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 Skill Clean CodeTiêu chuẩn lập trình thực dụng: mã nguồn ngắn gọn, tường minh, không over-engineering.
- tuyenht Skill Cloudflare
Chuyên gia nền tảng Cloudflare: Workers, Pages, cấu trúc lưu trữ và phân phối.
- tuyenht Bundle App Builder
Điều phối viên kiến trúc tổng thể. Khởi tạo và liên kết dự án Full-stack.
- tuyenht Skill Go Patterns
Các mẫu thiết kế Go: concurrency, interfaces, error handling và clean architecture.
- tuyenht Skill MCP Builder
Nguyên lý xây dựng MCP Server, cấu trúc tài nguyên và quản lý tool kết nối.
-
caphtech Skill AI Readability AnalysisコードのAI可読性を分析し、生成AIがバグ修正や変更を行う際に苦戦する原因となる問題を特定するスキル。以下の場合に使用する：(1)「AIが修正しやすいコードか分析して」「AI可読性を診断して」と依頼された時 (2) バグ修正や変更作業が難航している原因を調査したい時 (3) コードベースのAIフレンドリー度を評価したい時 (4) リファクタリング優先度を決めたい時。分析観点：コンテキストウィンドウ問題、命名・表現問題、構造・設計問題、テスト・検証問題、ドキュメント問題、LLM特有の苦手パターン
-
duncan-buildroom Bundle Fable GoalConvert a rambling description of a desired outcome into a polished, autonomous /goal prompt for Fable. Use whenever the user says /fable-goal, "turn this into a goal prompt", "write me a fable prompt", "I want fable to build X, write the prompt", or rambles about something they want made and asks for the prompt that makes it. The output is a single copy-paste prompt, not the build itself. Do NOT use when the user wants the thing built right now in this session; only when they want the PROMPT that will make it happen in a fresh session.
- duncan-buildroom Bundle Prompt Fixer
Paste the prompt that gave you bad output and get back the reason it failed plus the rewritten prompt to run instead. Checks the seven usual causes — too vague, three asks in one, no constraints, no format, no done-when, missing context, asking for code instead of an outcome — and hands you a fixed version. Use when the user says "this isn't what I wanted", "Claude gave me garbage", "my prompt didn't work", "fix my prompt", "why did it do that", "it ignored what I asked", "it keeps giving me the wrong thing", "rewrite this prompt", or "/prompt-fixer".
- duncan-buildroom Bundle Brief Builder
Turns a vague ask into a surgical 5-Part Brief you can paste straight into Claude and get the right thing back on the first try. Fills in CONTEXT, GOAL, CONSTRAINTS, FORMAT, and DONE-WHEN, then gives you a one-sentence compressed version for quick asks. Use when the user says "write me a prompt", "how do I ask for this", "turn this into a prompt", "make my prompt better", "I don't know how to describe what I want", "help me explain this to Claude", "brief for", "what should I type", or "/brief-builder". Also use before any real build, so they ask properly the first time.
-
fr-e-d Skill Memory SearchSearch memory by frontmatter fields, full-text keywords, or cross-reference graph. Returns ranked file list — never loads full content. Use when the agent needs to find relevant memory without knowing exact paths.
- tuyenht Bundle Architecture
Khung quyết định kiến trúc phần mềm, phân tích yêu cầu và đánh giá trade-off.
- tuyenht Skill Plan Writing
Kỹ năng lập kế hoạch công việc chuẩn xác, chia nhỏ tác vụ và nghiệm thu.
- tuyenht Bundle Tdd Workflow
Quy trình phát triển phần mềm kiểm thử dẫn động (Test-Driven Development thực chiến lõi).
- tuyenht Bundle Velzon Admin Dashboard
Kiến trúc xây dựng Admin Dashboard hoàn cấp theo tiêu chuẩn Velzon chuyên nghiệp nhất.
- duncan-buildroom Bundle Content Prompt
Generate a single thought-provoking question for the user to answer on camera as short-form content (TikTok, Reels, YouTube Shorts, or any off-the-cuff video), plus 5 hook options and text overlays. Use whenever the user asks for "content ideas", "what should I talk about", "give me a question to answer", "prompt me", "short-form ideas", "what's trending I can speak to", "I need content inspiration", or says /content-prompt. Always trigger when the user wants something to riff on for a quick video — even a casual "give me something to talk about" or "what should my next video be about".
-
hk-vk Bundle LlmstxtA proposal that those interested in providing LLM-friendly content add a /llms.txt file to their site. This is a markdown file that provides brief background information and guidance, along with links to markdown files providing more detailed information.
- hk-vk Bundle Mantine
Mantine UI - LLM Documentation documentation and resources. Use this skill when working with Mantine UI - LLM Documentation or when the user mentions mantine ui - llm documentation.
- fr-e-d Skill Compose Team
Assemble the context bundles for each sub-agent based on evaluate-story output. Produces spawn-ready packages for Planning, Implementation, QA, or MicroDelivery sub-agents. Activate after evaluate-story, before spawning any sub-agent.
- fr-e-d Skill Memory Index Lint
Validate discoverability invariants of memory `index.md` and `archive/superseded-decisions.archive.md`. Tool-agnostic L3 prompt + capability-dependent L4 script. Detects table corruption, dangling/orphan supersession pointers, frontmatter inconsistencies, missing affordance signals.
- fr-e-d Skill Build Agents Index
Scan all agent and sub-agent definition files in .gaai/core/agents/, extract YAML frontmatter, merge with specialists.registry.yaml, and generate a derived agents-index.yaml at .gaai/core/agents/agents-index.yaml. Activate after adding, modifying, or removing any agent, sub-agent, or specialist entry.
-
nilecui Bundle Nano BananaGenerate and edit high-quality AI images using Google's Gemini 3 Pro Image model (Nano Banana Pro) via MCP. Use when user wants to create images, edit photos, generate graphics, or needs visual content with text rendering.
- nilecui Skill Architecture Diagrams
Create system architecture diagrams using Mermaid, PlantUML, C4 model, flowcharts, and sequence diagrams. Use when documenting architecture, system design, data flows, or technical workflows.
- tuyenht Skill AI Sdk Expert
Chuyên gia xử lý Vercel AI SDK v5, streaming, tool calling, prompt engineering.
- tuyenht Bundle Brainstorming
Giao thức đặt câu hỏi Socratic, khơi gợi và làm rõ yêu cầu nghiệp vụ.
- tuyenht Bundle Mobile Design
Tư duy thiết kế ưu tiên Mobile-first (iOS/Android), tối ưu hiệu năng và chạm.
- tuyenht Skill Nestjs Expert
Chuyên gia framework NestJS: Dependency Injection, Microservices, Security và TypeORM chuyên dụng.
- tuyenht Skill Prisma Expert
Chuyên gia Prisma ORM: thiết kế schema, truy vấn phức tạp và tối ưu database dữ.
- tuyenht Skill Rust Patterns
Các mẫu thiết kế Rust: ownership, lifetimes, async, error handling và performance optimization.
- tuyenht Bundle Webapp Testing
Kiểm thử tự động Web App End-to-End nâng cao bằng framework Playwright chuyên nghiệp cực.
- fr-e-d Skill Project Surface Scan
Scan project root for file tree, dominant languages, and LOC estimate. Produces structured baseline context for Stage 2 LLM synthesis during bootstrap. Respects .gitignore and standard exclusions. Outputs per-directory file counts, ranked language list, size class, and observability summary.
- fr-e-d Skill Coordinate Handoffs
Validate sub-agent handoff artefacts, sequence phase transitions, and manage retry and escalation logic. Activate after each sub-agent terminates to determine next action.
- tuyenht Bundle Database Design
Nguyên tắc thiết kế cơ sở dữ liệu, chiến lược đánh chỉ mục và lựa chọn ORM.
- tuyenht Skill Parallel Agents
Điều phối và chạy song song nhiều mô hình AI agents độc lập cho tác vụ khó.
- tuyenht Skill Python Patterns
Kiến trúc lõi Python: async, type hints, web scraping và phân tích dữ liệu AI nền.
- tuyenht Skill Testing Mastery
Đỉnh cao kiểm thử tổng hợp: TDD, Contract, Web App End-to-End và Mocking toàn diện ảo.
- tuyenht Skill Behavioral Modes
Quản lý và chuyển đổi các chế độ hoạt động thông minh của AI Agent.
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 fable-goal, prompt-fixer, brief-builder. 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.