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.
-
loulanyue Skill Security Scan 4Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
-
loulanyue Skill Context Budget 5审核Claude Code上下文窗口在代理、技能、MCP服务器和规则中的消耗情况。识别膨胀、冗余组件,并提供优先的令牌节省建议。
-
loulanyue Skill Claude Devfleet 6Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.
-
loulanyue Skill Context Budget 6Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.
-
loulanyue Skill Dmux Workflows 6Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
-
loulanyue Skill Claude Devfleet 2Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.
-
loulanyue Skill MCP Server PatternsBuild MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
-
loulanyue Skill Prompt Optimizer 5Prompt 优化器
-
loulanyue Skill Autonomous Loops 2Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
-
loulanyue Skill Prompt Optimizer 2Prompt Optimizer
-
loulanyue Skill Pytorch Patterns 2PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
-
loulanyue Skill Autonomous Loops 3Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
-
loulanyue Skill Autonomous Loops 6Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
-
loulanyue Skill Prompt Optimizer 6Prompt Optimizer
-
loulanyue Skill Pytorch Patterns 6PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
-
loulanyue Skill Prompt Optimizer 3Prompt Optimizer
-
loulanyue Skill Pytorch Patterns 3PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
-
loulanyue Skill Autonomous Loops 4Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
-
loulanyue Skill Prompt Optimizer 4Prompt Optimizer
-
loulanyue Skill Agentic Engineering 3Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
-
loulanyue Skill MCP Server Patterns 3Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
-
loulanyue Skill AI First EngineeringEngineering operating model for teams where AI agents generate a large share of implementation output.
-
loulanyue Skill Pytorch Patterns 4PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
-
loulanyue Skill Agentic EngineeringOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
-
loulanyue Skill Enterprise Agent OpsOperate long-lived agent workloads with observability, security boundaries, and lifecycle management.
-
loulanyue Skill Data Scraper Agent 2Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.
-
loulanyue Skill Agentic Engineering 4Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
-
loulanyue Skill MCP Server Patterns 4Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
-
loulanyue Bundle Continuous Learning V2Hook'lar aracılığıyla oturumları gözlemleyen, güven skorlaması ile atomik instinct'ler oluşturan ve bunları skill/command/agent'lara evriltiren instinct tabanlı öğrenme sistemi. v2.1 çapraz proje kontaminasyonunu önlemek için proje kapsamlı instinct'ler ekler.
-
loulanyue Skill AI Regression Testing 3Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.
-
loulanyue Skill Continuous Agent Loop 3Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
-
loulanyue Skill AI Regression Testing 4Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.
-
loulanyue Skill Continuous Agent Loop 4Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
-
loulanyue Skill Data Scraper Agent 3Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.
-
loulanyue Skill Data Scraper Agent 4Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.
-
loulanyue Skill AI Regression TestingRegression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.
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 security-scan, context-budget, claude-devfleet. 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.