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 Cao Supervisor ProtocolsSupervisor-side orchestration patterns for assign, handoff, and idle inbox delivery in CAO Use when this capability is needed.
- tomevault-io Bundle Flutter Form Handling
Implements form state management and validation in Flutter with Riverpod. Trigger this skill whenever the user says "build a form", "form validation", "text field", "submit button", "multi-step form", "conditional field", "form ekranı", "doğrulama", "validate input", "input field", or any request to collect user input. Covers the Riverpod form state model, TextFormField validator chain, async validation with debounce, conditional fields, submit flow with loading state, keyboard FocusNode chain, and after-submit navigation. Pairs with flutter-error-handling for displaying submission errors and flutter-page-creation for the surrounding page structure. Use when this capability is needed.
- tomevault-io Bundle Defi Threat Model
Produce structured DeFi threat models covering actors, trust assumptions, attacker goals, and critical attack surfaces. Use during design or before audits and invariant work for protocols and integrations. Use when this capability is needed.
- tomevault-io Bundle AI Agent Manager Playbook
Your company deployed AI agents. Now what? This skill turns you Use when this capability is needed.
- tomevault-io Bundle Nanmicoder Claude Code Skills Agent Team Orchestrator
Agent Teams 智能编排决策引擎
- tomevault-io Bundle Omer Metin Skills For Antigravity Agent Communication
---
- tomevault-io Bundle Agent Swarm Orchestrator
Designs multi-agent systems with coordinated agent swarms, task distribution, inter-agent communication, and emergent collective behavior. Use when this capability is needed.
- tomevault-io Bundle MCP Integration Patterns
Builds MCP (Model Context Protocol) servers and clients for extending AI assistants with custom tools, resources, and prompts.
- tomevault-io Bundle Paiml Paiml MCP Agent Toolkit Paiml MCP Agent Toolkit
PMAT Multi-Language Project Analysis Skill
- tomevault-io Bundle Domain Model Boundaries Mapper
Identifies domain modules, ownership boundaries, dependencies, and interfaces using Domain-Driven Design principles. Provides domain maps, bounded contexts, refactor recommendations. Use for "DDD", "domain modeling", "bounded contexts", or "service boundaries". Use when this capability is needed.
- tomevault-io Bundle Ask User Questions
Ask clarifying questions to users via interactive TUI. Use when you need user input on preferences, implementation choices, or ambiguous instructions. Use when this capability is needed.
- tomevault-io Bundle Convex Workos
WorkOS AuthKit authentication integration for Convex. Use when setting up WorkOS AuthKit, configuring ConvexProviderWithAuthKit, handling auto-provisioning, or troubleshooting WorkOS-specific auth issues. Use when this capability is needed.
- tomevault-io Bundle Documentation Verification
Validate documentation before merging - check completeness, broken links, code example accuracy, and factual correctness. Use when reviewing docs for quality gates or running pre-merge doc validation. Use when this capability is needed.
- tomevault-io Bundle Verification Quality
Verifies agent outputs against expected results and validates code changes pass quality checks before merge. Use when verifying agent outputs are correct, validating code changes before merge, or configuring automatic rollback for failed quality checks. Use when this capability is needed.
- tomevault-io Bundle Qredence Agentic Fleet Dspy Agent Framework Quick Ref
DSPy + Agent Framework Quick Reference
- tomevault-io Bundle Contextarchitect
Audit and optimize agent context files across Claude Code and OpenAI Codex. Covers CLAUDE.md, AGENTS.md, rules, skills, and memory organization. USE WHEN "optimize context" OR "audit setup" OR "context architecture" OR "where should this go" OR "reduce duplication" OR "context budget" OR "too many tokens" OR "reorganize rules" OR "skill hierarchy" OR "CLAUDE.md too big" OR "AGENTS.md too big" OR "optimize skills". Based on Gloaguen et al. 2026 research, Anthropic best practices, and OpenAI Codex docs. Use when this capability is needed.
- tomevault-io Bundle Domain Model Generator
Use when creating or modifying domain model types (Aggregate, Entity, VO, Enum, Exception) in the domain module. No Lombok, minimal API surface.
- tomevault-io Bundle Saeed Vayghan Gemini Agent Skills Performance Monitor
You are a senior performance monitoring specialist with expertise in observability, metrics analysis, and system optimization. Your focus spans real-time monitoring, anomaly detection, and performance insights with emphasis on maintaining system health, identifying bottlenecks, and driving continuous performance improvements across multi-agent systems.
- tomevault-io Bundle Etymology And Word Origins Expert
Expert in word etymology, historical linguistics, and the development of language families Use when this capability is needed.
- tomevault-io Bundle Kanji Etymology And Learning Expert
Kanji specialist covering character origins, radical systems, mnemonic techniques, and historical development Use when this capability is needed.
- tomevault-io Bundle Number Theory Explorer
Number theory expert covering primes, divisibility, modular arithmetic, Diophantine equations, and cryptographic applications Use when this capability is needed.
- tomevault-io Bundle Refactoring Specialist
Code refactoring expert for improving code quality, reducing technical debt, and safe transformations Use when this capability is needed.
- tomevault-io Bundle Testing Strategy Guide
Test automation expert covering unit tests, integration tests, TDD, and testing best practices Use when this capability is needed.
- tomevault-io Bundle Search Console MCP
Expert skill for installing, configuring, and troubleshooting the Search Console MCP server. Use when this capability is needed.
- tomevault-io Bundle Agent Skill Copilot Instructions
Create GitHub Copilot custom instructions files (.instructions.md and copilot-instructions.md) tailored to a repository, language, framework, platform, or concern. Use when asked to create custom instructions, write copilot instructions, create .instructions.md files, set up copilot-instructions.md, configure Copilot for a project, add path-specific instructions, write coding guidelines for Copilot, or customize Copilot behavior for a repository. Use when this capability is needed.
- tomevault-io Bundle Adaptive Workflows
Self-learning workflow system that tracks what works best for your use cases. Records experiment results, suggests optimizations, creates custom templates, and builds a personal knowledge base. Use to learn from experience and optimize your LLM workflows over time. Use when this capability is needed.
- tomevault-io Bundle Unsloth MCP Server
Work with the Unsloth MCP Server codebase. Use when maintaining, extending, or debugging this specific MCP server implementation. Provides architecture knowledge, code patterns, and development workflows. Use when this capability is needed.
- tomevault-io Bundle Sdcorejs Clarify Requirements
Use AFTER `sdcorejs-brainstorm` has settled direction (or skip brainstorm if scope was already clear), BEFORE `sdcorejs-write-spec`. Hard-confirms the blocking inputs for the detected track — angular-portal (module / entity / fields / layout / workflow), nestjs (module / entity / persistence / transactions), nextjs (domain / contact / hosting / languages / OG / caching). Each unanswered blocker prevents the spec stage. Triggers - "tạo CRUD cho ...", "thêm entity", "create screen", "build module", "set up backend module", "tạo landing page với ...", or any request missing concrete inputs for the track. Applies to angular-portal, nestjs, nextjs. Bilingual (VI/EN). Use when this capability is needed.
- tomevault-io Bundle Compliance Checklist Generation
Generate compliance checklists for SOC2, HIPAA, PCI-DSS, and GDPR with gap analysis and remediation priorities. Use when this capability is needed.
- tomevault-io Bundle Humanlike Chat Timing
Psychological principles and implementation patterns for AI chat interfaces that feel natural and engaging. Covers Weber-Fechner timing, beta-distribution delays, character-by-character typing simulation, and model response padding. Use when this capability is needed.
- tomevault-io Bundle M3 Web Webcomponents
Implement Material Design 3 using Google's official @material/web library — Lit-based web components. Framework-agnostic, works with any framework that supports Custom Elements. Use this when you want the official M3 implementation or need cross-framework components. Use when this capability is needed.
- tomevault-io Bundle Donggri Gemini CLI Operations
Use when Donggri tasks involve Gemini CLI, Gemini Code Assist, MCP workflows, Google provider readiness, quota checks, or safe Gemini-based agent handoffs from Codex.
- tomevault-io Bundle Sickn33 Antigravity Awesome Skills Cal Com Automation
Cal.com Automation via Rube MCP
- tomevault-io Bundle MCP Tool Developer
Build Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing, deployment, and registry publishing. Use when this capability is needed.
- tomevault-io Bundle Structured Logging
This skill should be used when the user asks to "analyze data with SQLite", "query logs", "find patterns in test results", or "correlate errors across files". Automatically activates when parsing large output (>100 lines), correlating data from multiple sources, tracking state across operations, aggregating results (counts, averages, grouping), or querying the same dataset multiple times. Not for tiny datasets (<50 records) with a single simple query. Use when this capability is needed.
- tomevault-io Bundle Extensibility Advisor
Advises on choosing the right Claude Code extensibility approach (Skills, Commands, Subagents, Hooks, Plugins, MCP, Output Styles). Activates when user discusses extending Claude Code, creating automation, or is unsure which feature to use. Analyzes use cases and recommends appropriate solutions with trade-off explanations. Use when user mentions "should I use", "what's the best way", "skill or command", "which approach", or discusses extensibility options. 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 cao-supervisor-protocols, flutter-form-handling, defi-threat-model. 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.