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 Skill EvaluatorEvaluate agent skill quality using rubric-based assessment. Use when assessing skill effectiveness, identifying improvement opportunities, or ensuring quality standards. Use when this capability is needed.
- tomevault-io Bundle AI Models
Fetch latest AI model IDs from Anthropic, OpenAI, and Google APIs to use accurate model names in code Use when this capability is needed.
- tomevault-io Bundle Tony AI Workflow Plugins Cursor
Cursor Agent CLI Skill
- tomevault-io Bundle Agent Gen
Generate a repo-tailored AGENTS.md file by analyzing the project's tech stack, build commands, codebase patterns, git history, and CI configuration. Presents the result for user approval before writing. Use when this capability is needed.
- tomevault-io Bundle Butler DB Schema
Guide for designing and managing a butler's PostgreSQL database schema. Use when creating tables, writing migrations, adding indexes, or evolving a butler's data model. Use when this capability is needed.
- tomevault-io Bundle Dspy Rb
Build type-safe LLM applications with DSPy.rb - Ruby's programmatic prompt framework with signatures, modules, agents, and optimization Use when this capability is needed.
- tomevault-io Bundle Glm Image
Generate images using GLM-Image API. Use when the user wants to generate, create, or draw an image from a text prompt. Triggers on requests like "generate an image of...", "create a picture of...", "draw...", or any image generation request. Use when this capability is needed.
- tomevault-io Bundle Vizra Adk Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents Use when this capability is needed.
- tomevault-io Bundle Analyze Model
Analyze an external model URL (typically Hugging Face) to determine implementation style and estimate SD.Next porting difficulty using the port-model workflow. Use when this capability is needed.
- tomevault-io Bundle Agentteams
Mode B parallelism. Manually invoke Claude Code Agent Teams (multiple full Claude Code instances coordinating via shared task list + worktree isolation + Agent View). The multispec engine auto-selects this mode when the work demands it; this skill is for forcing it. Use when this capability is needed.
- tomevault-io Bundle Agent View
Diagnose Claude Code Agent View readiness safely inside the minmaxing harness. This route is static readiness and troubleshooting only; open the live Agent View TUI manually with claude agents. Use when this capability is needed.
- tomevault-io Bundle Pywayne LLM Chat Bot
LLM chat interface using OpenAI-compatible APIs with streaming support and session management. Use when working with pywayne.llm.chat_bot module for creating LLM chat instances with custom configuration, managing multi-turn conversations with history, handling streaming responses, or managing multiple chat sessions with ChatManager Use when this capability is needed.
- tomevault-io Bundle Repoprompt
Plan and troubleshoot Repo Prompt integration across editors, agents, MCP, and CLI workflows. Use when the user wants Repo Prompt configured, adopted, or compared inside an AI coding setup. Use when this capability is needed.
- tomevault-io Bundle Spacemolt
Play SpaceMolt - an MMO for AI agents. Includes session management for OpenClaw's persistent MCP connections. Use when this capability is needed.
- tomevault-io Bundle Collab Deliberation
Structure multi-agent brainstorming and deliberation (options, tradeoffs, decision framing) without drifting into implementation. Use when this capability is needed.
- tomevault-io Bundle Agent Runner Seed Plan Implement Run
Initialize an agent-runner `plan-implement-feature` run from the target repository root. Use this when the user wants to prepare the single-run plan-plus-implement workflow, not when they want the run driven to completion immediately. Use when this capability is needed.
- tomevault-io Bundle Kevsmir02 Toji Agent Stack Mern
MERN Standards
- tomevault-io Bundle Session Logs
View and manage agent session logs for debugging and auditing. Use when this capability is needed.
- tomevault-io Bundle Kubeshark Kubeshark Network Rca
Network Root Cause Analysis with Kubeshark MCP
- tomevault-io Bundle Deep Recon
Run extended multi-agent reconnaissance sessions. Use when asked to brainstorm deeply, explore ideas from multiple angles, or generate a structured recon document. Use when this capability is needed.
- tomevault-io Bundle Eth Agent
Expert knowledge for using the eth-agent library - the simplest, safest way for AI agents to send stablecoins on Ethereum. Use when writing code that interacts with Ethereum, sends tokens, or builds AI agent payment systems. Use when this capability is needed.
- tomevault-io Bundle Suno
This skill should be used when the user wants to compose songs for Suno AI, write lyrics, create style prompts, or generate Suno metatags. Supports J-pop, K-pop, EDM, ballads, rock, and Latin genres, plus album/EP composition, variations, and song continuations. Also handles reference-based composition ("like YOASOBI", "in the style of Aimer") and J-pop tier presets ("anisong", "mainstream", "doujin"). Triggers on "write a song", "Suno prompt", "Suno metatags", "style of music", "song lyrics", "Suno AI", "acoustic version", "create an album", "extend this song", "like [artist]", "in the style of", "/suno", "anisong", "doujin", "negative prompting", "ad-libs". Use when this capability is needed.
- tomevault-io Bundle Prompt Expander
EXPAND vague prompts into precise, platform-optimized instructions. Detects target platform (Claude, GPT, Gemini, Midjourney, Sora, etc.) and applies appropriate prompting patterns. Use when user says "coggle", "expand", "improve prompt", "make better". Use when this capability is needed.
- tomevault-io Bundle RAG Skills
RAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers. Covers ingestion, retrieval, embeddings, and performance. Use when this capability is needed.
- tomevault-io Bundle Lowyshin Giip Dev Agent Dynamic
Intermediate (Dynamic) Skill
- tomevault-io Bundle Lowyshin Giip Dev Agent Starter
Beginner (Starter) Skill
- tomevault-io Bundle Meerkat Platform
Comprehensive guide for building applications with the Meerkat agent platform. Covers all surfaces (CLI, REST, RPC, MCP, Python SDK, TypeScript SDK, Rust SDK), configuration, sessions, streaming, skills, hooks, memory, inter-agent communication, and mob orchestration (spawn, fork, helpers, flows). This skill should be used when users ask how to integrate with Meerkat, build agents, configure the runtime, use the SDK, set up multi-agent systems, or work with any Meerkat feature. Use when this capability is needed.
- tomevault-io Bundle Ma1orek Replay Claude Agent Sdk
Claude Agent SDK - Structured Outputs & Error Prevention Guide
- tomevault-io Bundle Handoff To Claude Code
Use when the user asks to hand a finished design off to a developer or a coding agent for implementation in a real codebase. Produces a self-sufficient handoff folder with a spec README, zipped for download.
- tomevault-io Bundle Disable Model Invocation
Use when working with a skill that cannot be invoked by the model.
- tomevault-io Bundle Doc Fetcher
Fetch library and framework documentation via context7-mcp and fetch-mcp Use when this capability is needed.
- tomevault-io Bundle Write A Skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill. Use when this capability is needed.
- tomevault-io Bundle Mauromedda Agent Toolkit Golang
ABOUTME: Go 1.26 idiomatic development skill with automated quality gates
- tomevault-io Bundle Mauromedda Agent Toolkit Python
ABOUTME: Comprehensive skill for idiomatic Python best practices
- tomevault-io Bundle Remote MCP
Control remote machines via MCP using terminator CLI. Auto-activates when user says "remote MCP", "connect to machine", "execute on remote", or wants to run commands on remote VMs. Use when this capability is needed.
- tomevault-io Bundle Team Review
Multi-agent PR review team orchestration with 7 specialized reviewers for security-sensitive or architectural PRs. Spawns architecture, security, performance, testing, style, docs/UX, and adversary reviewers as a coordinated team. Premium review for critical code changes. 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 skill-evaluator, ai-models, tony--ai-workflow-plugins--cursor. 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.