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.
-
tuyenht Bundle Contract TestingKiến trúc kiểm thử hợp đồng API (Contract Testing) chuyên sâu cho hệ thống Microservices.
- tuyenht Bundle Game Development
Điều phối dự án phát triển game, định tuyến tới các nền tảng thiết kế phù hợp.
- tuyenht Bundle GRAPHQL Patterns
Các mẫu thiết kế GraphQL API toàn diện, cấu trúc schema và best practices.
- tuyenht Skill Red Team Tactics
Chiến thuật tấn công Red Team (MITRE ATT&CK), mô phỏng đe dọa và phòng thủ.
- tuyenht Skill State Management
Mô hình quản lý trạng thái luồng dữ liệu (Redux, Zustand, Pinia) hiệu quả bền.
- tuyenht Bundle Testing Patterns
Nguyên tắc và quy chuẩn kiểm thử phần mềm nền tảng (Unit, Integration, E2E).
- tuyenht Skill Vector Databases
Cấu trúc cơ sở dữ liệu Vector, truy vấn ngữ nghĩa AI và mô hình tối ưu truy RAG.
- tuyenht Bundle I18N Localization
Giải pháp ứng dụng đa ngôn ngữ (i18n), quản lý bản dịch và hỗ trợ đa quốc.
- tuyenht Bundle Lint And Validate
Quy trình kiểm soát chất lượng tự động, linting và phân tích mã lỗi tĩnh.
-
kunhai-88 Skill MCP Builder创建高质量 MCP（Model Context Protocol）服务器的指南，使 LLM 通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用，无论是 Python（FastMCP）还是 Node/TypeScript（MCP SDK）。
- kunhai-88 Bundle Agent Browser
浏览器自动化工具，用于网页导航、交互、截图、录制等。当需要自动化浏览器操作、测试网页、抓取网页内容、填写表单、截图、录制视频，或提到「浏览器自动化」「网页测试」「agent-browser」「浏览器操作」时使用。
-
hk-vk Bundle Reflex DocumentationReflex is a Python framework for building full-stack web apps. Use this index to find agent-readable Markdown docs, or see [llms-full.txt](https://reflex.dev/docs/llms-full.txt) for the complete docs in one file.
- hk-vk Bundle Tsrx Aillm Documentation
TSRX - AI/LLM Documentation documentation and resources. Use this skill when working with TSRX - AI/LLM Documentation or when the user mentions tsrx - ai/llm documentation.
- hk-vk Skill Txtskills Llms To Agent Skills
Convert docs base URLs, llms.txt, or llms-full.txt into installable Agent Skills with txtskills CLI. Use when a user asks to generate, publish, and optionally install a new skill from documentation.
-
fr-e-d Skill Gaai Oss BootstrapInitialize or refresh a project's GAAI OSS memory by activating the Bootstrap Agent and context-bootstrap workflow.
- fr-e-d Skill Delivery High Level Plan
Transform validated Stories into a clear, minimal, governed execution plan. Used by the Planning Sub-Agent as the first planning pass before prepare-execution-plan for Tier 2/3, or as the sole planning output for simple Stories.
-
89jobrien Bundle Mlx Fine TuningSpecialized skill for MLX-based LLM fine-tuning on Apple Silicon. This skill should be used when working with LoRA fine-tuning, model conversion from HuggingFace to MLX format, adapter management, hyperparameter tuning, memory optimization, and benchmarking on M1/M2/M3/M4 chips.
- tuyenht Skill Typescript Expert
Chuyên gia TypeScript lõi: Type gymnastics, thiết kế Generic và tối ưu biên chế dịch.
- tuyenht Bundle Context Hub Bridge
Truy xuất tài liệu API bên ngoài qua Context Hub (chub CLI/MCP). Định tuyến giữa external docs và internal knowledge.
- tuyenht Skill Powershell Windows
Viết kịch bản tự động hóa PowerShell chuyên sâu và quản trị hệ điều hành Windows.
- tuyenht Bundle Laravel Performance
Tối ưu hóa hiệu suất Laravel toàn diện theo chuẩn doanh nghiệp lớn (Enterprise).
- tuyenht Skill Architecture Mastery
Đỉnh cao kiến trúc tổng hợp: API, Microservices, GraphQL và Design Patterns cốt lõi.
- tuyenht Skill Systematic Debugging
Khung phương pháp gỡ lỗi có hệ thống, truy xuất nguyên nhân gốc rễ vòng lặp chéo.
- tuyenht Bundle Templates
Project scaffolding templates for new applications. Use when creating new projects from scratch. Contains 12 templates for various tech stacks.
- tuyenht Skill Code Review Checklist
Tiêu chuẩn đánh giá mã nguồn, rà soát bảo mật và thực hành lập trình tốt.
- tuyenht Skill Deployment Procedures
Cẩm nang quy trình triển khai production an toàn, quản lý rủi ro và rollback.
-
meaningfy-ws Skill GuardrailsApply agentic guardrails to every step where an LLM agent acts — decision bounds, output validation, and prompt-injection defence. Use to make an agent step safe before it runs tools, writes files, or trusts external content. Guardrails validate agent BEHAVIOUR (is this action in bounds, is this output well-formed, is this input trustworthy); clarity-gate/tests/review validate CONTENT. Trigger on "add guardrails", "is this agent step safe", "bound this agent's decisions", "validate this agent output", "defend against prompt injection", "what can this agent be allowed to do". Each guardrail points to a concrete enforcement home.
-
treasure-data Skill Foundry AgentBuild Treasure AI Foundry agents using `tdx agent pull/push` with YAML/Markdown config. Covers agent.yml structure, tools (knowledge_base, agent, web_search, image_gen), @ref syntax, and knowledge bases. Use for TD AI Foundry agent development workflow.
-
forgivesam168 Skill DebugSystematic debugging methodology for build failures, test failures, unexpected agent behavior, and drift-related errors. Use when a build fails, tests fail unexpectedly, an agent produces wrong output repeatedly, or sync drift is detected. Triggers on: "debug", "fix build", "tests failing", "unexpected behavior", "drift error", "can't reproduce", "something is broken", "why is this failing", "investigate the failure". Escalates to human after 2 consecutive failed debug cycles.
- forgivesam168 Bundle Agentic Eval
Adversarial evaluation patterns for any output or decision where you want a devil's advocate challenge before committing. Use when: you want to challenge a decision, get an adversarial second opinion, implement self-critique loops, apply rubric-based scoring, run evaluator-optimizer pipelines, judge-and-refine cycles, verify a downstream agent can consume an upstream artifact, or check inter-stage artifact consistency. Triggers on "devil's advocate", "challenge this decision", "挑戰這個決策", "扮演反對者", "adversarial review", "self-critique", "質疑這個方案". Do NOT use for standard code review (use code-security-review skill), general refactoring (use refactor skill), or security audits.
- tuyenht Skill Nodejs Best Practices
Kiến trúc hệ thống Node.js, quản lý tác vụ bất đồng bộ và tối ưu hiệu suất.
- tuyenht Bundle Performance Profiling
Phương pháp đo lường, cấu hình và tinh chỉnh hiệu suất cơ sở hệ thống chuyên sâu.
- tuyenht Bundle Vulnerability Scanner
Chiến lược dò quét và khắc phục lỗ hổng an toàn thông tin theo chuẩn OWASP chuyên sâu.
- tuyenht Skill Documentation Templates
Khuôn mẫu tài liệu chuẩn hóa: README, API docs và hướng dẫn thân thiện AI.
- tuyenht Skill Monitoring Observability
Thiết kế hệ thống giám sát production, logging, metrics và quan sát (Observability).
- treasure-data Bundle Google Slides
Use this skill any time the user wants to create a Google Slides deck from a template, mentions "Google Slides" with a template in mind, provides a Google Slides URL plus a content brief, or asks to "make slides", "build a deck", "generate a presentation", or "fill this template" in a Google Workspace context. Requires the Studio Google Slides + Google Drive MCP connectors. Do NOT use for PowerPoint (.pptx) creation (use the pptx skill), for editing without a template, or for authoring a new template (template authoring has its own skill).
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 mlx-fine-tuning, reflex-documentation, tsrx-aillm-documentation. 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.