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 Thread Orchestrator SkillMulti-agent thread orchestration and coordination Use when this capability is needed.
- tomevault-io Bundle Release Mcpsm
Create a new release of mcp-server-manager with GitHub release (CI handles version bump and npm publish) Use when this capability is needed.
- tomevault-io Bundle Neurosurgery Literature
Use when searching for neurosurgery literature, developing PubMed search strategies, identifying MeSH terms, or building systematic search queries. Invoke for literature searching in neurosurgery topics.
- tomevault-io Bundle Adw Design
Guide creation of AI Developer Workflows (ADWs) that combine deterministic orchestration code with non-deterministic agents. Use when building automated development pipelines, designing AFK agent systems, or implementing the PITER framework. Use when this capability is needed.
- tomevault-io Bundle RAG Design
Design a RAG architecture for a use case Use when this capability is needed.
- tomevault-io Bundle Michaelleehobbs Mission Critical TS Deep Review
Deep Code Review — Multi-Agent Analysis
- tomevault-io Bundle Verify Dotnet Samples
How to build, run and verify the .NET sample projects in the Agent Framework repository. Use this when a user wants to verify that the samples still function as expected. Use when this capability is needed.
- tomevault-io Bundle Copilot Features
Use when creating or modifying any GitHub Copilot customization features, including custom instructions, AGENTS.md, agent skills, prompt files, custom agents, or agent hooks. Helps select the correct feature type and create, review, or modify it for optimal performance.
- tomevault-io Bundle Agent CLI Tmux Supervision
Use when spawning and supervising multiple agent-cli Codex worktrees through tmux, especially when you must poll progress, force prompt rereads against the local TASK file, run current-context and fresh-context pr-review loops, and verify that review fixes are actually pushed before merge.
- tomevault-io Bundle Mixelpixx Google Search MCP Server News Monitor
---
- tomevault-io Bundle Modbender Skill Library MCP Google Gemini Media
---
- tomevault-io Bundle Modbender Skill Library MCP Next Best Practices
---
- tomevault-io Bundle Codex Ecosystem Setup
Use this skill to initialize Codex configuration and manage MCP servers in a project after confirming with the user.
- tomevault-io Bundle Wp Requirements To Goals
Convert a full WordPress plugin requirements.md (multiple user stories, edge cases, settings, cross-cutting features) into a complete Codex /goal-ready project — goals-plan.md, root scaffold (.wp-env.json, package.json, AGENTS.md, plugin bootstrap, run-goals.sh, protocols), and a layered goals/ tree (foundation, per-US, non-US, integration). The full-workflow counterpart to wp-spec-to-goal — that handles single-goal vague specs; this handles multi-goal full requirements. Probes the repo first to skip clarifications the filesystem already answers (slug, namespace, WP/PHP versions). Asks remaining clarifications in ≤3 rounds. Supports phased (checkpoint after plan) or one-shot mode. Detects an existing goals-plan.md and offers to resume from Phase 2. Supports extend mode — on a completed project, appends new goals and writes only new goal folders without disturbing what shipped. Codex-only outputs — never references Claude Code or .claude/. Use when this capability is needed.
- tomevault-io Bundle Lecture Designer
This skill creates slides directly in Google Slides using the Google Docs MCP server. Before starting, ensure the MCP is installed and configured. Use when this capability is needed.
- tomevault-io Bundle D2 Diagram
Comprehensive tool for creating D2 diagrams based on descriptions and requirements. This skill should be used when creating visual diagrams, system architectures, flowcharts, network topologies, data flows, or any visual representation that can be expressed as a diagram. Triggers include requests to "create a diagram," "visualize," "draw an architecture," "show relationships," or when converting textual descriptions into visual diagrams. Use when this capability is needed.
- tomevault-io Bundle Prediction Markets Analysis
Generate Kalshi prediction market research reports or fetch structured event history. Use when the user mentions Kalshi, prediction markets, market probability, expected return, or event history. Use when this capability is needed.
- tomevault-io Bundle Omer Metin Skills For Antigravity LLM Architect
---
- tomevault-io Bundle Omer Metin Skills For Antigravity MCP Developer
---
- tomevault-io Bundle Open Ma Open Managed Agents Open Managed Agents
openma Agent Creator
- tomevault-io Bundle Openhands Software Agent Sdk Software Agent Sdk
Python Linting Skill
- tomevault-io Bundle Ray Train
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps. Use when this capability is needed.
- tomevault-io Bundle Overcut AI Overcut Playbooks Prompt Engineering
Prompt Engineering for Overcut Workflows
- tomevault-io Bundle Packmind CLI List Commands
Reference for Packmind CLI listing commands. This skill should be used when an agent needs to discover available standards, commands, or skills in the Packmind organization. Use when this capability is needed.
- tomevault-io Bundle Paiml Apr Model QA Playbook Model Certification
Model Certification
- tomevault-io Bundle AI Engineering Hub
This skill provides comprehensive tools for AI engineers and researchers to publish, manage, and link research papers on the Hugging Face Hub. It streamlines the workflow from paper creation to publication, including integration with arXiv, model/dataset linking, and authorship management. Use when this capability is needed.
- tomevault-io Bundle Patchy631 AI Engineering Hub Brightdata Web MCP
---
- tomevault-io Bundle Prompt Regression Tester
Compares old vs new prompts across test cases with diff summaries, stability metrics, breakage analysis, and fix suggestions. Use for "prompt testing", "A/B testing prompts", "prompt versioning", or "quality regression". Use when this capability is needed.
- tomevault-io Bundle Unity Editor Imgui Design
Unity IMGUI (Immediate Mode GUI) for editor tools and custom inspectors. Use for EditorWindow, Custom Inspector, Property Drawer development. NOT for game UI - use unity-game-ugui-design or unity-game-ui-toolkit-design instead. Use when this capability is needed.
- tomevault-io Bundle Agent Command
Use when coordinating AI agents as a military-style unit, applying this repo's AGENTS.md command hierarchy, fireteam/squad/platoon structure, relief protocol, D-Day-inspired command cadence, or mixed Codex/Claude task organization.
- tomevault-io Bundle Openclaw Memory Tactics
Master OpenClaw's memory architecture and self-evolution patterns. Use for optimizing memory systems, creating skills from patterns, and evolving agent capabilities. Essential for long-running autonomous agents. Use when this capability is needed.
- tomevault-io Bundle Edge Model Compression
Edge Model Compression enables deployment of large, accurate machine Use when this capability is needed.
- tomevault-io Bundle LLM Token Optimization
This skill provides techniques for optimizing token usage in LLM applications. Use when this capability is needed.
- tomevault-io Bundle Prompt Library Minimal
Library of minimal prompts that use fewest tokens while delivering good results, with templates and best practices Use when this capability is needed.
- tomevault-io Bundle AI Data Engineering
Data pipelines, feature stores, and embedding generation for AI/ML systems. Use when building RAG pipelines, ML feature serving, or data transformations. Covers feature stores (Feast, Tecton), embedding pipelines, chunking strategies, orchestration (Dagster, Prefect, Airflow), dbt transformations, data versioning (LakeFS), and experiment tracking (MLflow, W&B). Use when this capability is needed.
- tomevault-io Bundle Openclaw Cursor Brain
Use Cursor Agent as the AI brain for OpenClaw, connecting all Gateway plugin tools via MCP. 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 thread-orchestrator-skill, release-mcpsm, neurosurgery-literature. 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.