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 Agent StartBegin each work session by understanding the current state and context Use when this capability is needed.
- tomevault-io Bundle Duc01226 Easy Claude Custom Agent
Quick Summary
- tomevault-io Bundle Duc01226 Easyplatform Code Review
<!-- PROMPT-ENHANCE:STEP-TASK-ANCHOR:START -->
Audited - tomevault-io Bundle Mockup
Generate UI mockups and design images using Gemini Nano Banana Pro. Use when user says build mockup, generate mockup, create mockup, make mockup, design mockup, or references creating visual designs with optional reference images for style guidance. Use when this capability is needed.
- tomevault-io Bundle Duongdev Ccpm Ccpm MCP Management
CCPM MCP Management
- tomevault-io Bundle Agent Init
Initialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or replace an agent init command (Codex, Claude), standardize multi-agent behavior, or audit an existing AGENTS.md for clarity, commands, boundaries, and repo-specific context. For Claude Code, also create CLAUDE.md as a symlink to AGENTS.md. Use when this capability is needed.
- tomevault-io Bundle Eco2 Team Backend Chat Agent Flow
Chat Agent Flow Guide
- tomevault-io Bundle Team Builder
Builds a specialized AI development team using Claude Code plugins and subagents. This skill should be used when starting a new project and you need to assemble the right team of AI specialists. It creates the .claude/ configuration directory with agent files and provides installation commands for plugins. Optimized for homelab infrastructure (Proxmox, Semaphore, MCP Servers, DVR Channels) and full-stack web development projects.
- tomevault-io Bundle Status Map
Generate human-readable ASCII status visualizations for agent sessions Use when this capability is needed.
- tomevault-io Bundle Elastic Agent Skills Agent Skills
Elasticsearch Security Troubleshooting
- tomevault-io Bundle Meting Agent
Use when an AI agent needs direct music lookup capabilities through the bundled Meting scripts in this skill, including song search, album lookup, artist lookup, playlist lookup, lyrics, cover URLs, and playback URLs, or when it needs to maintain this skill's standalone music client implementation.
- tomevault-io Bundle Elnora AI Elnora CLI Elnora Agent
Elnora Agent Capabilities
- tomevault-io Bundle Write Skills
Use when creating or improving agent skills - ensures efficient context usage, clear activation conditions, and proper structure for different skill types
- tomevault-io Bundle Before Code Analysis
Use BEFORE reading multiple files to understand code. Reminds you to use codebase-analyzer agent instead of manual file reading. Use when this capability is needed.
- tomevault-io Bundle System Setup
Guides installation and verification of MCP runtime dependencies (Python, Node.js, uv) across Windows, Linux, and macOS. Use when users need to set up their environment for running MCP servers or troubleshoot missing dependencies. Use when this capability is needed.
- tomevault-io Bundle Data Explore Data
Profile and explore a dataset to understand its shape, quality, and patterns Use when this capability is needed.
- tomevault-io Bundle Laravel Livewire
Livewire 3 reactive components - wire:model, actions, events, Volt, Folio. Use when building reactive UI without JavaScript. Use when this capability is needed.
- tomevault-io Bundle Event Driven
Event-driven architecture with pub/sub and message queues. Use for reactive systems. Use when this capability is needed.
- tomevault-io Bundle Mithril Core Agent
Build mithril-core shared infrastructure. Use when implementing storage, compression, hashing, or common types for the Mithril ML toolkit. Use when this capability is needed.
- tomevault-io Bundle Thinkfirst
Transform brain dumps, rough ideas, and vague requirements into professional, well-structured prompts following Claude's official best practices. Use this skill whenever the user wants to create a prompt, turn a rough idea into clear AI instructions, prepare for a work session, or describes what they want without clear structure. Triggers on phrases like "help me write a prompt", "brain dump", "turn this into a prompt", "I have a rough idea", "I want to build/create/make X" (when the goal is to craft the prompt, not execute it immediately), or when someone shares unstructured notes about what they need from AI. Also use when the user explicitly invokes /thinkfirst. This is the recommended starting point before any significant AI-assisted work. Use when this capability is needed.
- tomevault-io Bundle Tabz Browser
Browser automation via 70 tabz MCP tools. Use when taking screenshots, filling forms, debugging network requests, testing responsive design, or using text-to-speech notifications. Use when this capability is needed.
- tomevault-io Bundle Cross Repo Sync
Check and sync data model consistency across eventky, pubky-app-specs, and pubky-nexus repositories. Use when modifying types, adding new fields to models, or when data validation errors occur between repos. Use when this capability is needed.
- tomevault-io Bundle Gitroomhq Agent Media Agent Media
Make Product In Hands
- tomevault-io Bundle Gluestack UI V4validation
Validation checklist and anti-patterns for gluestack-ui v4 - use for code review, checking implementation quality, and identifying common mistakes. Use when this capability is needed.
- tomevault-io Bundle Agent Doc Init
Initialize baseline agent-docs files safely for new repositories using dry-run-first workflow. Use when this capability is needed.
- tomevault-io Bundle Connect Source
Connect to external data sources including MCP servers, REST APIs, and local filesystems. Use when this capability is needed.
- tomevault-io Bundle Getblock
GetBlock — RPC node and API access for 100+ blockchains; authentication, endpoints, CU pricing, Ethers/JSON-RPC, Yellowstone gRPC, MCP integration. Use when this capability is needed.
- tomevault-io Bundle Thegraph
Use when working with the Graph — subgraph manifest, schema, mappings, GraphQL API, templates, Substreams, and performance practices for agent-driven indexing.
- tomevault-io Bundle Local Council Execution
Runs a local council when no external AI providers are configured. Spawns N independent Claude subagents (one per role, blind to each other) that each answer the question from a single assigned lens, then synthesizes their perspectives. Invoked by the ask command via --local, or when the user accepts the local-council offer after no providers are found. This is a same-model (Claude-only) panel, not a cross-vendor council.
- tomevault-io Bundle View Results
View and analyze Hawk evaluation results. Use when the user wants to see eval-set results, check evaluation status, list samples, view transcripts, or analyze agent behavior from a completed evaluation run. Use when this capability is needed.
- tomevault-io Bundle Mguinada Agent Skills Git Commit
Git Commit
- tomevault-io Bundle Button Check
Traverse all interactive elements on the page — click clickables, Use when this capability is needed.
- tomevault-io Bundle Deno Typescript
Guidelines for developing with Deno and TypeScript using modern runtime features, security model, and native tooling Use when this capability is needed.
- tomevault-io Bundle Minimax AI Mini Agent Mini Agent
DOCX creation, editing, and analysis
- tomevault-io Bundle Apple Mail
Search, read, and extract attachments from Apple Mail's local storage. Query emails by sender, recipient, subject, body, date, mailbox, and flags. Read raw RFC822 messages and extract file attachments. Use when this capability is needed.
- tomevault-io Bundle Modbender Skill Library MCP Rust
---
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 agent-start, duc01226--easy-claude--custom-agent, duc01226--easyplatform--code-review. 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.