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

J4flmao Agent Skills Nodejs Express Skill

Node.js Express

Sep 17
tomevault-io Bundle

Call Foundry Agent

Call Foundry agent with a prompt and get the response. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Agentskills

Agent Skills Open Standard reference (agentskills.io). Use when creating portable skills for Claude Code, Cursor, Gemini CLI, OpenAI Codex, VS Code, Roo Code, and 20+ compatible agents. Covers frontmatter schema, naming rules, directory structure, progressive disclosure, validation, and authoring. Load before creating cross-agent skills. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Pydantic Model

Guide for creating Pydantic v2 models with proper validation, field examples, and schema separation following this project's conventions. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Agent Zero Comparison

Detailed product/option comparisons using Agent Zero Use when this capability is needed.

Sep 17
tomevault-io Bundle

Uat Import

Convert AI agent configs between platforms with one command. Supports 12 platforms (Dify, Cursor, Windsurf, Claude, etc.) Use when this capability is needed.

Sep 17
tomevault-io Bundle

Opencode Docs

Local OpenCode documentation reference. Use when asked about OpenCode features, tools, agents, MCP servers, plugins, CLI, TUI, or IDE integration. Use when this capability is needed.

Sep 17
tomevault-io Bundle

MCP Tool Design

Engineering robust, self-describing, and error-resilient tools for AI models. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Jeffrichley Agent Core Spawning Subagents

spawning-subagents — dispatching minions

Sep 17
tomevault-io Bundle

AI Consultation

This skill should be used when the user asks for a "second opinion", "ask codex", "ask gemini", "AI code review", "external AI consultation", or needs prompt templates and workflows for code review, security audit, architecture analysis, or multi-model consultation. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Parallel Integrate

Verify integration after parallel agent execution and generate report Use when this capability is needed.

Sep 17
tomevault-io Bundle

Python Naming

Python naming conventions for variables, constants, files, and directories Use when this capability is needed.

Sep 17
tomevault-io Bundle

Python Uv CLI

UV command-line usage patterns for Python project management Use when this capability is needed.

Sep 17
tomevault-io Bundle

Alignment Checkpoint

Intent-alignment gate for ambiguous/high-stakes requests. Use this when you want to extract goal/assumptions/criteria and require an explicit /proceed approval gate before any tool use. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Tidymodels Overview

This skill should be used when working with R tidymodels packages, including when the user asks to "create a tidymodels workflow", "build a recipe", "tune a model", "use parsnip", "set up resampling", "create a workflow_set", "compare models", "stack models", or mentions tidymodels packages like recipes, parsnip, workflows, workflowsets, tune, rsample, yardstick, or stacks. Provides ecosystem context before package-specific skills. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Agent Harness Construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Spectre

Deep Research Swarm — Deploys parallel researchers to explore any topic via web, codebase, and documents, then synthesizes, validates claims, and generates a structured report. Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Moltoffer Candidate

MoltOffer candidate agent. Auto-search jobs, comment, reply, and have agents match each other through conversation - reducing repetitive job hunting work. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Testing Unit

Deterministic unit-test strategy for isolated logic and fast feedback. Use when core logic branches, error paths, and edge conditions need low-latency regression evidence with controlled dependencies; do not use for browser-flow or cross-service compatibility validation. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Kilo Org Kilo Marketplace Langsmith Fetch

LangSmith Fetch - Agent Debugging Skill

Sep 17
tomevault-io Bundle

Copilotkit Demo Parity

Keeps examples/integrations/* demos aligned to the north-star (langgraph-python). Use when the user says "sync demos", "sync integrations", "port to north-star", "align integration demos", "parity check", or when working inside examples/integrations/ and tracked files diverge. Drives the pnpm parity:sync / parity:verify commands and handles the manual-merge zones (agent code, api route, Dockerfile). Use when this capability is needed.

Sep 17
tomevault-io Bundle

Agent Skills Nix

Reads from a shared dir at the source root. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Lambdatest Agent Skills API Sdk Generator

API SDK & Codegen Skill

Sep 17
tomevault-io Bundle

Kebab Codebase Navigation

Navigate and modify the Kebab CUDA codebase safely. Use when asked to locate GEMM, CuTe, CUDA baseline, benchmark, microbenchmark, profiling, or build logic in this repository, and when deciding where a change should be implemented. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Langgraph Workflows

Expert guidance for designing LangGraph state machines and multi-agent workflows. Use when building workflows, connecting agents, or implementing complex control flow in LangConfig. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Using Agent Setup

When to use the agent-setup CLI to link a project's .agents/ declarations (skills, MCP servers, AGENTS.md) into every detected AI coding agent's native config format. Use this skill whenever a user asks how to install, sync, or share skills and MCP servers across Claude Code, Codex, Cursor, Gemini CLI, or OpenCode. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Git CLI Agentic

Git commands optimized for AI agent workflows with porcelain output and deterministic execution patterns. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Building Agent Skills

Assists in creating Agent Skills of varying complexity levels (simple, moderate, complex). Use when the user wants to create, design, or build a new Agent Skill, or when they need guidance on skill architecture, workflow design, schema validation, or template structure.

Sep 17
tomevault-io Bundle

Gtasks Todo Manager

Manages to-do items across multiple Google accounts using the Google Tasks API. Use when the user needs to create, update, complete, or organize tasks in Google Tasks, manage task lists, or view tasks across multiple Google accounts. Supports personal Gmail, Google Workspace, and organization-provisioned accounts with secure OAuth authentication.

Sep 17
tomevault-io Bundle

Paw Rewind

Workflow rewind utility skill for PAW workflow. Rolls back workflow state to a previous stage or phase with safeguards and user confirmation. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Paw Status

Workflow status activity skill for PAW workflow. Diagnoses workflow state, recommends next steps, explains PAW process, and optionally posts updates to Issues/PRs. Use when this capability is needed.

Sep 17
tomevault-io Bundle

System Prompt Engineer

Author and review system prompts for agent behavior control, instruction precedence, safety constraints, and output contracts. Use when defining or auditing operational prompts for reliability. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Fastapi Review

Deep review of FastAPI applications — dependency injection, Pydantic validation, async patterns, middleware, security, and OpenAPI contract correctness. Use when this capability is needed.

Sep 17
tomevault-io Bundle

GRAPHQL Review

Deep review of GraphQL implementations — query complexity, N+1 resolution, schema design, authorization, subscriptions, and common GraphQL-specific vulnerabilities. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Rust Ml Huggingface Porting

Port HuggingFace models to Candle with correct tensor naming. Use when debugging weight loading errors or matmul issues. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Create Pw Skill

Guides the creation of a new ProcessWire agent skill from source material. Reads provided sources, proposes file structure and description, creates SKILL.md with reference files following best practices. Use when creating a new PW skill for this repository. Use when this capability is needed.

Sep 17

Frequently asked questions

What are AI & ML agent skills?

Which AI & ML skills are most installed?

Popular AI & ML skills on SkillMD right now include j4flmao--agent-skills--nodejs-express-skill, call-foundry-agent, agentskills. 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.