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 Brainstorming IdeasAI agent generates diverse solutions through structured divergent thinking and systematic exploration frameworks. Use when exploring options, solving problems creatively, or generating alternatives. Use when this capability is needed.
- tomevault-io Bundle Feature Flags And Progressive Delivery
Use when working with the agent implements feature flag systems for trunk-based development, canary releases, and A/B testing. Use when implementing gradual rollouts, kill switches, or experiment-driven development.
- tomevault-io Bundle Stacked Diffs Workflow
Use when working with the agent implements stacked diffs (stacked PRs) for breaking large changes into reviewable chunks. Use when working on complex features, managing dependent changes, or optimizing code review flow.
- tomevault-io Bundle Vib3 Create
VIB3+ creative engine for gaming VFX, multi-scene performances, AI-driven presets, trading cards, and audio-reactive experiences. Leverages 31 MCP tools, WebGPU compute particles, AI preset generation, choreography engine, Three.js integration, and C++ WASM 4D math core. Use when this capability is needed.
- tomevault-io Bundle Vib3 Design
VIB3+ visualization design and navigation. Use when creating 4D visualizations, designing presets, choreographing animations, configuring audio-reactive visuals, or answering "how do I make it look like X" questions. Integrates with VIB3+ MCP server for real-time control. Use when this capability is needed.
- tomevault-io Bundle Bootstrap Agent Config
Generate a high-quality project CLAUDE.md and AGENTS.md by inspecting the current repository. Use when a repo has no agent config, when onboarding a new project, or when the user asks to "set up Claude/Codex for this repo" or "write a CLAUDE.md". Detects languages, build/test commands, and structure, then drafts config grounded in what's actually there. Use when this capability is needed.
- tomevault-io Bundle AI Testing
Use when working with an AI tool for automated testing, focusing on output quality, reliability, user trust, regulatory compliance, and security. Use this skill to prevent injection attacks, ensure system integrity, and protect data by integrating LLM-based systems into the Deepeval Framework, running test cases, and generating structured fact-check reports.
- tomevault-io Bundle Handoff Workflow
Hand off work to another agent with full context and documentation Use when this capability is needed.
- tomevault-io Bundle Claude Code Team
Asynchronous Claude Code Agent Teams with session management and multi-channel notifications (Feishu, Discord, Telegram). Use when this capability is needed.
- tomevault-io Bundle Clerk Token Ops
Automates Clerk JWT token generation, validation, and export for FastAPI integration tests. Use when an agent must refresh tokens, verify JWT templates, or unblock authentication workflows without breaking environment state.
- tomevault-io Bundle Adk Expert
Use when working with an expert AI developer with in-depth knowledge about the Agent Development Kit (ADK) SDK.
- tomevault-io Bundle Work Items
Optimize and analyze work items for LLM-assisted development Use when this capability is needed.
- tomevault-io Bundle Pufferlib
This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs. Use when this capability is needed.
- tomevault-io Bundle Faiss
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications. Use when this capability is needed.
- tomevault-io Bundle Dawsonblock Vsagent Agent Customization
Agent Customization
- tomevault-io Bundle Fact Checker
Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements. Use when this capability is needed.
- tomevault-io Bundle Aieos
AIEOS (AI Entity Object Specification) is a standardization framework designed to solve the "identity crisis" currently facing AI agents. Combined with Soul Documents, together they form a comprehensive blueprint for AI behavior. The goal is to establish a standardized data structure that defines exactly how an agent speaks, reacts, and remembers. This allows developers, and agents themselves, to construct specific personas with the portability to move across different ecosystems without losing their behavioral integrity. As we move toward a world of "Agentic Workflows," AIEOS ensures that agents maintain consistent traits regardless of the underlying model. By treating personality as a deployable asset rather than a fragile prompt, we are providing the "DNA kit" for the next generation of digital entities. Use when this capability is needed.
- tomevault-io Bundle Clawcourt
Use when working with the First Sovereign AI Agent Democracy & Judiciary. A protocol for autonomous agent governance, dispute resolution, and legislative deliberation.
- tomevault-io Bundle Design Audit
UI/UX design audit with Steve Jobs and Jony Ive design philosophy Use when this capability is needed.
- tomevault-io Bundle Nodejs Specialist
Node.js expertise — patterns for building APIs, middleware, and server-side logic using Express, Fastify, or Node.js built-ins. Covers async patterns, streams, error handling, and TypeScript on the server. Use when this capability is needed.
- tomevault-io Bundle Workspace Guide
Workspace guide to introduce OpenWork and onboard new users. Use when this capability is needed.
- tomevault-io Bundle Digitarald MCP Apps Playground MCP Apps
MCP Apps Development
- tomevault-io Bundle API Radar
Analyzes REST API endpoints in any GitHub repository (read-only) and generates structured API documentation as Endpoint Reference Cards. Supports Django, FastAPI, Express, NestJS, Spring and more. Find endpoints by path, keyword, or natural language — or analyze API changes in PRs, commits, and branches.
- tomevault-io Bundle AI Engineering
Building production AI applications with Foundation Models. Covers prompt engineering, RAG, agents, finetuning, evaluation, and deployment. Use when working with LLMs, building AI features, or architecting AI systems. Use when this capability is needed.
- tomevault-io Bundle AI Integration
AI/ML model integration including vision, audio, embeddings, and RAG implementation patterns Use when this capability is needed.
- tomevault-io Bundle Add Logging
Triggered when user asks to add structured logging, set up error tracking, implement monitoring, or configure observability. Automatically delegates to the logging-specialist agent. Use when this capability is needed.
- tomevault-io Bundle CLI Tools
Master Shopify CLI and developer tools. Use this skill for using Shopify CLI commands, theme development workflow, app development workflow, debugging with Theme Check, using the Liquid language server, and configuring development environments. Covers VS Code extension and development best practices. Use when this capability is needed.
- tomevault-io Bundle Mixseek Model List
MixSeek-Coreで利用可能なLLMモデルの一覧を表示します。「使えるモデル」「モデル一覧」「どのモデルがある」「モデルを取得」「APIからモデル」といった依頼で使用してください。API経由でプロバイダー別のモデル情報を動的取得し、推奨設定、互換性情報を提供します。 Use when this capability is needed.
- tomevault-io Bundle Git Convention
Generate conventional git commit messages following Angular convention format. Use this skill when creating commits, writing commit messages, or reviewing git history. Triggers include "git commit", "commit message", "changelog", or requests to version control changes. Use when this capability is needed.
- tomevault-io Bundle Dungle Scrubs Agent Config TS Standards
TypeScript Best Practices
- tomevault-io Bundle Flutter Copilot
连接 Flutter Copilot MCP，支持自动读取 VM Service URI、截图、交互、热重载，以及需要重启时自动调用脚本重连 Use when this capability is needed.
- tomevault-io Bundle Hook Methodology
Generates conversion-focused ad copy through research-first extraction. Creates unique hook concepts by mining EVERY section of the research document. Use when creating Meta ads, conversion campaigns, or scroll-stopping copy.
- tomevault-io Bundle Mern Add Feature
Scaffold a new feature with API route, Zod schema, Mongoose model, and UI components. Use when this capability is needed.
- tomevault-io Bundle Claude Code Doc
Quick access to Claude Code official documentation. Use when you need to reference Claude Code features, setup, configuration, plugin development, MCP integration, hooks, subagents, deployment options, or troubleshooting. Use when this capability is needed.
- tomevault-io Bundle Erich3000 Ji Agent Skills Todo Creation
todo-creation
- tomevault-io Bundle Trello Import
This skill should be used when the user asks to "import Trello boards", "convert Trello JSON to Markdown", "generate Obsidian notes from Trello", or has placed Trello JSON exports at the repository root. Converts Trello board JSON exports into browsable Obsidian Markdown notes organized by board, list, and card. 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 brainstorming-ideas, feature-flags-and-progressive-delivery, stacked-diffs-workflow. 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.