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 Claude Config ManagementUse when configuring, maintaining, troubleshooting, or optimizing Claude Code extensions including skills, commands, hooks, MCP servers, or agents. Provides best practices and prevents common mistakes.
- tomevault-io Bundle Flutter MCP Toolkit Dogfood Iterations
Runs and records flutter_test_app dogfood iterations (tool_quality_rubric, run_dogfood_eval.sh, dogfood_web_eval.yaml). Use when scoring MCP/intentcall quality, appending iteration N, comparing regressions, or CI static/weekly eval gates.
- tomevault-io Bundle Phase 6 Threat Identification
Phase 6 Threat Identification guide with STRIDE methodology reference. Use when identifying threats, categorizing security issues, applying STRIDE analysis, or assessing threat severity and likelihood. Use when this capability is needed.
- tomevault-io Bundle Personalized Fitness And Nutrition Plan
This prompt instructs the AI to act as a personal trainer and, using the user’s provided demographics, location, activity level, and goal details (including optional target weight, body fat percentage, preferred foods, and output language), calculate TDEE, set a daily calorie target, estimate the timeline to reach the goal, and produce a practical daily meal plan and exercise recommendations, along with key notes to help achieve the target safely and effectively. Use when this capability is needed.
- tomevault-io Bundle MCP To Skill Converter
This skill should be used when the user asks to "convert MCP to skill", "create skill from MCP", "list MCP servers", "batch convert MCP", "generate skills from .mcp.json", or when working with MCP server configurations. Reduces context usage by 90%+ compared to native MCP loading. Use when this capability is needed.
- tomevault-io Bundle Git Merge Conflict Resolution
Resolve Git merge/rebase conflicts with explicit intent tracking and post-resolution verification. Use when conflicts occur and intent-preserving resolution is required before integration; do not use for CI workflow design or application behavior implementation. Use when this capability is needed.
- tomevault-io Bundle Langcare Langcare MCP Fhir Medication Adherence Assessment
Medication Adherence Assessment
- tomevault-io Bundle Deepagents Planning Todos
Use the write_todos tool effectively for task planning and decomposition in Deep Agents. Use when users want to (1) implement task planning with write_todos, (2) break down complex tasks into subtasks, (3) track agent progress through todos, (4) debug why todos aren't completing, (5) design todo structures for different task types (research, coding, analysis), (6) understand todo status lifecycle and best practices, or (7) visualize todo progression from LangSmith traces. Use when this capability is needed.
- tomevault-io Bundle Dynamic Prompt Registry
Dynamic prompt registry with unified categorical syntax. Supports @skills:discover(), @skills:compose(A⊗B), Reader monad for runtime lookup, and quality-tracked prompt libraries. Use for meta-prompts referencing sub-prompts, building prompt libraries, implementing deferred resolution, or composing templates dynamically. Use when this capability is needed.
- tomevault-io Bundle Langgraph Orchestration
LangGraph stateful multi-agent graphs with categorical coordination patterns and cyclic workflows. Use when building stateful AI agent systems, implementing multi-agent orchestration with conditional routing, creating cyclic workflows with persistence, or designing graph-based AI pipelines with checkpointing and human-in-the-loop patterns. Use when this capability is needed.
- tomevault-io Bundle Agent Digivolve Harness Operator
Turn a vague user request like “make this artifact better or more reliable” into a durable optimization run with fixed evaluation, baseline, one bounded mutation per round, keep-or-revert acceptance, holdout protection, and external memory on disk. Use when an agent should operate or continue a `digivolve` run, or when a prompt, skill, document, or repo task should be improved through an eval-driven iterative loop instead of one-shot edits. Use when this capability is needed.
- tomevault-io Bundle Magento Environment Engineer
Manages Magento 2 environments including development, staging, and production. Use when setting up environments, configuring servers, managing environments, or troubleshooting environment issues. Masters environment configuration, server management, and environment optimization.
- tomevault-io Bundle Magento Requirejs Specialist
Develops AMD modules using RequireJS for Magento 2. Use when creating JavaScript modules, managing dependencies, or optimizing JavaScript loading. Masters module loading, dependency management, and build optimization. Use when this capability is needed.
- tomevault-io Bundle Agent Expert Creation
Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts. Use when this capability is needed.
- tomevault-io Bundle Agent Sdk Development
Central authority for Claude Agent SDK (TypeScript and Python SDKs). Covers SDK installation, authentication (Anthropic key, Bedrock, Vertex), sessions and resumption, forking sessions, streaming vs single mode, custom tools, permissions (allowedTools, disallowedTools, permissionMode), MCP integration, system prompts (CLAUDE.md, appendSystemPrompt, outputStyle), cost tracking, todo tracking, structured outputs, hosting patterns, plugins, and SDK branding guidelines. Assists with building custom agents, configuring SDK options, and troubleshooting SDK issues. Delegates 100% to docs-management skill for official documentation. Use when this capability is needed.
- tomevault-io Bundle Composable Primitives
Design composable agentic primitives for flexible workflows. Use when creating reusable workflow building blocks, designing SDLC primitives, or building agent operations that can be combined in different ways. Use when this capability is needed.
- tomevault-io Bundle Expertise File Design
Design YAML expertise file structures for agent experts. Use when creating mental models for domain-specific agents, defining expertise schema, or structuring knowledge for Act-Learn-Reuse workflows. Use when this capability is needed.
- tomevault-io Bundle Gateway Script Design
Design gateway scripts as entry points for agentic coding. Use when creating CLI entry points for agents, designing subprocess-based agent invocation, or building script interfaces for agentic workflows. Use when this capability is needed.
- tomevault-io Bundle Gemini Context Bridge
Facilitates context sharing and strategic delegation between Claude Code and Gemini CLI. Syncs CLAUDE.md to GEMINI.md and provides agent selection guidance. Use when onboarding Gemini to a project, syncing instructions between agents, or deciding whether to use Claude or Gemini for a specific task. Use when this capability is needed.
- tomevault-io Bundle Orchestration Prompts
Write prompts for orchestrator workflows with phases and aggregation. Use when designing multi-phase workflows, writing agent command prompts, or implementing result aggregation patterns. Use when this capability is needed.
- tomevault-io Bundle Policy Engine Builder
Guide for creating Gemini CLI policy engine TOML rules. Covers rule syntax, priority tiers, conditions, and MCP wildcards. Use when restricting Gemini tools, creating security policies, controlling MCP server permissions, or setting up approval workflows. Use when this capability is needed.
- tomevault-io Bundle Product Expert Design
Design user-facing agent experts for adaptive UX and personalization. Use when building product features that learn from user behavior, creating per-user expertise files, or implementing AI-driven personalization. Use when this capability is needed.
- tomevault-io Bundle Task Based Multiagent
Set up task-based multi-agent systems with shared task files. Use when setting up parallel agent execution, designing worktree isolation patterns, or implementing task file coordination. Use when this capability is needed.
- tomevault-io Bundle Writing Csharp Code
Provides C# and ASP.NET Core coding standards for this repository. Use when writing or modifying C# code, implementing API endpoints, configuring middleware, or working with authentication in the backend.
- tomevault-io Bundle Call Web Search Agent Strategy
This skill provides specialized capabilities for call web search agent strategy. Use when this capability is needed.
- tomevault-io Bundle Modbender Skill Library MCP Langchain Chat Prompt Template
---
- tomevault-io Bundle Decision Tracing
Trace agent decision-making, tool selection, and reasoning chains Use when this capability is needed.
- tomevault-io Bundle LLM Call Tracing
Instrument LLM API calls with proper spans, tokens, and latency Use when this capability is needed.
- tomevault-io Bundle Discord Get Messages
Retrieve messages from Discord channels via the Discord API. Use this skill when the user wants to read, search, or analyze messages from a Discord channel. Use when this capability is needed.
- tomevault-io Bundle Discord Send Message
Send messages to Discord channels via the Discord API. Use this skill when the user wants to send text messages, notifications, or formatted content to a Discord channel. Use when this capability is needed.
- tomevault-io Bundle Switchbot
Use when the user mentions SwitchBot devices, smart-home automation, or asks about controlling lights, locks, curtains, sensors, plugs, or IR appliances (TV/AC/fan). Teaches the agent how to drive the authoritative `switchbot` CLI safely, read user preferences from `policy.yaml`, and respect safety tiers.
- tomevault-io Bundle Multi Agent Workforce Planner
Designs parallel agent workstreams for large feature sets by analyzing dependencies, assigning specialized agent types (Explore, Plan, Bash, Edit), maximizing parallelization, and creating execution plans with progress tracking and failure recovery. Use when breaking down large features into parallel agent work. Use when this capability is needed.
- tomevault-io Bundle Agent Ready Apis
Knowledge about AI agent API compatibility. Use when user asks about API readiness, agent compatibility, or wants to improve their API for AI consumption. Use when this capability is needed.
- tomevault-io Bundle Saeed Vayghan Gemini Agent Skills Basic Sample API Auditor
API Auditor Instructions
- tomevault-io Bundle Subagent Prompt Engineering Pattern
Claude Code Agent tool 서브에이전트 prompt 작성 패턴. 사용 시점 — "subagent prompt", "Agent tool", "claude code agent dispatch", "병렬 에이전트", "general-purpose agent", "race 대비 prompt", "보고 형식". 명확한 출력 + race 대비 + atomic commit + 보고 단어 제한. 60h 530 디스패치 검증. Use when this capability is needed.
- tomevault-io Bundle Abstract Algebra Specialist
Expert in groups, rings, fields, and algebraic structures with applications to cryptography and number theory 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 claude-config-management, flutter-mcp-toolkit-dogfood-iterations, phase-6-threat-identification. 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.