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 Plural Pinelabs Pinelabs Online MCP Pinelabs MCP TroubleshooPine Labs MCP Troubleshoot
- tomevault-io Bundle Logfire Observability
Full OpenClaw observability in Pydantic Logfire — agent traces, tool calls, metrics, and logs via OpenTelemetry Use when this capability is needed.
- tomevault-io Bundle App Intents Expert Skill
Expert App Intents guidance for building Siri, Shortcuts, Spotlight, Apple Intelligence, and interactive snippet integrations on iOS 26+. Use when implementing AppIntent, AppEntity, AppEnum, EntityQuery, AppShortcutsProvider, SnippetIntent, SiriTipView, IndexedEntity, or when making an app work with Siri, Shortcuts, Spotlight, Apple Intelligence, Visual Intelligence, Action Button, or Apple Pencil. Also use when asked about App Intents architecture, intent-driven development, or migrating from SiriKit. Use when this capability is needed.
- tomevault-io Bundle Saeed Vayghan Gemini Agent Skills Dotnet Framework 4 8 Exper
You are a senior .NET Framework 4.8 expert with expertise in maintaining and modernizing legacy enterprise applications. Your focus spans Web Forms, WCF services, Windows services, and enterprise integration patterns with emphasis on stability, security, and gradual modernization of existing systems.
- tomevault-io Bundle Saeed Vayghan Gemini Agent Skills Powershell Module Architec
You are a PowerShell module and profile architect. You transform fragmented scripts
- tomevault-io Bundle Astrology Interpretation Guide
Comprehensive astrology expert covering natal charts, transits, houses, aspects, and astrological traditions from Western to Vedic Use when this capability is needed.
- tomevault-io Bundle Material Design 3 Components
Comprehensive guide to Material Design 3 components — from baseline Material You through M3 Expressive. Covers action, containment, communication, navigation, selection, and text input components with specifications, states, and implementation guidelines. Use this when building or styling UI components following Material Design 3 guidelines. Use when this capability is needed.
- tomevault-io Bundle Sightflow Dev Sightflow Desktop Agent Sightflow Desktop Agen
SightFlow Agent 控制 Skill
- tomevault-io Bundle Error State Recovery
Wraps command execution in a self-healing loop. Uses heuristics to auto-fix common errors (missing deps, locked files) or escalates to the Agent with structured error context. Use when this capability is needed.
- tomevault-io Bundle Async Feedback Loop
Enables mid-stream course correction by monitoring a FEEDBACK.md file for user interventions. Allows the agent to incorporate new instructions without restarting the task.
- tomevault-io Bundle Avc
Use AVC (Agent View Controller) to present complex execution plans, architecture changes, and multi-step operations as interactive visual UIs. Instead of dumping walls of text, pipe structured JSON to `avc` for human visual review and confirmation. The human can drag-to-reorder, edit, skip, delete, and add steps before confirming. Use when this capability is needed.
- tomevault-io Bundle MCP Server Stdio
This skill helps create and configure stdio Model Context Protocol (MCP) server connections for OpenAI Agents SDK. Use when this capability is needed.
- tomevault-io Bundle Creating Effective Skills
Creating high-quality agent skills following Claude's official best practices. Use when designing, implementing, or improving agent skills, including naming conventions, progressive disclosure patterns, description writing, and appropriate freedom levels. Helps ensure skills are concise, well-structured, and optimized for context efficiency. Use when this capability is needed.
- tomevault-io Bundle Takemi Ohama AI Agent Marketplace Researcher Report Template
Researcher Report Templates Skill
- tomevault-io Bundle Cc Skill Project Guidelines Example
Project Guidelines Skill (Example) Use when this capability is needed.
- tomevault-io Bundle LLM Application Dev Langchain Agent
You are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph. Use when this capability is needed.
- tomevault-io Bundle LLM Application Dev Prompt Optimize
You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati Use when this capability is needed.
- tomevault-io Bundle Agent Governance Review
Review enterprise governance for Codex and Claude Code. Use when assessing AGENTS.md, CLAUDE.md, coding-agent policies, role boundaries, approval rules, tool restrictions, data-protection controls, or AI engineering governance gaps. Use when this capability is needed.
- tomevault-io Bundle Engineering Ticket Descriptive Title
Apply for engineering-ticket-descriptive-title. // Engineering Ticket Template - .cursorrules prompt file // Specialized prompt for creating standardized engineering tickets with detailed requirements, // implementation plans, and acceptance criter Use when this capability is needed.
- tomevault-io Bundle Tryboy869 Dojutsu For AI Nativescript Cursorrules Prompt Fil
nativescript-cursorrules-prompt-file
- tomevault-io Bundle Swift Testing Pro
Writes, reviews, and improves Swift Testing code using modern APIs and best practices. Use when reading, writing, or reviewing projects that use Swift Testing. Use when this capability is needed.
- tomevault-io Bundle Claude Code Agent Sdk
Use when building custom AI agents headlessly, embedding Claude Code tools in an app, or running scripted/cron agents—need SDK package names, setup, core API entry points, supported languages, and relation to Claude Code CLI and Messages...
- tomevault-io Bundle Result To Claim
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. A secondary Codex agent evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
- tomevault-io Bundle Xellos1010 Sdlc Visual Workflow Workspace Agent Team Launche
Agent Team Launcher
- tomevault-io Bundle Aaronbassett Agent Foundry Flutter Coreflutter Testing Quali
Flutter Testing & Quality
- tomevault-io Bundle Mastra Typescript AI Agent Framework
Mastra is an open-source TypeScript framework for building AI-powered applications and agents. Created by the team behind Gatsby, it provides model routing across 40+ providers, graph-based workflows, human-in-the-loop suspension, and MCP server authoring in a single cohesive package. Use when this capability is needed.
- tomevault-io Bundle Ollama Local LLM Runner And Model Server
Ollama runs large language models locally with a simple CLI and REST API. It supports hundreds of open models including Llama, Gemma, Qwen, and DeepSeek, with GPU acceleration and an OpenAI-compatible API endpoint. Use when this capability is needed.
- tomevault-io Bundle Orch Routing
Orchestrator routing preset — routing user requests to the correct specialist agent based on task analysis. Supports single-agent, multi-phase, and parallel routing patterns. Maps user intent to the appropriate Hyper agent using keyword matching, context analysis, and domain ownership rules. Use this skill when determining which agent should handle a user request or coordinating cross-domain tasks. Use when this capability is needed.
- tomevault-io Bundle AI Testing Workbench Test Workbench Vscode Agent Customizati
Agent Customization
- tomevault-io Bundle Aldelar Context Aware Vision Grounded Kb Agent Pytest Covera
Pytest Coverage Analysis
- tomevault-io Bundle Plagiarism Checker
Scans lyrics for phrases that may match existing songs using web search and LLM knowledge. Use before release to check for unintentional borrowing. Use when this capability is needed.
- tomevault-io Bundle Harness Engineering Playbook
Implement OpenAI Harness Engineering practices in any repository. Use when setting up or refactoring agent-first workflows, writing or upgrading AGENTS.md and PLANS.md, creating deterministic smoke/test/lint/typecheck harness commands, defining strict architecture boundaries and data-shape contracts, wiring observability from day 1, and adding entropy-control checks plus CI automation for reliable autonomous runs. Use when this capability is needed.
- tomevault-io Bundle Building Agents
Expert at creating and modifying Claude Code agents. Auto-invokes when creating/updating agents, modifying agent frontmatter (model, tools, description), designing agent architecture, or writing to */agents/*.md files. Use when this capability is needed.
- tomevault-io Bundle Langchain Skill
LangChain is a python library that built around modular components that can be chained together (hence the name "LangChain") to create complex workflows. Use this skill to orchestrate the supervisor agent that routes between take_order, answer_menu_question, and get_error_response tools for the fast food order bot. Use when this capability is needed.
- tomevault-io Bundle Chris Debug 0225 Learn Claude Code Java Learn Claude Code Ja
Agent Builder
- tomevault-io Bundle Global Setup Assistant
Guides users through one-time machine setup for claude-config-template. Auto-activates when users ask about installation, global settings, MCP setup, or first-time configuration. Reduces setup friction and validates installation. 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 plural-pinelabs--pinelabs-online-mcp--pinelabs-mcp-troubleshoot, logfire-observability, app-intents-expert-skill. 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.