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

Dependency Check

Check for required dependencies (Chrome DevTools MCP, OpenRouter API) before running commands that need them. Use at the start of /implement, /review, /validate-ui commands to provide helpful setup guidance. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Harness Prompt

Create and manage the system prompt entity in agent-harness, generating CLAUDE.md, AGENTS.md, and copilot-instructions.md from a single canonical source. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Harmonyos App

HarmonyOS application development expert. Use when building HarmonyOS apps with ArkTS, ArkUI, Stage model, and distributed capabilities. Covers HarmonyOS NEXT (API 12+) best practices. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Convert Cc Defs

Use when importing, converting, or syncing agent, skill, or command definitions from CEP or other Claude Code-format sources into the Systematic plugin for OpenCode. Triggers on "import from CEP", "sync upstream", "convert CC definition", "add agent/skill/command from upstream", or when updating existing bundled definitions from upstream sources.

Sep 17
tomevault-io Bundle

Mark64oswald Healthsim Agent Patientsim

PatientSim - Clinical Patient Data Generation

Sep 17
tomevault-io Bundle

RAG Security

Review a retrieval augmented generation system for ingestion poisoning, retrieval boundary failures, insecure chunking and metadata handling, document trust confusion, and cross-tenant or stale-context exposure across any language or framework. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Mauromedda Agent Toolkit Web Automation

ABOUTME: Claude Code skill for web automation, debugging, and E2E testing using Playwright

Sep 17
tomevault-io Bundle

Synthesize Session

Terminal phase of the SDD lifecycle — runs once per session after /substrate:execute archives a spec, before the human moves on. Captures non-obvious session learning that the spec/commit format can't carry, and converts it into either immediate doctrine fixes (atomic commits, capped at 5), queued doctrine amendments (for human triage), or filed beads with state-transfer prompts so a fresh Claude Code agent can pick the work up cold. Idempotent — re-running on a session already synthesized is a no-op. Skipping it is allowed; what gets lost is the ephemeral chat-only learning. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Oh My Opencode

Multi-agent orchestration plugin for OpenCode. Use when the user wants to install, configure, or operate oh-my-opencode — including agent delegation, ultrawork mode, Prometheus planning, background tasks, category-based task routing, model resolution, tmux integration, or any oh-my-opencode feature. Covers installation, configuration, all agents (Sisyphus, Oracle, Librarian, Explore, Atlas, Prometheus, Metis, Momus), all categories, slash commands, hooks, skills, MCPs, and troubleshooting. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Mhlavac Claude Marketplace Agent Create

agent:create

Sep 17
tomevault-io Bundle

Gc Config Init

Bootstrap a best-practice GitHub Copilot Coding Agent configuration for a new or unconfigured project. Use when a user asks to set up GitHub Copilot, create copilot-instructions.md, or configure GitHub Copilot for the first time. Also use when the user says things like "set up my Copilot config", "bootstrap Copilot", or "initialize GitHub Copilot". Grounded in official GitHub Copilot Coding Agent best practices. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Sync Agent Briefs

Sync the repo's agent-orientation files after structural or meaningful codebase changes. Use when commands, workflows, integrations, environment variables, architecture, layout, or other durable project facts change, or when finalizing meaningful work that may require AGENTS.md, CLAUDE.md, and GEMINI.md updates. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Mikecubed Agent Orchestration Conductor

Conductor — Composable Code Codex Orchestrator

Sep 17
tomevault-io Bundle

Shubhamsaboo Awesome LLM Apps Debugger

Debugger

Sep 17
tomevault-io Bundle

Workspace Architect

Specialized agent for workspace end-to-end (E2E) implementation, focusing on file system alignment, permission hardening, and AI integration across IDE, Notes, and Knowledge workspaces. Use this skill when implementing workspace file system strategies, auditing FSA permission models, creating agent tool permission matrices, or handling concurrent file access. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Unifi Network Setup

Configure the UniFi Network MCP server for Claude Code, Codex, or OpenClaw — set controller host, credentials, and permissions Use when this capability is needed.

Sep 17
tomevault-io Bundle

Unifi Protect Setup

Configure the UniFi Protect MCP server for Claude Code, Codex, or OpenClaw — set NVR host, credentials, and permissions Use when this capability is needed.

Sep 17
tomevault-io Bundle

Orchestrationcreating Workflows

Use when user says "create workflow", "create a workflow", "design workflow", "orchestrate", "automate multiple steps", "coordinate agents", "multi-agent workflow". Creates orchestration workflows from natural language using Socratic questioning to plan multi-agent workflows with visualization.

Sep 17
tomevault-io Bundle

Crewai Developer

Comprehensive CrewAI framework guide for building collaborative AI agent teams and structured workflows. Use when developing multi-agent systems with CrewAI, creating autonomous AI crews, orchestrating flows, implementing agents with roles and tools, or building production-ready AI automation. Essential for developers building intelligent agent systems, task automation, and complex AI workflows. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Difficult Workplace Conversations

Structured approach to workplace conflicts, performance discussions, and challenging feedback using preparation-delivery-followup framework. Use when preparing for tough conversations, addressing conflicts, giving critical feedback, or navigating sensitive workplace discussions. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Specstory Yak

Analyze your SpecStory AI coding sessions in .specstory/history for yak shaving - when your initial goal got derailed into rabbit holes. Run when user says "analyze my yak shaving", "check for rabbit holes", "how distracted was I", or "yak shave score". Use when this capability is needed.

Sep 17
tomevault-io Bundle

Agent Coordination

Coordination protocol for main Claude Code agent. Explicit user invocation required ("mobilize agents", "coordinate", "check registry"). Provides agent orchestration, registry management, and handoff protocols. Subagents never access this - main agent provides context in task prompts. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Build Agent Team

Designs a long-running, autonomous Claude Code agent team for the current project, then writes a /start-<team>-team skill that spawns it. Use when the user asks to build an agent team, multi-agent system, agent crew, agent squad, agent fund, agent org, or wants multiple agents running together with shared tasks and inter-agent messaging — even when they don't use the words "agent team". Pairs with Claude Code's experimental agent teams (CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1). Produces a skill, not the team itself; the produced skill spawns the team. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Super Agent AI Tmux Agents Tmux Agents

tmux-agents CLI Skill

Sep 17
tomevault-io Bundle

Context7 Docs

Fetch latest framework/library docs Use when this capability is needed.

Sep 17
tomevault-io Bundle

Mega Research

6-API integrated research system Use when this capability is needed.

Sep 17
tomevault-io Bundle

Research Free

API-free integrated research Use when this capability is needed.

Sep 17
tomevault-io Bundle

Type Migration

Migrate Python code from loose typing to strict typing standards. Use when refactoring code to eliminate Any, add TypedDict, or improve type safety. Use when this capability is needed.

Sep 17
tomevault-io Bundle

C4 Container

Expert C4 Container-level documentation specialist. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Fal Generate

Generate images and videos using fal.ai AI models Use when this capability is needed.

Sep 17
tomevault-io Bundle

Fal Platform

Platform APIs for model management, pricing, and usage tracking Use when this capability is needed.

Sep 17
tomevault-io Bundle

Fal Workflow

Generate workflow JSON files for chaining AI models Use when this capability is needed.

Sep 17
tomevault-io Bundle

Nosql Expert

Expert guidance for distributed NoSQL databases (Cassandra, DynamoDB). Focuses on mental models, query-first modeling, single-table design, and avoiding hot partitions in high-scale systems. Use when this capability is needed.

Sep 17
tomevault-io Bundle

PDF Official

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmaticall... Use when this capability is needed.

Sep 17
tomevault-io Bundle

Pypict Skill

Pairwise test generation Use when this capability is needed.

Sep 17
tomevault-io Bundle

Techwavedev Agi Agent Kit RAG Engineer

RAG Engineer

Sep 17

Frequently asked questions

What are AI & ML agent skills?

Which AI & ML skills are most installed?

Popular AI & ML skills on SkillMD right now include dependency-check, harness-prompt, harmonyos-app. 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.