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 Tandem BrowserUse Tandem Browser's MCP server (local and remote agents) or HTTP API (local and remote agents) to inspect, browse, and interact with the user's shared browser safely. Prefer targeted tabs and sessions, use snapshot refs before raw DOM or JS, verify action completion explicitly, and leave durable handoffs instead of retrying blindly. Use when this capability is needed.
- tomevault-io Bundle Dspy Ruby
This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use this when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers (OpenAI, Google Gemini, Ollama), building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications. Use when this capability is needed.
- tomevault-io Bundle Siftcoder Workflow
Full autonomous multi-agent workflow for implementing features Use when this capability is needed.
- tomevault-io Bundle Tool Integration
Create custom tools, integrate external APIs, and manage tool registry. Use when extending agent capabilities with new tools. Use when this capability is needed.
- tomevault-io Bundle Sv Data
Build and manage Security Verifiers datasets. Use when asked to build E1 or E2 datasets, create test fixtures, validate data, or manage dataset files for network-logs or config-verification environments. Use when this capability is needed.
- tomevault-io Bundle Resume Handoff
Resume work from a handoff stored under .ai/shared/handoffs. Use when a user asks to resume a handoff, provides a handoff path, or provides a ticket ID like ENG-1234. Use when this capability is needed.
- tomevault-io Bundle Sm Domain Model
Provides SourceMonitor engine domain model context. Use when working with engine models, associations, validations, scopes, database schema, or any model-layer code in the source_monitor namespace.
- tomevault-io Bundle Agentic Voice Workflow
Building Claude Agent SDK background jobs with voice I/O. Use when creating new agents, building background jobs, implementing agentic services, adding voice notifications to agents, or integrating with RunningFifoQueue. Use when this capability is needed.
- tomevault-io Bundle Deevsdeevs Agent System Agent System
MFT Research Experts
- tomevault-io Bundle Anti AI Slop
After working on the code, ensure the branch contains only the minimal, idiomatic changes by removing AI-generated slop introduced on this branch. Use when this capability is needed.
- tomevault-io Bundle Deevsdeevs Agent System Venue Expert
Venue Expert
- tomevault-io Bundle Gmail Chrome
Automate Gmail actions using Chrome DevTools MCP - search, read, compose, reply, and manage emails Use when this capability is needed.
- tomevault-io Bundle Self Improve
Update skill documentation and extend OpenCode capabilities based on learnings Use when this capability is needed.
- tomevault-io Bundle RAG Systems
Retrieval-Augmented Generation - chunking strategies, embedding, vector search, hybrid retrieval, reranking, query transformation. Use when building RAG pipelines, knowledge bases, or context-augmented applications. Use when this capability is needed.
- tomevault-io Bundle Prompt Wizard
Interactive wizard to craft effective prompts using Claude Code best practices Use when this capability is needed.
- tomevault-io Bundle Duc01226 Easyplatform MCP Management
> **[IMPORTANT]** Use `TaskCreate` to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.
- tomevault-io Bundle Duntak1 Agentworkflow Agent Workflow
agent-workflow（运行时精简版）
- tomevault-io Bundle Build Knowledge Graph
Reverse engineer codebase architecture and build a knowledge graph using gnapsis MCP tools. Use when the user wants to map domains, features, modules, components, and their relationships. Use when this capability is needed.
- tomevault-io Bundle Agent Provisioning
Agent 시스템 프로비저닝 가이드. Dependencies 싱글톤, HTTP 클라이언트 풀링, LLM 클라이언트 설정, 환경변수 관리, Worker 초기화 패턴. "dependencies", "provisioning", "http client", "connection pool", "worker setup" 키워드로 트리거. Use when this capability is needed.
- tomevault-io Bundle Ejirocodes Agent Skills Exa Entities
Exa Entity Search
- tomevault-io Bundle Ejirocodes Agent Skills Exa Research
Exa Research & Answer API
- tomevault-io Bundle Anti Conflict
Prevent file conflicts between multiple AI agents working in parallel Use when this capability is needed.
- tomevault-io Bundle Stub Detection
Systematic detection of placeholder implementations, stubs, and hidden incomplete code. Three-pattern taxonomy with search strategies Use when this capability is needed.
- tomevault-io Bundle Abp Source Reference
Reference map for local ABP Framework, ABP Studio, and commercial module source trees. Use when working on ABP internals so the agent checks real implementations under C:\\P\\abp, C:\\P\\abp-studio, C:\\P\\volo, and C:\\P\\lepton instead of guessing. Use when this capability is needed.
- tomevault-io Bundle Subagent Artifact
Validate, diagnose, and understand subagent definitions (agents/*.md) — frontmatter format, delegation model, and vendor support across Claude Code, Cursor, and Codex. Use when this capability is needed.
- tomevault-io Bundle Forge MCP Server
Designing an MCP server LLM agents actually use well. Transport choice (stdio vs HTTP streaming), capability scoping, structured error responses the model can recover from, tool count limits, telemetry, auth, versioning. Contains ready-to-paste stdio server skeleton + remote HTTP server pattern. Use when building an MCP server that exposes tools/resources/prompts to Claude, Cursor, Codex, or any MCP client. Use when this capability is needed.
- tomevault-io Bundle Evaluate Agent
Statically lint a Claude Code agent or skill file against a citation-backed rule set (frontmatter, description, tool hygiene, model fit, body structure, anti-patterns). Use proactively before merging any change to .claude/agents/ or any SKILL.md. Use when an agent is misbehaving or the team adds a new specialist. Use when this capability is needed.
- tomevault-io Bundle Dotclaude Config
Work with Claude Code configuration at global (~/.claude) or project (.claude/) level. Use when editing settings.json (permissions, hooks, statusline, model), managing MCP servers, creating agents/commands/skills, writing CLAUDE.md, setting up rules files, or configuring a new project. Determines context automatically and provides guidance on global vs project placement to avoid duplication. Use when this capability is needed.
- tomevault-io Bundle MCP Web Agent Docs
Review and update agent documentation and skills in `./agents/` related to MCP-Web. Use when this capability is needed.
- tomevault-io Bundle Code Safety
Scan LLM-generated code for security vulnerabilities using language-aware pattern rules Use when this capability is needed.
- tomevault-io Bundle Agent Orchestration
This skill provides battle-tested patterns for orchestrating multiple AI agents to solve complex problems collaboratively. Use when this capability is needed.
- tomevault-io Bundle Frankxai Arcanea V3 MCP Optimization
---
- tomevault-io Bundle Yahoo Finance2
Use when building with the yahoo-finance2 TypeScript/Deno/npm library, using its Yahoo Finance data modules, CLI, or MCP server, or contributing to the yahoo-finance2 repository including modules, validation schemas, cached fixtures, and npm/JSR build output.
- tomevault-io Bundle Parallel Extract
URL content extraction via Parallel API. Extracts clean markdown from webpages, articles, PDFs, and JS-heavy sites. Use for reading specific URLs with LLM-ready output. Use when this capability is needed.
- tomevault-io Bundle Langchain Core
Use this skill when working with LangChain chains, prompts, LCEL, output parsers, message history, or model integrations. Triggers when code imports from langchain_core, langchain_aws, langchain_anthropic, langchain_community, or uses the pipe operator to compose chains. Also triggers on mentions of "LCEL", "runnable", "prompt template", "output parser", or "message history".
- tomevault-io Bundle LLM Council
Multi-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an implementation plan, or asks to "consult the council", "ask other models", or "get perspectives from other AIs". Queries external LLM APIs, synthesizes their perspectives, and presents an adapted implementation plan. 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 tandem-browser, dspy-ruby, siftcoder-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.