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.
-
tomevault-io Bundle Debian777 Kairos MCP Kairos Installkairos-install
- tomevault-io Bundle Deevsdeevs Agent System Bug Hunters
Bug Hunters
- tomevault-io Bundle Deevsdeevs Agent System Cost Status
Cost Status
- tomevault-io Bundle Deevsdeevs Agent System Dev Experts
Dev Experts
- tomevault-io Bundle Investigate Sentry Issue
Investigate and triage a Sentry error issue Use when this capability is needed.
- tomevault-io Bundle IOS Debugger Agent
Use XcodeBuildMCP to build, run, launch, and debug the current iOS project on a booted simulator. Trigger when asked to run an iOS app, interact with the simulator UI, inspect on-screen state, capture logs/console output, or diagnose runtime behavior using XcodeBuildMCP tools. Use when this capability is needed.
- tomevault-io Bundle Learn Architecture
Deep scan of project structure to update architecture knowledge. Uses semantic code search for API, model, error, and test patterns. Use to bootstrap or refresh project knowledge. Use when this capability is needed.
- tomevault-io Bundle Testing With Playwright
Claude writes reliable E2E tests using Playwright for browser automation. Use when writing end-to-end tests, implementing Page Object Model, visual regression testing, API mocking, or cross-browser testing. Use when this capability is needed.
- tomevault-io Bundle Connection Properties
Specialized agent for creating and improving Connection Properties in Aspire resource and README files Use when this capability is needed.
- tomevault-io Bundle Dvy1987 Agent Loom Code Review Crsp
Code Review
- tomevault-io Bundle Openai Agents Sdk
OpenAI Agents SDK (2025~) 활용 가이드. Agent + Runner + WebSearchTool + RunContextWrapper 패턴. Structured Output, Function Tool, Handoff 구현 시 참조. "agents sdk", "openai agent", "runner", "web_search", "function_tool", "handoff" 키워드로 트리거. Use when this capability is needed.
- tomevault-io Bundle Manako Setup
This skill should be used when the user asks to "manako をセットアップ", "manako setup", "manako の設定", "manako CLI をインストール", "MCP Server を設定", "manako に接続", "manako plugin setup", "manako login", "monitoring tool setup". Guides initial setup of Manako CLI and MCP Server for Claude Code integration. Use when this capability is needed.
- tomevault-io Bundle Github Labels
Reference for valid GitHub labels in HestAI-MCP repository to prevent label errors Use when this capability is needed.
- tomevault-io Bundle Dial MCP Server
Run DIAL as an MCP server for AI assistants. Use when integrating with Claude Desktop or other MCP clients. Use when this capability is needed.
- tomevault-io Bundle Seedance Vocab En
This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints. Use when this capability is needed.
- tomevault-io Bundle Erich3000 Ji Agent Skills Todo Init
todo-init
- tomevault-io Bundle Escotilha Claude Kit Autonomous Dev
Autonomous Coding Agent
- tomevault-io Bundle Doc Lint
Quick lint check for a single documentation file. Faster than full validation - checks frontmatter and basic formatting only. Use during writing to catch issues early. Use when this capability is needed.
- tomevault-io Bundle Code Search Exa
Code context using Exa. Finds real snippets and docs from GitHub, StackOverflow, and technical docs. Use when searching for code examples, API syntax, library documentation, or debugging help. Use when this capability is needed.
- tomevault-io Bundle Update MCP
Create, update, or manage universal-ai-config MCP server templates. Handles finding existing configs, deciding whether to create or modify, and writing the template. Use when this capability is needed.
- tomevault-io Bundle Shared Memory
Read and write project memory that ANY AI agent can find (Claude Code, Cursor, Codex, OpenClaw, Aider, ...). Defines a portable on-disk convention in the project repo plus a private layer for personal notes. Use when saving project knowledge that should survive across tools, or when you suspect another agent's memory might be relevant. Use when this capability is needed.
- tomevault-io Bundle Trading
Manage TastyTrade brokerage accounts — monitor portfolios, analyze options with Greeks, place and manage multi-leg orders, and stream real-time market data. Use when the user asks about account balances, positions, options chains, IV rank, order placement, watchlists, or market status. Use when this capability is needed.
- tomevault-io Bundle Review Comments
Address PR review comments from reviewers (amazon-q-developer, copilot, humans). Use when the user wants to see and respond to feedback on their pull request. Use when this capability is needed.
- tomevault-io Bundle Fluxloop AI Fluxloop Prompt Compare
FluxLoop Prompt Compare Skill
- tomevault-io Bundle Custom Agent Builder
Create, audit, modify, convert, or retire persistent Claude Code or Codex custom agent definitions. Use when the user asks for a reusable custom agent, subagent definition, agent portfolio, persistent reviewer/researcher/worker agent, or an audit of existing agent files. Do not use for one-off transient delegation, ordinary skill authoring, AGENTS.md work, connector setup, hooks, or prompts that do not need a durable agent file. Use when this capability is needed.
- tomevault-io Bundle Frootai Frootai Tune Voice AI Agent
Tune Voice AI Agent
- tomevault-io Bundle Github Copilot
GitHub Copilot AI code suggestions and chat. Use for code completion. Use when this capability is needed.
- tomevault-io Bundle Parallel Search
AI-powered web search via Parallel API. Returns ranked results with LLM-optimized excerpts. Use for up-to-date research, fact-checking, and domain-scoped searching. Use when this capability is needed.
- tomevault-io Bundle Analyze Run
Analyze all failures in a convex-evals run, spawning parallel sub-agents to investigate each failure and producing a report with classifications and recommendations. Use when the user asks to analyze an entire run, review all failures in a run, or wants to understand why a model scored poorly. Use when this capability is needed.
- tomevault-io Bundle Agent Researcher
Agent skill for researcher - invoke with $agent-researcher Use when this capability is needed.
- tomevault-io Bundle Agent User Tools
Agent skill for user-tools - invoke with $agent-user-tools Use when this capability is needed.
- tomevault-io Bundle Agentdb Advanced Features
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications. Use when this capability is needed.
- tomevault-io Bundle Agentdb Learning Plugins
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience. Use when this capability is needed.
- tomevault-io Bundle Hooks Automation
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows. Use when this capability is needed.
- tomevault-io Bundle MCP Server Builder
Especialista en construccion de servidores MCP (Model Context Protocol). Cubre ciclo de vida del protocolo, transportes stdio y SSE/HTTP, definicion de herramientas con JSON Schema, seguridad de inputs, testing con MCP Inspector y despliegue. Activa al construir un servidor MCP propio, exponer herramientas internas a Claude, o publicar un servidor MCP en el registro oficial. Use when this capability is needed.
- tomevault-io Bundle Codex Review Branch
Fully automated review of an entire feature branch using Codex MCP Use when this capability is needed.
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 debian777--kairos-mcp--kairos-install, deevsdeevs--agent-system--bug-hunters, deevsdeevs--agent-system--cost-status. 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.