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 Google WorkspaceGoogle Workspace MCP integration for Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, and Chat. Use when the user wants to read/send emails, manage files, create/edit documents, schedule events, or interact with any Google Workspace service. Use when this capability is needed.
-
tomevault-io Bundle Plurigrid Asi MCP OrchestratorMCP Orchestrator Skill
-
tomevault-io Bundle Signal MessagingSignal Protocol MCP server (Rust). 3 tools — encrypt, initialize_session, verify_safety_number. Bypass route when Beeper Desktop is down. Use when this capability is needed.
-
tomevault-io Bundle Human Auth Contacts DataHandle contacts, calendar, files, and notification data delegation from Human Phone. Covers data export, push to Agent Phone, and app import flows. Use when this capability is needed.
-
tomevault-io Bundle Prune ContextSelectively prune redundant lines from .agent/FULL_CONTEXT.md via AI (Gemini/Codex). Use when FULL_CONTEXT.md has grown large (500+ lines). Distinct from /compact (Claude Code built-in, which summarizes the live conversation). Use when this capability is needed.
-
tomevault-io Bundle Prompt LookupActivates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts. Use when this capability is needed.
-
tomevault-io Bundle Swift DataSwiftData persistence and data-layer architecture for iOS 26 / Swift 6.2 clinic modular MVVM-C apps. Use when writing, reviewing, or refactoring @Model entities, repository implementations, stale-while-revalidate reads, optimistic queued writes, sync/retry behavior, and SwiftUI integration that keeps SwiftData types inside Data-only boundaries. Use when this capability is needed.
-
tomevault-io Bundle Agenthub TypescriptGuidance for using the AgentHub TypeScript SDK (`@prismshadow/agenthub`). Use when developing agents that call different LLM APIs, need a unified interface for LLM providers, mention AgentHub, request `@prismshadow/agenthub`, or already import it. Use when this capability is needed.
-
tomevault-io Bundle UI ScreenshotsTake UI screenshots using agent-browser. Use this skill to capture visual state of UI components for code review, visual regression testing, or documentation. Use when this capability is needed.
-
tomevault-io Bundle Florianbuetow Claude Code StrideSTRIDE Threat Model Dispatcher
-
tomevault-io Bundle Jules APIDelegate asynchronous coding tasks to Jules (Google's AI coding agent) to maximize efficiency. Use for code reviews, refactoring, adding tests, bug fixes, and documentation. Proactively suggest Jules delegation when appropriate. Invoke when user asks to interact with Jules, create sessions, check task status, or when tasks are suitable for async delegation. Use when this capability is needed.
-
tomevault-io Bundle Openclaw ManagementThis skill should be used when the user wants to interact with OpenClaw, delegate tasks to their AI assistant, or check gateway status. Activates for AI assistant delegation and orchestration. Use when this capability is needed.
-
tomevault-io Bundle Furedea Agent Harness Rust StyleRust Coding Style Guidelines
-
tomevault-io Bundle Android SdkAndroid SDK development tools. Use for native Android. Use when this capability is needed.
-
tomevault-io Bundle API GatewayAPI Gateway pattern for routing. Use for microservices entry. Use when this capability is needed.
-
tomevault-io Bundle Objective CObjective-C for legacy iOS/macOS development with manual memory. Use for .m files. Use when this capability is needed.
-
tomevault-io Bundle Spring BootSpring Boot Java framework for microservices with auto-configuration. Use for enterprise Java. Use when this capability is needed.
-
tomevault-io Bundle Cesium QuickstartGuide users through their first interaction with the Cesium 3D globe via MCP tools Use when this capability is needed.
-
tomevault-io Bundle Agent PlatformsGuide for multi-platform skill compatibility across Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, and other AI coding agents. Use when this capability is needed.
-
tomevault-io Bundle Gologo13 Agent Skills Git CommitGit Create Commit
-
tomevault-io Bundle Gologo13 Agent Skills Lint SuiteFix Lint Issues
-
tomevault-io Bundle Secops Setup AntigravityHelps the user configure the Google SecOps Remote MCP Server for Antigravity. Use this when the user asks to "set up" or "configure" the security tools for Antigravity. Use when this capability is needed.
-
tomevault-io Bundle Activity ChannelYou have completed something significant and want the whole org — all agents and the user — to know about it. Or you need to broadcast a status update, a briefing summary, or a coordination announcement that is not directed at one specific agent. Use this skill any time the audience is the entire org rather than a single person or agent. Use when this capability is needed.
-
tomevault-io Bundle Screen RecordCapture recordings or screenshots for a window/display via the screen-record CLI (macOS 12+ and Linux). Use when this capability is needed.
-
tomevault-io Bundle TokenkrushCompresses agent instruction markdown files (CLAUDE.md, AGENTS.md, SOUL.md, GEMINI.md, memory files) using Vercel-style pipe-delimited dense format and telegraphic prose. Reduces token count ~39% (measured across Claude, GPT-5, and Gemini tokenizers) while preserving directive clarity. TRIGGER when user asks to compress, shrink, reduce tokens, optimize, or slim down any agent instruction file. Works globally (~/.claude/CLAUDE.md) or per-project (./CLAUDE.md). Use when this capability is needed.
-
tomevault-io Bundle RoboneuronControl RoboNeuron through its project-scoped MCP servers via mcporter. Use when this capability is needed.
-
tomevault-io Bundle Bmad Builderbmad-builder agent Use when this capability is needed.
-
tomevault-io Bundle Skills CreatorCreates new Claude Code skills in the .claude/skills/ directory. Specializes in designing well-structured, effective skills through thorough requirements gathering. Use when the user wants to create a new skill, command, agent, or automation.
Audited -
tomevault-io Bundle Business Model CanvasBusiness Model Canvas framework for value proposition, customer segments, revenue streams, and sustainable business model design Use when this capability is needed.
-
tomevault-io Bundle MoralisMoralis — Web3 Data API, Streams, Auth API, and Cortex (AI/MCP) for EVM and Solana. Use when this capability is needed.
-
tomevault-io Bundle ClaudrabandUse claudraband CLI and daemon workflows programmatically to send prompts, resume sessions, inspect status, and manage live session state. Use when running, scripting, or automating Claude Code via claudraband/`cband`, including startup prompt handling, `--connect` daemon mode, and ACP sessions. Use when this capability is needed.
-
tomevault-io Bundle Heyvhuang Ship Faster MCP StripeStripe MCP Transaction Skill
-
tomevault-io Bundle Prompt HelperInteractive assistant that guides users through crafting effective prompts for SiftCoder commands Use when this capability is needed.
-
tomevault-io Bundle AgentguildsAI labor marketplace on Monad — create missions, register agents, join guilds, earn MON. Full lifecycle from human requests to agent payouts. Use when this capability is needed.
-
tomevault-io Bundle Qmcp SyncManage QE Framework global MCP registry and sync shared MCP server definitions to Claude, Codex, and Gemini configs. Use when the user wants one MCP source of truth across clients. Use when this capability is needed.
-
tomevault-io Bundle WidgetkitBuild iOS/macOS/watchOS/visionOS widgets, Live Activities, watch complications, and controls using Apple's WidgetKit framework. Use when creating widget extensions, timeline providers, configurable widgets, Lock Screen widgets, Smart Stack widgets, Live Activities with ActivityKit, interactive widgets with buttons/toggles, or watch complications. Covers all widget families (systemSmall/Medium/Large/ExtraLarge, accessoryCircular/Rectangular/Inline/Corner) and rendering modes. 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 google-workspace, plurigrid--asi--mcp-orchestrator, signal-messaging. 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.