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 System Prompt EngineeringDesign effective system prompts for custom agents. Use when creating agent system prompts, defining agent identity and rules, or designing high-impact prompts that shape agent behavior. Use when this capability is needed.
- tomevault-io Bundle Microsoft Foundry Foundry Agent Webapp Reviewing Documentati
Documentation Review Guidance
- tomevault-io Bundle Laravel Extended Commands Development
Use this skill when working with mrpunyapal/laravel-extended-commands in a Laravel application. Trigger when the task involves this package's generators for actions, custom Eloquent builders, custom Eloquent collections, concerns, contracts, facades, or the extended `make:model` workflow with `--builder` or `--collection`. Teach the package conventions and generated structure, then use `php artisan help <command>` for full command syntax and options.
- tomevault-io Bundle Patrickgallucci Fabric Skills Fabric Data Agent Perf Remedia
Fabric Data Agent Performance remediate
- tomevault-io Bundle Applied Mathematics For Engineering
Applied math expert for engineering applications including Fourier analysis, transforms, and practical problem solving Use when this capability is needed.
- tomevault-io Bundle Sddevelopment Be Quickstart Agent Augmented Development Revi
Review: Architect Code Review
- tomevault-io Bundle Sddevelopment Be Quickstart Agent Augmented Development Stat
Status: Planning State Assessment
- tomevault-io Bundle Active Directory Skill
Active Directory 攻撃・検知に関する包括的な知識スキル。Kerberos 認証プロトコル、権限昇格、ドメイン間信頼悪用、LDAP 攻撃、Windows ログ分析による脅威検知など、AD セキュリティの多岐にわたるトピックをカバーしています。ELKと統合し、IT セキュリティの基盤を提供。認証フロー、権限昇格経路、永続化技術、ドメイン間信頼悪用、ログ分析検知、LDAP 操作、防御戦略の 8 つの主要機能をサポートします。 Use when this capability is needed.
- tomevault-io Bundle Sickn33 Antigravity Awesome Skills Incident Response Smart F
Intelligent Issue Resolution with Multi-Agent Orchestration
- tomevault-io Bundle Smartcontractkit Chainlink Agent Skills Chainlink Agent Skil
Chainlink Confidential AI Attester
- tomevault-io Bundle Hosted MCP Server
This skill helps create and configure hosted Model Context Protocol (MCP) server connections for OpenAI Agents SDK. Use when this capability is needed.
- tomevault-io Bundle Data Engineering Data Driven Feature
Build features guided by data insights, A/B testing, and continuous measurement using specialized agents for analysis, implementation, and experimentation. Use when this capability is needed.
- tomevault-io Bundle Performance Testing Review AI Review
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C Use when this capability is needed.
- tomevault-io Bundle Ml Model Evaluation
Evaluate machine learning models rigorously — with train/test splits, cross-validation, business metric alignment, bias detection, and production readiness assessment. Use when this capability is needed.
- tomevault-io Bundle Python MCP Server Expert
Expert assistant for developing Model Context Protocol (MCP) servers in Python using FastMCP, mcp package, Pydantic, and async patterns. Use when building MCP tools, resources, prompts, or debugging Python MCP server issues. Use when this capability is needed.
- tomevault-io Bundle Sub Memory Bootstrap
Use when the user wants to install or validate the local sub-memory project, finish project-scoped Codex MCP registration, update AGENTS.md with sub_memory usage rules, start or inspect the shared local MCP daemon, start the local web UI, or generate ready-to-paste Codex, Gemini CLI, and Claude Code config snippets.
- tomevault-io Bundle Generate Skills From Knowledge
Turn one or more knowledge documents into a provider-agnostic Agent Skills bundle (SKILL.md + examples/templates), using a plan -> apply -> lint workflow. Use when this capability is needed.
- tomevault-io Bundle Awesome Ml Sys Tutorial
本文件是 /learn agent 的 prompt 定义文件的文档版本。实际的 skill 定义文件位于 `.claude/commands/` 目录下。 Use when this capability is needed.
- tomevault-io Bundle Openrouter Model Switcher
Dynamically switch AI models from multiple providers via environment variables. Supports OpenRouter, Anthropic, OpenAI, DeepSeek, and other OpenAI-compatible APIs without code changes. Use when this capability is needed.
- tomevault-io Bundle Aaronbassett Agent Foundry Flutter Coreflutter State Managem
Flutter State Management
- tomevault-io Bundle Flutter Bloc Feature Pattern
Use when adding a new feature to a Bloc-based Flutter project (after `flutter-bloc-setup`), structuring an existing feature with a canonical event/state/bloc trio backed by `freezed` sealed states, or deciding which `bloc_concurrency` transformer (`droppable`/`restartable`/`sequential`/`concurrent`) fits an event handler.
- tomevault-io Bundle Salesforce
Use when working with Salesforce orgs — executing Apex, writing SOQL/SOSL, managing records, running tests, deploying metadata, or analyzing code. Guidance for the Salesforce MCP Server's tools, prompts, and resources.
- tomevault-io Bundle Arenukvern MCP Flutter Flutter MCP Toolkit Intentcall Migrat
<!-- @FMT_MODE_PRELUDE -->
- tomevault-io Bundle Feature Technical Spec
Define technical approach (architecture, integration points, data model) for a feature through guided Q&A and write FEATURE_TECHNICAL_SPEC.md. Use after /feature-spec. Use when this capability is needed.
- tomevault-io Bundle Waltersumbon Claude Agent Sdk Skill Claude Agent Sdk Typescr
Claude Agent SDK — TypeScript Guide
- tomevault-io Bundle Standard Team
标准开发团队总指挥剧本（11 Phase 契约驱动 + 任务级 Dev-QA Loop）。当用户需要从需求到上线完整开发一个中型应用、说"用标准团队开发"、"完整开发新应用"、"按 11 Phase 跑"时激活。主会话作为调度者，按本剧本通过 Task 工具直接派遣 12 个成员 agent，不存在中间 orchestrator agent。 Use when this capability is needed.
- tomevault-io Bundle Altimateai Data Engineering Skills Developing Incremental Mo
dbt Incremental Model Development
- tomevault-io Bundle Pi Ax Model Optimization
Nested skill should be ignored. Use when this capability is needed.
- tomevault-io Bundle Codex Deepseek Subagents
Install, update, test, or remove a cost-optimized Codex multi-agent setup where GPT stays the planner-reviewer and DeepSeek runs through a single Python runtime with visible routing, SSE events, and approved repository tools. Use when this capability is needed.
- tomevault-io Bundle Building Commands
Expert at creating and modifying Claude Code slash commands. Auto-invokes when creating/updating commands, modifying command frontmatter (model, allowed-tools, argument-hint), designing workflows, or writing to */commands/*.md files. Use when this capability is needed.
- tomevault-io Bundle Agent Introspection
AI agent 自身の failure (loop / drift / max tool call / 環境ズレ) に対する構造化 self-debug。 capture → diagnose → contained recovery → introspection report の 4 phase で、 retry blind を防ぎ human escalation の前に agent が自己修正する。 Use when this capability is needed.
- tomevault-io Bundle Alicloud AI Audio Tts Voice Design Test
Minimal voice design TTS smoke test for Model Studio Qwen TTS VD. Use when this capability is needed.
- tomevault-io Bundle D Padmanabhan Agent Engineering Handbook Documentation Stand
Documentation Standards
- tomevault-io Bundle Appforge Manager Work Pickup
Use when the manager agent needs to order actionable work. Prioritize open PRs with comments first, then In Progress issues, then Ready issues. Skip blocked or developer-waiting items.
- tomevault-io Bundle Langchain Chat Prompt Template
Guide to using ChatPromptTemplate and MessagesPlaceholder in LangChain for conversational AI. Use when building chatbots, conversational interfaces, or AI assistants that need to maintain conversation history. Use when this capability is needed.
- tomevault-io Bundle Summon The Knights Of The Round Table
Multi-model brainstorming to challenge assumptions and reach consensus. Use when needing to double-check work, validate plans, or get diverse perspectives on decisions. Invokes Claude Opus 4.6, GPT-5.3-Codex, and Gemini 3 Pro with randomized roles to debate and find common ground. 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 system-prompt-engineering, microsoft-foundry--foundry-agent-webapp--reviewing-documentation, laravel-extended-commands-development. 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.