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.
-
tools-only Bundle 627 Library And RAG 6ebbccebResearch Library & RAG Guide
7 - tools-only Bundle 1748 Deployment Modes 08c03d66
MCP Gateway Deployment Modes
7 - tools-only Bundle 2033 Readme MCP Tools 031f87ef
MCP Tool Integration
7 - tools-only Bundle 2441 Security Auditor 1a0a4929
Use this agent for deep security-focused code review: OWASP vulnerabilities, hardcoded secrets, injection flaws, insecure patterns, and dependency lock-file analysis.
7 - tools-only Bundle 2441 Security Auditor 20e17ae9
Use this agent for deep security-focused code review: OWASP vulnerabilities, hardcoded secrets, injection flaws, insecure patterns, and dependency lock-file analysis.
7 - tools-only Bundle 2460 Agent Sdk Python 6152fc1a
Installation
7 - tools-only Bundle 1152 Worker 2d020372
Focused implementation agent. Executes ONE specific task completely. Does not decide what to build - implements what it's told.
7 - tools-only Bundle 1121 Validator 10fea6de
Quality assurance agent. Runs tests, linters, type checks. Reports pass/fail with specific errors. Does not fix issues.
7 - tools-only Bundle 1284 MCP Tools 51e3f2ec
Connect CLI Reference
7 - tools-only Bundle 1284 MCP Tools 86b6280f
Model Context Protocol (MCP) Tools
7 - tools-only Bundle 1284 MCP Tools 906f3e39
MCP Tools — Prefer Over Manual Alternatives
7 - tools-only Bundle 2849 LLM Setup 0e48d404
LLM Setup
7 - tools-only Bundle 1138 Vuln Review 0884fa25
MCP漏洞报告专业审查专家
7 - tools-only Bundle 677 PDF MCP Tool 48095ee6
PDF Scraping MCP Tool (Task B1.7)
7 - tools-only Bundle 2476 AI Agent Summary 737a2f10
AI Agent Composability - Quick Summary
7 - tools-only Bundle 2498 Alpaca MCP Setup Fdfb5774
Alpaca MCP Server Setup Guide
7 - tools-only Bundle 2526 AI Agent Summary Eb15178c
AI Agent Composability - Quick Summary
7 - tools-only Bundle 2508 PDF Multimodal RAG 4bfa3c61
Multi-vector RAG: Building Multimodal Document Search Systems With Weaviate
7 - tools-only Bundle 2563 X Popular Papers F6579aef
Popular Papers on RAG & AI Agents (Computer Science)
7 - tools-only Bundle 2585 Evaluation Guide 8b06b6e9
MCP Server Evaluation Guide
7 - tools-only Bundle 2691 Hn 1 Claude Code 475e9314
Research Results: Claude Code skills and MCP servers
7 - tools-only Bundle 537 02 Core Directory 3b15c9d0
Agent orchestration, state management, and prompting system
7 - tools-only Bundle 659 Description Skill 01b2e4d1
Scientific delegation framework for orchestrators coordinating sub-agents. Provides WHERE-WHAT-WHY context patterns while preserving agent autonomy. Use when delegating tasks, structuring sub-agent prompts, planning multi-agent workflows, or coordinating specialist agents.
7 - tools-only Bundle 659 Description Skill 02846f3c
Scientific delegation framework for orchestrators coordinating sub-agents. Provides WHERE-WHAT-WHY context patterns while preserving agent autonomy. Use when delegating tasks, structuring sub-agent prompts, planning multi-agent workflows, or coordinating specialist agents.
7 - tools-only Bundle 659 Description Skill 0a0bb338
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
7 - tools-only Bundle 659 Description Skill 0bf827f7
Scientific delegation framework for orchestrators coordinating sub-agents. Provides WHERE-WHAT-WHY context patterns while preserving agent autonomy. Use when delegating tasks, structuring sub-agent prompts, planning multi-agent workflows, or coordinating specialist agents.
7 - tools-only Bundle 659 Description Skill 1dae8dde
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
7 - tools-only Bundle 659 Description Skill 3474a51c
Create high-quality Claude Code agents from scratch or by adapting existing agents as templates. Use when the user wants to create a new agent, modify agent configurations, build specialized subagents, or design agent architectures. Guides through requirements gathering, template selection, and agent file generation following January 2026 Anthropic best practices.
7 - tools-only Bundle 659 Description Skill 859b3fbb
Integrate patterns from external sources (URLs or files) into local skills, agents, and plugins. Triggers on comparing external agent definitions against local equivalents, extracting best practices from frameworks like GSD or BMAD-METHOD, enhancing local skills with external patterns, or ensuring interoperability with external tool ecosystems.
7 - tools-only Bundle 659 Description Skill A46211ee
Create high-quality Claude Code agents from scratch or by adapting existing agents as templates. Use when the user wants to create a new agent, modify agent configurations, build specialized subagents, or design agent architectures. Guides through requirements gathering, template selection, and agent file generation following January 2026 Anthropic best practices.
7 - tools-only Bundle 659 Description Skill A62eb497
Create high-quality Claude Code agents from scratch or by adapting existing agents as templates. Use when the user wants to create a new agent, modify agent configurations, build specialized subagents, or design agent architectures. Guides through requirements gathering, template selection, and agent file generation following January 2026 Anthropic best practices.
7 - tools-only Bundle 659 Description Skill Ad1e8a07
Scientific delegation framework for orchestrators — provide observations and success criteria while preserving agent autonomy. Use when assigning work to sub-agents, before invoking the Task tool, or when preparing delegation prompts for specialist agents.
7 - tools-only Bundle 659 Description Skill B651fba2
Create high-quality Claude Code agents from scratch or by adapting existing agents as templates. Use when the user wants to create a new agent, modify agent configurations, build specialized subagents, or design agent architectures. Guides through requirements gathering, template selection, and agent file generation following January 2026 Anthropic best practices.
7 - tools-only Bundle 519 Librarian B1b4898d
Smart file reading agent. Reads files intelligently, summarizes large content, extracts relevant sections. Git analysis (diffs, changelogs, detailed commits). Protects main context from raw file dumps.
7 - tools-only Bundle 913 Resources C32f64a7
MCP Resources Reference
7 - tools-only Bundle 1284 MCP Tools 03c87257
MCP & Tool Calling
7
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 627-library-and-rag_6ebbcceb, 1748-deployment-modes_08c03d66, 2033-readme_mcp_tools_031f87ef. 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.