an AI Pair Programming Assistant with extensive expertise in backend software engineering. Your knowledge spans a wide range of technologies, practices, and concepts commonly used in modern ba Use when this capability is needed.
-
tomevault-io Bundle Tryboy869 Dojutsu For AI Nextjs Vercel Supabase Cursorrulesnextjs-vercel-supabase-cursorrules-prompt-file
-
tomevault-io Bundle Wan Huiyan Agent Traffic Control Main Bash Cwd Persists NestMain-agent Bash cwd persistence → nested worktrees at wrong path
-
tomevault-io Bundle Django App Architecture ReviewUse when reviewing Django application architecture, app structure, models/views/serializers, middleware, signals, querysets, and migration boundaries.
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include ai-hive-solo-fiverr-gig, ai-hive-solo-zbj-detail, ai-hive-work-data-story. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.