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 Agentic Self ImprovementRun behavioral benchmarks against the agent, detect failure patterns, generate guidance patches, apply them with auto-revert safety net. Implements the closed-loop self-improvement cycle from Hermes PR
- tomevault-io Bundle Documentation Search
Search the internal knowledge base for runbooks, architecture documentation, ADRs, best practices, and troubleshooting guides using RAG. Use when looking for internal documentation, deployment procedures, architecture decisions, or operational runbooks. Use when this capability is needed.
- tomevault-io Bundle Neverthrow Wrap Exceptions
Capture exceptions and promise failures with `neverthrow` instead of hand-written `try/catch` in TypeScript and JavaScript code. Use when wrapping synchronous functions that may throw, promise-returning functions that may throw before returning, existing `PromiseLike` values that may reject, or third-party APIs such as parsers, database clients, HTTP clients, file-system helpers, serializers, and SDK calls. Prefer `Result.fromThrowable` for synchronous throwers, `ResultAsync.fromThrowable` for promise-returning functions that may throw or reject, and `ResultAsync.fromPromise` when you already have a `PromiseLike` value in hand. Only keep `try/catch` when the language construct, cleanup requirement, or framework boundary truly requires it. Use when this capability is needed.
- tomevault-io Bundle MCP Management
Search, install, configure, update, and remove MCP servers across coding agents (Claude Code, Cursor, VS Code, Claude Desktop, Gemini CLI, Codex, Goose, Zed, and more). Supports multi-agent installation via npx add-mcp, the official MCP registry, and direct config editing. Use when this capability is needed.
- tomevault-io Bundle Cristianoaredes MCP Apple Store Apple Developer Apis
Apple Developer APIs
- tomevault-io Bundle Serving Llms Vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism. Use when this capability is needed.
- tomevault-io Bundle Playwright E2e Builder
Plan and build comprehensive Playwright E2E test suites with Page Object Model, authentication state persistence, custom fixtures, visual regression, and CI integration. Uses interview-driven planning to clarify critical user flows, auth strategy, test data approach, and parallelization before writing any tests. Use when this capability is needed.
- tomevault-io Bundle Agnxi Search
Use when working with the official search utility for Agnxi.com - The premier directory of AI Agent Tools, MCP Servers, and Skills.
- tomevault-io Bundle Demerzels Lab Elsamultiskillagent Fluxa Agent Wallet
FluxA Agent Wallet
- tomevault-io Bundle Metals Agent Teneo
Provides real time prices for gold, silver, and copper
- tomevault-io Bundle Demerzels Lab Elsamultiskillagent Polymarket Trading
Polymarket + Hyperliquid Trading Agent
- tomevault-io Bundle Model API Server
This skill should be used when the user asks to "use the model API server", "call the API", "query the model via HTTP", "create elements via API", "use curl with Archi", "interact with the REST API", "use the plan/apply pattern", "plan and apply changes", "run a script via API", "export a view via API", "search elements via HTTP", mentions the Model API Server, REST endpoints, or HTTP-based model operations against the JArchi server running on localhost:8765. Use when this capability is needed.
- tomevault-io Bundle Thinking Model Router
Route to the right mental model based on your domain and problem type. The single entry point for all thinking skills. Use when this capability is needed.
- tomevault-io Bundle Check Sdk Updates
Check whether Claude Code, Claude Agent SDK, and Codex SDK have new versions on npm. Use when the user asks to check for SDK/CLI updates, e.g. "check sdk updates", "check claude code update", "有沒有更新", "檢查 SDK 版本". Use when this capability is needed.
- tomevault-io Bundle Spec Quality Checklist
Validate a specification before implementation. Use when you've drafted a spec and need to verify it's complete, precise, and unambiguous. Runs in a forked spec-reviewer agent. Creates TodoWrite items for each check. Run this before proceeding to implementation planning. Use when this capability is needed.
- tomevault-io Bundle Ibus AI Pinyin Domain Dictionary
Generate and validate .dict.json domain dictionary files for ibus_llm_pinyin_input. Use this skill when the user wants to extract project-specific terms, proper nouns, product names, system names, module names, technical abbreviations, or business vocabulary from documents and convert them into an importable input-method dictionary. Use when this capability is needed.
- tomevault-io Bundle Wonderstone Agent Framework Template Design Patterns
Design Patterns — Architecture & Implementation Advisor
- tomevault-io Bundle Yeloo Vibe Skills Evaluating Machine Learning Models
Model Evaluation Suite
- tomevault-io Bundle Yeloo Vibe Skills Explaining Machine Learning Models
Model Explainability Tool
- tomevault-io Bundle Agent Voice Mobile Bridge
Drive an Android phone (running WakeHermesClaw for Android) through its opt-in Mobile Bridge HTTP API. Use whenever Hermes needs to list installed apps, read the clipboard, fetch device info, or otherwise reach Android capabilities the user has explicitly enabled. Use when this capability is needed.
- tomevault-io Bundle AI Keygen
Generate a new Ethereum keypair. Use when the user asks the AI to generate a private key/address for testing. Use when this capability is needed.
- tomevault-io Bundle Zysilm AI Video Producer Skill Gemini Video Producer
AI Video Producer (MCP Edition)
- tomevault-io Bundle Security Assurance Team
Use only when a human explicitly asks for the Security Assurance Team to run architecture-to-code security assurance and conditionally invoke identity, API, MCP, and language-specific specialists. Use when this capability is needed.
- tomevault-io Bundle Abhirkeesara Test Automation Skills Page Object Model
Page Object Model (POM) Skill
- tomevault-io Bundle Semantic Searchsearch
Use when searching the codebase with natural language queries like "authentication logic" or "database connection
- tomevault-io Bundle Eslint Rule Generator Agent
Generates custom ESLint rules from natural language descriptions using the ESLint RuleTester API and AST selectors. Integrates with typescript-eslint parser for TypeScript-aware linting.
- tomevault-io Bundle Stagehand Browser Agent Sdk
Stagehand is Browserbase's open source SDK for browser agents, combining code-first control with natural language actions. It is aimed at reliable production browser automation, with TypeScript integrations, docs, and npm distribution for agent workflows. Use when this capability is needed.
- tomevault-io Bundle Akiojin Unity MCP Server Unity Game UI Toolkit Design
Unity Game UI Toolkit Design Skill
- tomevault-io Bundle Alexlombana9 Sre Agent Hackathon 2026 Fastapi Backend
When to Use
- tomevault-io Bundle Add Model Server
Add a new VLA model server to the evaluation harness. Use this skill whenever the user wants to integrate, create, or add a new model — e.g. 'add OpenVLA server', 'integrate RT-2', 'hook up my model', 'write a model server'. Also use when they ask how model servers work or want to understand the server interface. Use when this capability is needed.
- tomevault-io Bundle Model Registry Versioning
Model Registry is a centralized system for managing complete lifecycle Use when this capability is needed.
- tomevault-io Bundle Embedding Optimization
Optimizing vector embeddings for RAG systems through model selection, chunking strategies, caching, and performance tuning. Use when building semantic search, RAG pipelines, or document retrieval systems that require cost-effective, high-quality embeddings. Use when this capability is needed.
- tomevault-io Bundle Using Vector Databases
Vector database implementation for AI/ML applications, semantic search, and RAG systems. Use when building chatbots, search engines, recommendation systems, or similarity-based retrieval. Covers Qdrant (primary), Pinecone, Milvus, pgvector, Chroma, embedding generation (OpenAI, Voyage, Cohere), chunking strategies, and hybrid search patterns. Use when this capability is needed.
- tomevault-io Bundle Documentation Manager Agent
Manage documentation lifecycle, enforce standards, validate structure, detect redundancy, and ensure proper archival. Automate documentation quality checks with validation scripts. Use when creating, updating, or organizing documentation across the repository to maintain single source of truth and prevent documentation drift. Use when this capability is needed.
- tomevault-io Bundle Web Test Wallet Connect
Connect wallet to Web3 DApp - navigate to DApp, click Connect Wallet, approve in MetaMask popup, verify connection. Can be used as a test case or as a precondition for other tests. Use when this capability is needed.
- tomevault-io Bundle Avdlee Swift Testing Agent Skill Swift Testing Expert
Swift Testing
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 agentic-self-improvement, documentation-search, neverthrow-wrap-exceptions. 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.