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 Robinhood For AgentsTrade stocks, options, and crypto on Robinhood — dual mode (MCP tools or TypeScript client). Use when this capability is needed.
- tomevault-io Bundle Tcia Remapping Skill
Guide users through remapping their data to the TCIA imaging submission data model and generating standardized TSVs using ontologies and a tiered conversational flow. Use when this capability is needed.
- tomevault-io Bundle Agent Skill Visualizer
Claude Code 프로젝트의 에이전트와 스킬 관계를 D3.js 노드 그래프로 시각화합니다. 에이전트-스킬 의존성을 파악하고 구조를 탐색할 때 사용하세요. Use when this capability is needed.
- tomevault-io Bundle Extension Create
Creates slash commands, subagents/workflows, or agent skills using the Claude request type framework. Analyzes requirements, determines the optimal extension type (command/subagent/skill), decides project vs personal scope, and generates properly structured files following templates and best practices. Use when creating new commands, workflows, or skills, or when the user mentions "create a command", "new workflow", "build a skill", or requests custom Claude Code extensions.
- tomevault-io Bundle Lambdatest Agent Skills Postman Collection Generator
Postman Collection Generator
- tomevault-io Bundle Agent Coordination Discipline
Use when deciding whether to launch an agent, selecting which agent to use, or coordinating multiple agents. Covers delegation criteria, external-model patterns, task isolation, and agent selection strategies.
- tomevault-io Bundle Django Model Helper
Generates Django models with proper field types, relationships, and migrations. Use when creating Django models or database schemas.
- tomevault-io Bundle Guidance Grammars
Guidance library grammar-constrained generation with categorical structure. Use when implementing structured LLM outputs with grammar constraints, building template-based generation with guaranteed formats, creating type-safe prompt templates with interleaved computation, or applying categorical grammar theory to constrained generation. Use when this capability is needed.
- tomevault-io Bundle Pr Review And Document
This skill should be used when the user asks to "review PR and save results", "run PR review with documentation", "create PR review document", "review and document PR", "save PR review to docs", "document PR review", or mentions reviewing a PR with the intention of saving the review results. Executes comprehensive PR review using pr-review-toolkit with opus model and posts results as a PR comment. Use when this capability is needed.
- tomevault-io Bundle AI News Fetcher
Tavily MCPを使用して最新AIニュースを取得し、日英バイリンガルのマークダウン記事を生成。「AIニュースを取得」「最新ニュース」などで使用。 Use when this capability is needed.
- tomevault-io Bundle Magento PHP Specialist
Advanced PHP development for Magento 2 following PSR-12 and Magento coding standards. Use when writing PHP code, implementing business logic, or ensuring code quality. Masters modern PHP features, object-oriented programming, design patterns, and Magento-specific PHP practices. Use when this capability is needed.
- tomevault-io Bundle Magento XML Specialist
Creates XML configurations for Magento 2 including layout XML, dependency injection, system configuration, and module definition. Use when working with XML configuration files, layout XML, di.xml, or system.xml. Masters XML schema design, validation, and configuration management.
- tomevault-io Bundle Factory Engineering
Configures factory engineering across IDEs. Sets up symlinks so .claude/commands and .claude/skills are available where each IDE expects them (Cursor and GitHub Copilot read .claude/skills directly; Windsurf, Kilo Code, and Antigravity need symlinks for skills; Cursor and others need symlinks for commands). Syncs .claude/commands to GitHub Copilot prompt files (.github/prompts/*.prompt.md) for VS Code. Use when configuring slash commands or skills across IDEs, setting up .cursor/commands or .windsurf/workflows from .claude/commands, syncing commands for Copilot, or unifying command and skill folders.
- tomevault-io Bundle Skill CLI Development
Use when creating, modifying, or reviewing CLI tools bundled with agent skills. Covers when to build a CLI vs. use third-party tools, domain boundary design, language selection (Python preferred, Node.js when required), complexity tiers (lightweight single-file vs. standard full-project), cross-platform configuration and credential storage under ~/.config/copilot-skills/, agent security boundaries, dependency and size management, testing, and maintainability standards.
- tomevault-io Bundle Effectiveness Tracking
Tracks task success metrics to improve future model routing. Use when completing any implementation, refactor, bugfix, or testing task. Use when this capability is needed.
- tomevault-io Bundle Modbender Skill Library MCP Nanobot Overstory Bridge
---
- tomevault-io Bundle Architecture Chief
Chief system architect responsible for end-to-end design, boundaries, and correctness of the entire platform. Use when this capability is needed.
- tomevault-io Bundle Datastore Postgres
Designs PostgreSQL schemas with RLS, migrations, and event stores. Use when this capability is needed.
- tomevault-io Bundle Development Workflow Standards
Development workflow procedures including conflict assessment, re-implementation proposals, and TDD steps. Use when you need step-by-step workflow guidance beyond what the auto-loaded verification rules provide. Use when this capability is needed.
- tomevault-io Bundle Teddynote Langchain RAG
Use this skill for public-safe reasoning about RAG and LangChain pipelines, document loading, splitting, embedding, vector stores, retrievers, prompts, chains, evaluation, deployment, and troubleshooting.
- tomevault-io Bundle Nholder88 AI Agent Workflows Impl Typescript Backend
TypeScript Backend Implementation
- tomevault-io Bundle Codanna Codebase Intelligence
Use codanna MCP tools for semantic code search, call graphs, and impact analysis before grep/find. Use when this capability is needed.
- tomevault-io Bundle Oleksandrkucherenko MCP Obsidian Via REST Release It
Release-It Skill
- tomevault-io Bundle Omer Metin Skills For Antigravity Agent Tool Builder
---
- tomevault-io Bundle Litellm Agent Platform
Use this checklist when adding a new managed-agent runtime provider.
- tomevault-io Bundle Orchestrator Conductor
This skill should be used when the user asks to "orchestrate agents", "run /orchestrate", "manage parallel agents", "coordinate multiple agents", "decompose this task", or needs patterns for multi-agent workflows with parallel execution and task decomposition. Use when this capability is needed.
- tomevault-io Bundle Agent Relay Local Update
Force-refresh local code relay status documents such as STATUS.yml, CHECKPOINT.md, HANDOFF.md, and LEADERBOARD.md in repositories that already use AGENTS.md and orchestrator-based relay files. Use when Codex should manually update relay documents after code changes, before switching sessions, before a commit, after a training run, or whenever hooks and local automation are absent or intentionally skipped. Use when this capability is needed.
- tomevault-io Bundle Bolta Team Create Agent Teammate
Create an agent identity (service account) inside a workspace and issue an API key with least privilege. Use when this capability is needed.
- tomevault-io Bundle Brendadeeznuts1111 Tier 1380 Omega Sub Agent Patterns
Sub-Agents in Claude Code
- tomevault-io Bundle Captcanadaman Session Briefing Agent Session Briefing
Agent Session Briefing
- tomevault-io Bundle Agdmigrate Agents Md
Migrate existing agent documentation to the standardized AGENTS.md format. Use when the user wants to convert, migrate, or port from AGENT.md, .cursorrules, .windsurfrules, CLAUDE.md, or contributing.md. Also triggers on 'convert .cursorrules to AGENTS.md', 'migrate agent docs', 'switch to AGENTS.md format'. Use when this capability is needed.
- tomevault-io Bundle Virtual Machine Management
Create, manage, and optimize virtual machines in Proxmox. Control VM lifecycle, monitor performance, adjust resources, and plan VM deployment strategies. Use when this capability is needed.
- tomevault-io Bundle Rwkv Architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters. Use when this capability is needed.
- tomevault-io Bundle Langsmith Observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications. Use when this capability is needed.
- tomevault-io Bundle Dspy
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming Use when this capability is needed.
- tomevault-io Bundle Demerzels Lab Elsamultiskillagent Mac Reminders Agent
Mac Reminders Agent
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 robinhood-for-agents, tcia-remapping-skill, agent-skill-visualizer. 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.