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.
-
majiayu000 Bundle Mot 2System health check (MOT) for skills, agents, hooks, and memory
567 - majiayu000 Bundle Cloudflare Browser Rendering 3
Guide for implementing Cloudflare Browser Rendering - a headless browser automation API for screenshots, PDFs, web scraping, and testing. Use when automating browsers, taking screenshots, generating PDFs, scraping dynamic content, extracting structured data, or testing web applications. Supports REST API, Workers Bindings (Puppeteer/Playwright), MCP servers, and AI-powered automation. (project)
567 - majiayu000 Bundle Ctdna Dynamics Mrd Agent 2
AI-powered circulating tumor DNA dynamics analysis for molecular residual disease detection, treatment response monitoring, and early relapse prediction using liquid biopsy.
567 - majiayu000 Bundle Diagnosing Energy Models 2
Use this skill when troubleshooting OpenStudio or EnergyPlus energy models that fail to simulate, have geometry errors (intersecting surfaces, non-planar surfaces, story organization issues), need HVAC validation against Engineer of Record specifications, require LEED Appendix G baseline generation, or need systematic diagnostics for complex commercial building models. Handles model triage, geometry rebuild decisions, EOR specification mapping, and quality assurance for LEED compliance.
567 - majiayu000 Bundle Google Gemini Embeddings 4
Build RAG systems, semantic search, and document clustering with Gemini embeddings API (gemini-embedding-001). Generate 768-3072 dimension embeddings for vector search, integrate with Cloudflare Vectorize, and use 8 task types (RETRIEVAL_QUERY, RETRIEVAL_DOCUMENT, SEMANTIC_SIMILARITY) for optimized retrieval. Use when: implementing vector search with Google embeddings, building retrieval-augmented generation systems, creating semantic search features, clustering documents by meaning, integrating embeddings with Cloudflare Vectorize, optimizing dimension sizes (128-3072), or troubleshooting dimension mismatch errors, incorrect task type selections, rate limit issues (100 RPM free tier), vector normalization mistakes, or text truncation errors (2,048 token limit).
567 - majiayu000 Bundle Builder Skill 7
Skill creation specialist. Use PROACTIVELY for creating skills, YAML frontmatter design, and knowledge organization. MUST INVOKE when ANY of these keywords appear in user request: --ultrathink flag: Activate Sequential Thinking MCP for deep analysis of skill design, knowledge organization, and YAML frontmatter structure. EN: create skill, new skill, skill optimization, knowledge domain, YAML frontmatter KO: 스킬생성, 새스킬, 스킬최적화, 지식도메인, YAML프론트매터 JA: スキル作成, 新スキル, スキル最適化, 知識ドメイン, YAMLフロントマター ZH: 创建技能, 新技能, 技能优化, 知识领域, YAML前置信息
567 - majiayu000 Bundle Template Skill 6
A template for creating new AceDataCloud Agent Skills. Copy this directory and customize.
567 - majiayu000 Bundle Playwright Network Analyzer 2
Monitors and analyzes network traffic during browser automation workflows using Playwright MCP tools. Use when investigating API behavior, debugging failed requests, performance analysis, or checking network activity during user flows. Triggers on "analyze network requests", "check API calls", "monitor network traffic", "debug API errors", or "performance analysis". Works with Playwright browser automation (browser_navigate, browser_network_requests, browser_click, browser_fill_form).
567 - majiayu000 Bundle Tdd 42
Test-driven development workflow with philosophy guide - plan → write tests → implement → validate
567 - majiayu000 Bundle Autonomous Skill 5
Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Codex non-interactive mode with auto-continuation. Trigger phrases include autonomous, long-running task, multi-session, 自主执行, 长时任务, autonomous skill.
567 - majiayu000 Bundle Research Agent 7
Research agent for external documentation, best practices, and library APIs via MCP tools
567 - majiayu000 Bundle Verify Prompt 2
Validate distilled prompts preserve essential instructions
567 - majiayu000 Bundle Checkpoint Resume Long Job 2
Persist progress for long-running jobs (batched LLM calls, large ingestions, multi-hour syncs) so that a context reset, crash, or interrupt doesn't lose work. Use whenever a job iterates over N items and completing item K matters independently. Provides a resumable.mjs library pattern plus the skill's invocation heuristics.
567 - majiayu000 Bundle Command Placement Priority 2
コマンドの配置場所と優先順位（プロジェクト/ユーザー/MCP、名前空間、競合解決）を整理し、配置判断と移行方針を支援するスキル。 配置基準、優先順位ルール、移行フローを一貫して整理する。 Anchors: • The Pragmatic Programmer (Andrew Hunt, David Thomas) / 適用: 配置判断の実務 / 目的: 運用の一貫性確保 • Priority Resolution Protocol / 適用: 同名競合の解決 / 目的: 優先順位の明確化 Trigger: Use when determining command placement, resolving command priority conflicts, or migrating commands between project/user/MCP layers. command placement, priority resolution, namespace design, project vs user commands, MCP integration
567 - majiayu000 Bundle Openai Docs 6
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.
567 - majiayu000 Bundle Discover Ml 2
Automatically discover machine learning and AI skills when working with machine learning, PyTorch, training, inference, RAG, embeddings, fine-tuning, LLM, DSPy, HuggingFace, or diffusion models. Activates for ML development tasks.
567 - majiayu000 Bundle Local Finetune 2
local-finetune
567 - majiayu000 Bundle 033 Architecture Diagrams 3
Use when you need to generate Java project diagrams — including UML sequence diagrams, UML class diagrams, C4 model diagrams, UML state machine diagrams, and ER (Entity Relationship) diagrams — through a modular, step-based interactive process that adapts to your specific visualization needs. This should trigger for requests such as Generate UML diagram; Create sequence diagram; Create class diagram; Create state machine diagram; Create C4 diagram. Part of cursor-rules-java project
567 - majiayu000 Bundle Cellular Senescence Agent 2
AI-powered analysis of cellular senescence for aging research, cancer therapy response, and senolytic drug development.
567 - majiayu000 Bundle Codex Agent Collaboration 2
Execute tasks using Codex AI agent for code analysis, implementation, and collaboration
567 - majiayu000 Bundle Pdx Model Analysis Agent 2
AI-powered analysis of patient-derived xenograft (PDX) models for drug response prediction, translational research, and personalized treatment selection.
567 - majiayu000 Bundle Doc Verify 2
Verify documentation accuracy against code reality and external claims — runs as a fresh agent after /doc-rigor to prevent confirmation bias
567 - majiayu000 Bundle Next 8
Pick the next bead to work on. Shows ready tasks (no blockers), applies user preferences for ordering (priority, type, recency), and helps select work.
567 - majiayu000 Bundle Testing Agent 3
Run goal-based evaluation tests for agents. Use when you need to verify an agent meets its goals, debug failing tests, or iterate on agent improvements based on test results.
567 - majiayu000 Bundle Add Opencode 2
Use OpenCode as an agent provider (AGENT_PROVIDER=opencode). OpenRouter, OpenAI, Google, DeepSeek, etc. via OpenCode config — not the Anthropic Agent SDK. Per-session and per-group via agent_provider; host passes OPENCODE_* and XDG mount when spawning containers.
567 - majiayu000 Bundle Fan Out 3
Parallel agent orchestration for OST exploration. Fan-out multiple solution explorations, fan-in results to compare and select winners.
567 - majiayu000 Bundle Jat Start 2
Begin working on a JAT task. Registers agent identity, selects a task, searches memory, detects conflicts, reserves files, emits IDE signals, and starts work. Use this at the beginning of every JAT session.
567 - majiayu000 Bundle LLM Safety Patterns 2
Use when securing LLM integrations against prompt injection, hallucination, or data leakage. Implements context separation, input validation, and output filtering patterns.
567 - majiayu000 Bundle Distill Prompt 2
Create lean, token-efficient versions of prompts
567 - majiayu000 Bundle Extract Prompt 2
Turn successful interactions into reusable prompts
567 - majiayu000 Bundle Langflow 3
A powerful Python-based visual framework for building and deploying AI-powered agents and workflows with Model Context Protocol (MCP) integration, drag-and-drop interface, and enterprise-grade deployment options
567 - majiayu000 Bundle Langfuse 2
Debug AI traces, find exceptions, analyze sessions, and manage prompts via Langfuse MCP. Use when debugging AI pipelines, investigating errors, analyzing latency, managing prompt versions, or setting up Langfuse. Triggers on "langfuse", "traces", "debug AI", "find exceptions", "what went wrong", "why is it slow", "datasets", "evaluation sets".
567 - majiayu000 Bundle Langgraph Agents 2
Multi-agent systems with LangGraph - supervisor/swarm patterns, state coordination, multi-provider routing. Use when: build LangGraph agent, multi-agent workflow, supervisor pattern, agent orchestration, StateGraph, coordinate multiple agents, agentic workflow. Uses Claude, DeepSeek, Gemini (no OpenAI).
567 - majiayu000 Bundle Ln 840 Benchmark Compare 2
Use when benchmarking hex-line MCP against Claude built-in tools with scenario manifests, activation checks, and diff-based correctness.
567 - majiayu000 Bundle Assumption Test 3
Design the smallest viable test to validate or invalidate a critical assumption. Based on Torres's assumption testing framework, organized by Gilad's AFTER model (Assessment → Fact-Finding → Tests → Experiments → Release Results).
567 - majiayu000 Bundle Pend 2
View latest reply from AI provider (gemini/codex/opencode/droid/claude).
567
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 mot, cloudflare-browser-rendering, ctdna-dynamics-mrd-agent. 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.