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 556 MCP Integration 29e711f3MCP Integration
7 - tools-only Bundle 729 Prompt Patterns De74e547
Prompt Patterns
7 - tools-only Bundle 730 Prompting Guide 86c21f98
Prompt‑Driven Development Prompting Guide
7 - tools-only Bundle 943 Sealos Use Case C8ba4170
🛡️ Context-Aware Support Agent (Sealos Edition)
7 - tools-only Bundle 251 Agent Guide 00619144
Agent Implementation Guide
7 - tools-only Bundle 2529 Release Protocol B1b92a4f
Pre-release checklist for Nucleus MCP Server
7 - tools-only Bundle 659 Description Skill 12b697de
Orchestrator context window discipline enforcement. Prevents the orchestrator from reading source files it will not edit, running diagnostic commands that waste context, and rationalizing delegation bypasses. Use when setting up orchestrator guardrails, reviewing delegation discipline, or diagnosing context window waste in multi-agent workflows. Activates PreToolUse hooks that surface decision points before source file reads and diagnostic command execution.
7 - tools-only Bundle 659 Description Skill 1e1d4f01
Assess a plugin and create refactoring task files for parallel agent execution. Use when you need to analyze a plugin structure, score its quality, and generate a phased refactoring plan with design map and implementation tasks.
7 - tools-only Bundle 659 Description Skill 23a7763d
Global contract for all specialist subagents. Enforces role boundaries, scope discipline, and DONE/BLOCKED status signaling. Load this skill in any agent that should operate as a bounded specialist following supervisor delegation patterns.
7 - tools-only Bundle 659 Description Skill 2fa92b3a
Explain how and when to use Chain of Verification (CoVe) in prompt design. Use when designing prompts that require factual accuracy, self checking, or reduction of hallucinations.
7 - tools-only Bundle 659 Description Skill 5e1cc879
Assess a plugin and create refactoring task files for parallel agent execution
7 - tools-only Bundle 659 Description Skill 69f1d260
Assess a plugin and create refactoring task files for parallel agent execution
7 - tools-only Bundle 659 Description Skill E76b1d9e
Execute refactoring tasks from a task file with parallel agent orchestration
7 - tools-only Bundle 2583 AI Agent Developer D4385262
AI/Agent Systems Developer Persona
7 - tools-only Bundle 655 Write To Skill File 4ed508c4
Text to LLM Optimized Text workflow instructions
7 - tools-only Bundle 1753 Instructions 3a431a0e
Web Search MCP Server
7 - tools-only Bundle 191 Configuration 701830f6
Configure mcpbr with YAML files to define MCP server settings, benchmark selection, model parameters, and evaluation options.
7 - tools-only Bundle 2477 Data Model Reference F7c247c5
<!-- Parent: sf-ai-agentforce-observability/SKILL.md -->
7 - tools-only Bundle 2478 Backend Requirements 4ae9bbe4
Backend Requirements — How to Make Your AI Agent Compatible with EvalView
7 - tools-only Bundle 2486 Code Review Overview 7b5d10f4
Code Review Overview: Agent Enhancement Phase 1
7 - tools-only Bundle 2497 Cross Platform Notes B77d95b9
mcp-server-motherduck — Cross-Platform Path Configuration
7 - tools-only Bundle 102 Best Practices 1084ad10
Best practices for running mcpbr evaluations including cost optimization, sample sizing, MCP server configuration, and result interpretation.
7 - tools-only Bundle 102 Best Practices Db22df12
Best practices for running mcpbr evaluations including cost optimization, sample sizing, MCP server configuration, and result interpretation.
7 - tools-only Bundle 1353 Observability B78f7cbb
MCP Gateway Observability Guide
7 - tools-only Bundle 1353 Observability C86d215e
MCP Gateway Observability Guide
7 - tools-only Bundle 2696 Devkitlrainit E63e2f8d
Initialize environment for long-running agent workflow (creates feature list, progress file, init.sh)
7 - tools-only Bundle 2847 LLM Providers 16d48180
LLM Providers
7 - tools-only Bundle 2878 MCP Contracts A2cd7e77
MCP Contract Testing — Detect External MCP Server Interface Changes
7 - tools-only Bundle 2884 Reverse Proxy 047a8541
MCP Reverse Proxy
7 - tools-only Bundle 2902 LLM Providers 78faa506
LLM Providers
7 - tools-only Bundle 2929 Reverse Proxy C536397f
MCP Reverse Proxy
7 - tools-only Bundle 3043 Reverse Proxy A49bea67
MCP Reverse Proxy
7 - tools-only Bundle 2963 API Reviewer 9dc83ac9
API Reviewer Agent
7 - tools-only Bundle 2571 Branch Comparator B3bd8f70
Program Implementation Comparator Agent
7 - tools-only Bundle Swarm Task Planner 2
Creates dependency-based task plans for parallel AI agent execution. Transforms architecture docs and PRDs into priority-ordered tasks with acceptance criteria, sync checkpoints, and quality gates. Uses CLEAR+CoVe task design standards.
7 - tools-only Bundle Swarm Task Planner 3
Creates dependency-based task plans for parallel AI agent execution. Transforms architecture docs and PRDs into priority-ordered tasks with acceptance criteria, sync checkpoints, and quality gates. Uses CLEAR+CoVe task design standards.
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 556-mcp-integration_29e711f3, 729-prompt-patterns_de74e547, 730-prompting_guide_86c21f98. 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.