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 Swift ProgrammingLearn and program in Swift - Apple's programming language for iOS, Use when this capability is needed.
- tomevault-io Bundle Migrate Skills Between Libraries
Use when moving skills between library workspaces or upgrading from a personal library to a team library. Export from one workspace, import into another.
- tomevault-io Bundle Monocloud Auth Express
Use when integrating MonoCloud access-token validation into an Express API — installing or configuring `@monocloud/backend-node/express`, wiring the `protectApi()` middleware factory, validating JWT or opaque (introspection) bearer tokens, enforcing scopes/groups, attaching `claims` to `req` via `AuthenticatedExpressRequest`, or troubleshooting `MONOCLOUD_BACKEND_*` env vars / audience / JWKS / mTLS certificate binding.
- tomevault-io Bundle Evolving Workflow
Templates for building parallel AI agent workflows in MoonBit. Includes patterns for simple fan-out processing and multi-phase orchestration with automatic retry and validation. Use when this capability is needed.
- tomevault-io Bundle Gh Issue Merge
Merge captain workflow to safely merge a PR for a GitHub issue after QA PASS (checks, reviews, merge, cleanup). Use as the Merge sub-agent. Use when this capability is needed.
- tomevault-io Bundle Nolte Claude Reachy Mini MCP Server Bootstrap
MCP Server Bootstrap
- tomevault-io Bundle Jupyter Live Kernel
Iterative Python via live Jupyter kernel (hamelnb). Use when this capability is needed.
- tomevault-io Bundle Orchestrating Agents
Orchestrates parallel API instances, delegated sub-tasks, and multi-agent workflows with streaming and tool-enabled delegation patterns. Use for parallel analysis, multi-perspective reviews, or complex task decomposition. Use when this capability is needed.
- tomevault-io Bundle Okareo AI Okareo Tools Agent Improvement Loop
Okareo: Agent Improvement Loop
- tomevault-io Bundle Subagent Worker Research
子 agent（Research）：生成澄清/边界产物并落盘。 Use when this capability is needed.
- tomevault-io Bundle Claude Agent Sdk TS
Build AI agents with Claude Agent SDK in TypeScript. Covers V1 query() API for batch workflows and V2 session API for interactive apps. Includes tool configuration, hooks, MCP servers, and multi-turn patterns. Use when this capability is needed.
- tomevault-io Bundle Omer Metin Skills For Antigravity MCP Product
---
- tomevault-io Bundle Omer Metin Skills For Antigravity MCP Testing
---
- tomevault-io Bundle Dspy Bootstrap Fewshot
This skill should be used when the user asks to "bootstrap few-shot examples", "generate demonstrations", "use BootstrapFewShot", "optimize with limited data", "create training demos automatically", mentions "teacher model for few-shot", "10-50 training examples", or wants automatic demonstration generation for a DSPy program without extensive compute. Use when this capability is needed.
- tomevault-io Bundle Browser Inspection
Use when needing to inspect, debug, or interact with a browser - helps choose between Browser MCP (existing sessions) and DevTools MCP (debugging tools) based on the task requirements
- tomevault-io Bundle Geo Leaderboard
Run a category-wide GEO leaderboard — compare all brands in a category to see who has the strongest AI visibility Use when this capability is needed.
- tomevault-io Bundle Openhands Software Agent Sdk Code Style Guide
Code Style Guide
- tomevault-io Bundle Openhands Software Agent Sdk Rot13 Encryption
ROT13 Encryption Skill
- tomevault-io Bundle Openvinotoolkit Openvino Genai Openvino Genai
LLM Bench Fail Analyzer
- tomevault-io Bundle Paiml Paiml MCP Agent Toolkit Pmat Multi Lang
PMAT Multi-Language Project Analysis Skill
- tomevault-io Bundle Multi CLI Anything
Add a new CLI provider to cc-multi-cli-plugin (beyond the built-in Codex/Gemini/Cursor/Copilot). Use when the user asks to integrate another AI CLI like Qwen, OpenCode, Aider, or any CLI that speaks ACP, ASP, or another structured protocol. Trigger phrases include "add Qwen to the plugin", "integrate OpenCode", "hook up my custom CLI", "support another model via ACP". Use when this capability is needed.
- tomevault-io Bundle Photoszzt Tlaplus AI Tools Tla Model Checking
TLA+ Model Checking Workflow
- tomevault-io Bundle Mapping Invariants
Phylax Credible Layer assertions invariant mapping. Use when starting a protocol to map invariants before writing phylax/credible layer assertions or tests. Use when this capability is needed.
- tomevault-io Bundle Testing Assertions
Phylax Credible Layer assertions testing. Tests phylax/credible layer assertions with CredibleTest, fuzzing, and backtesting. Use when this capability is needed.
- tomevault-io Bundle Parametrised Optics Cybernetics
Parametrised optics model cybernetic systems - dynamical systems steered by agents. ⊛ represents agency exerted on systems. Connects Para(C), lenses, open games, and PCT. Use when this capability is needed.
- tomevault-io Bundle Portainer Portainer MCP Portainer MCP Hygiene
Portainer MCP hygiene
- tomevault-io Bundle Agent Scaffolding
Scaffold a multi-agent workspace with AGENTS.md, .agents/, .claude/, and .gemini/ directories. Use when the user asks to set up a new project for multi-agent development, create an AGENTS.md, or configure a workspace for both Claude Code and Gemini/Antigravity. Use when this capability is needed.
- tomevault-io Bundle Cl MCP Server Integration
For Claude agents using the cl-mcp-server REPL tools. Tool mental model, usage patterns, pitfalls. Use when this capability is needed.
- tomevault-io Bundle Prompt Refactor
Scan a prompt file for layer violations and structural problems, then fix them. Use when user wants to clean up documentation files or mentions /prompt-refactor command. Use when this capability is needed.
- tomevault-io Bundle Sync Plugin Docs
Regenerate plugin-docs/CLAUDE.md from source code and agent-notes to prevent documentation drift. Use when this capability is needed.
- tomevault-io Bundle Web UI Phase Closure
Close phase-13 web UI and XP editor gaps with MCP-first, user-flow Use when this capability is needed.
- tomevault-io Bundle Vibe Manifest Generator
自动分析项目结构并生成适配 Cursor, Claude Code, Windsurf 等主流 Vibe Coding 软件的 Manifest 配置文件（CLAUDE.md, AGENTS.md, .cursorrules）。使用场景：初始化项目、迁移 Vibe Coding 配置、优化 AI Agent 项目上下文。 Use when this capability is needed.
- tomevault-io Bundle Playwright MCP UI Testing
Visual UI testing using Playwright MCP to interact with the Wavecraft web UI. Use this skill when testing UI components, verifying visual appearance, taking screenshots, or validating UI behavior that requires browser interaction. Requires the dev server running (cargo xtask dev). Use when this capability is needed.
- tomevault-io Bundle Rubakas Agent Notes Rails Testing Controllers
Testing Controllers & Integration
- tomevault-io Bundle Agent Adaptive Coordinator
Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator Use when this capability is needed.
- tomevault-io Bundle Agent Analyze Code Quality
Agent skill for analyze-code-quality - invoke with $agent-analyze-code-quality 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 swift-programming, migrate-skills-between-libraries, monocloud-auth-express. 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.