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tools-only Bundle 1699 Agent Operating Manual 37e4ab16**Current year: 2026.** Your training data may be outdated. Verify external APIs, library versions, and best practices before implementation.
7 - tools-only Bundle 1699 Agent Operating Manual Daa8c0c5
**Current year: 2026.** Your training data may be outdated. Verify external APIs, library versions, and best practices before implementation.
7 - tools-only Bundle 1713 The Amnesiac Architect Dfb39fb3
Integrating Compound Engineering and Supermemory into the Namshub Agent Harness
7 - tools-only Bundle 1789 Agent Frameworks 40d5a119
Agent Framework Blogs
7 - tools-only Bundle 2531 Setup Skill Hook 14752a8c
Set up the skill-activation-prompt hook in your project with automatic configuration
7 - tools-only Bundle 659 Description Skill 21c9e586
Hook recipes and working examples — plugin hooks, frontmatter hooks in skills/agents/commands, prompt-based LLM hooks, and complete code examples in Python and Node.js. Use when building hook scripts, integrating hooks into plugins, implementing prompt-based hooks, or looking for hook configuration patterns.
7 - tools-only Bundle 659 Description Skill 54cfec92
Documentation and authoring workflow router — audit docs vs code drift, sync docs after code changes, optimize prompts and SKILL.md files for AI consumption, validate GLFM and Markdown, summarize files/URLs/images with fidelity enforcement. Routes each task to the right specialist agent automatically.
7 - tools-only Bundle 659 Description Skill 5839997c
Start or complete a specific task inside a SAM task file. Updates task status to IN PROGRESS with Started timestamp, writes active-task context for hooks, and supports --complete to mark tasks complete. Use when an agent needs to pick up a SAM task, set it in progress, implement acceptance criteria, and signal completion.
7 - tools-only Bundle 659 Description Skill 6e15c3d9
Guide for creating Claude Code plugin hooks — Node.js .cjs scripts only, hooks.json configuration, event selection, prompt-based vs command hooks, ${CLAUDE_PLUGIN_ROOT} paths, stdio suppression, timeout sizing, and testing. Use when adding hooks to a plugin, creating PreToolUse/PostToolUse/Stop/SubagentStop/SessionStart/UserPromptSubmit hooks, or wiring hook scripts to hooks.json.
7 - tools-only Bundle 659 Description Skill Be055adb
Guide for creating Claude Code plugin hooks — Node.js .cjs scripts only, hooks.json configuration, event selection, prompt-based vs command hooks, ${CLAUDE_PLUGIN_ROOT} paths, stdio suppression, timeout sizing, and testing. Use when adding hooks to a plugin, creating PreToolUse/PostToolUse/Stop/SubagentStop/SessionStart/UserPromptSubmit hooks, or wiring hook scripts to hooks.json.
7 - tools-only Bundle 659 Description Skill D2bc80fb
Start or complete a specific refactoring task from a task file. Use when a sub-agent needs to pick up a refactoring task, update its status, implement acceptance criteria, and run verification steps.
7 - tools-only Bundle 1759 Advanced Usage Ff9c1b16
Stable Diffusion Advanced Usage Guide
7 - tools-only Bundle 2875 Claude Desktop 32ca54e4
Claude Desktop × MCP Gateway
7 - tools-only Bundle 556 MCP Integration 8bb4aea3
Guide to integrating and testing MCP servers with mcpbr, including configuration, environment variables, and common server setups.
7 - tools-only Bundle 556 MCP Integration D8ae2e35
MCP Server Integration
7 - tools-only Bundle 619 New Whitepaper Bdbf8bcd
Prompt-Driven Development: Solving the Software Maintenance Crisis
7 - tools-only Bundle 1097 Troubleshooting 16180695
Chrome DevTools MCP Troubleshooting Guide
7 - tools-only Bundle 1762 Prompt Snippets A6995d7c
Prompt Snippets for Opus 4.5
7 - tools-only Bundle 2440 Provider Configuration 2591aec0
LLM Provider Configuration
7 - tools-only Bundle 2456 Agent Sdk Custom Tools Fc89c16b
Custom tools allow you to extend Claude Code's capabilities with your own functionality through in-process MCP servers, enabling Claude to interact with external services, APIs, or perform specialized operations.
7 - tools-only Bundle 2505 Model Accepts Settings 4bf52d6e
Watch the implementation of a warning system that alerts users when they try to apply reasoning settings to models that don't support them. Includes adding model metadata, confirmation dialogs, refactoring, and comprehensive test coverage.
7 - tools-only Bundle 2546 Forward Client Headers C0129ce1
Forward Client Headers to LLM API
7 - tools-only Bundle 175 Common Mistakes 608b39dd
Common C4 Model Mistakes to Avoid
7 - tools-only Bundle 720 Project Summary 5b159beb
作为专业的软件工程与安全分析专家，您需要对目标 MCP（Model Context Protocol）服务进行**动态信息收集**与分析。本阶段旨在为后续安全检测、架构评估提供基础数据支撑。
7 - tools-only Bundle 1212 MCP Tool Design 54c4e772
<overview>
7 - tools-only Bundle 1638 Docs MCP Server C37d79ec
Docs MCP Server (Grounded Docs) - Local Documentation Index for AI Assistants
7 - tools-only Bundle 1910 Comparison Mode Ab48989e
Side-by-Side MCP Server Comparison
7 - tools-only Bundle 2067 MCP Config JSON 4fcf3389
MCP Configuration (.mcp.json) Environment Variables
7 - tools-only Bundle 2133 Direct Creation 4bb15d31
Direct Creation (MCP) Details
7 - tools-only Bundle 274 Deployment Guide 5ec8ba99
Agent Deployment Guide
7 - tools-only Bundle 3055 Langflow Server 4739c90c
🌊 Langflow MCP Server Integration
7 - tools-only Bundle 332 Embedding Models A840774b
Embedding Models
7 - tools-only Bundle 592 Model Evaluation 246f20f8
Model Selection and Evaluation Reference
7 - tools-only Bundle 2876 Tool Categories 7ce43e0f
Tool Categories — Flexible Tool Matching by Intent for AI Agent Tests
7 - tools-only Bundle 2898 Issue Queen Bee Ff145db4
Hive Queen Bee: Native agent-building agent
7 - tools-only Bundle 2900 Threat Taxonomy E4412146
Agent Skills Threat Taxonomy
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 1699-agent-operating-manual_37e4ab16, 1699-agent-operating-manual_daa8c0c5, 1713-the-amnesiac-architect_dfb39fb3. 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.