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 Hissal Agent Plugins Repo SetupRepo Setup Skill
- tomevault-io Bundle Hive MCP
Use this skill when installing, configuring, or debugging Hive MCP in an AI client such as Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Gemini CLI, the OpenAI Responses API, or Codex CLI.
- tomevault-io Bundle Hjemmesidekongen AI MCP Creator
MCP Creator
- tomevault-io Bundle Cursor Rules
Project, user, and team rules that the Cursor SDK and Agent load — `.cursor/rules/*.mdc`, `AGENTS.md`, and the legacy `.cursorrules`. Use when authoring rules that the SDK will pick up via `local.settingSources`, or when writing rule frontmatter with the right type (always / auto-attached / agent-requested / manual). Use when this capability is needed.
- tomevault-io Bundle Create Eval
This skill should be used when the user asks to "create an eval", "write an eval test", "add a new eval", "create a test case", "write a test for Holmes", or discusses LLM evaluation tests, eval fixtures, or test_case.yaml files for the HolmesGPT project. Use when this capability is needed.
- tomevault-io Bundle Huggingface Diffusers Diffusers
Goal
- tomevault-io Bundle Coral New Task
End-to-end recipe for adding a new task under `examples/` — the three pieces that have to line up (`task.yaml`, `seed/`, and `grader/`), what to put in each, the `TaskGrader` API surface, the `coral validate` → smoke-test loop, and the common mistakes (repo_path pointing at the wrong dir, score direction backwards, hidden answer keys leaking into seed/, grader writing to codebase_path which the daemon force-removes, private-vs-public confusion, missing `run()` signature). Use whenever the user wants to add a new CORAL task or port an existing benchmark into CORAL. Use when this capability is needed.
- tomevault-io Bundle Groundwork
Set up and maintain state of the art context engineering for a new or existing project. Use this skill whenever the user wants to bootstrap a repo for AI-first development, write or improve a CLAUDE.md / AGENTS.md / .cursor/rules/ file, audit a project's "AI readiness", plan a non-trivial change before coding, author an ADR, scope rules to specific file patterns, design an MCP server with least-privilege access, or bake verification loops (tests, linters) into the AI's context. Also trigger when the user says "context engineering", "ContextOps", "AI-first repo", "cognitive debt", "plan mode", "negative space", or asks how to make a codebase work well with Claude Code, Cursor, Codex, or Copilot. Prefer this skill over ad-hoc prompting whenever the artifact being produced is something an AI agent will read on future runs. Use when this capability is needed.
- tomevault-io Bundle Scrapling
Web scraping with anti-bot bypass (Cloudflare Turnstile etc.), stealth headless browsing, adaptive selectors, and concurrent crawls. Use when the user asks to scrape, crawl, or extract data from websites; the built-in WebFetch fails; the target has anti-bot protections; or the work needs JavaScript rendering. Prefers the registered MCP tools (mcp__scrapling__*) over raw Python so token cost stays low. Use when this capability is needed.
- tomevault-io Bundle IOS Agent Iosagent Dev App Clip
Apple App Clip Skill
- tomevault-io Bundle Itechmeat LLM Code Skill Master
Skill Master
- tomevault-io Bundle API Integration
Master third-party API integration in ANY language with best practices and patterns Use when this capability is needed.
- tomevault-io Bundle Debug Detective
Systematic debugging approach for ANY codebase, ANY language, ANY bug type Use when this capability is needed.
- tomevault-io Bundle Japboy Dotfiles Creating Skills
Creating Agent Skills
- tomevault-io Bundle Joaquincampo Ml Ralph Old Ralph
Ralph - Autonomous ML Agent
- tomevault-io Bundle Beadboard Driver
Use when an agent is executing work in any project repo and needs to coordinate with a human or other agents via BeadBoard. BeadBoard is the human-facing dashboard running separately; this skill is the agent-side operating contract for state, mail, assignment, and evidence flow.
- tomevault-io Bundle Bat Adhoc
Run bot acceptance tests to validate MCP tools work correctly from a real AI agent's perspective. Use when testing PRs, detecting regressions, or verifying tool changes end-to-end with Claude/Gemini CLIs. Use when this capability is needed.
- tomevault-io Bundle Sub Agent Review
Review Claude Code sub-agent implementations for best practices in configuration, tool access, hooks, and delegation patterns. Use when creating, auditing, or optimizing sub-agents. Use when this capability is needed.
- tomevault-io Bundle Manifold API
Use when an agent needs to inspect or call the local Manifold HTTP API. Provides guidelines and scripts to filter specs before reading and handle payloads safely.
- tomevault-io Bundle IOS Agent Iosagent Dev Tap To Pay
Tap to Pay on iPhone — Skill
- tomevault-io Bundle Open AI Town
Use when working with a virtual world where AI agents live, chat, and socialize. Join as an external agent via HTTP API.
- tomevault-io Bundle Dependency Doctor
Diagnose and heal dependency issues in ANY package manager, ANY language. Use when facing version conflicts, security vulnerabilities, or dependency bloat. Use when this capability is needed.
- tomevault-io Bundle J4flmao Agent Skills Git Workflow
Git Workflow
- tomevault-io Bundle Prompt Brevity Review
Review AI prompts and instructions for conciseness and clarity. Use when reviewing skills, CLAUDE.md, slash commands, or any LLM prompt content. Use when this capability is needed.
- tomevault-io Bundle Jau123 Meigen AI Design MCP Setup
MeiGen Plugin Setup
- tomevault-io Bundle Clawdbot Release Check
Check for new OpenClaw releases and notify once per new version. Use when this capability is needed.
- tomevault-io Bundle Vibe Agent Toolkit
Use when building, adopting, or learning vibe-agent-toolkit (VAT). Covers agent creation, CLI commands (vat skills, vat resources, vat audit, vat rag), runtime adapters, skill packaging, and resource validation. Routes to specialized sub-skills.
- tomevault-io Bundle Schwab Data Sweep
Collect a single Schwab MCP data snapshot (accounts, quotes, indicators, option chains) with a five-minute cache so trading agents can reuse consistent inputs. Use whenever an options persona needs fresh risk, market, or chain data before recommending trades. Use when this capability is needed.
- tomevault-io Bundle Fastmcp Client CLI
Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server offers, call tools, or integrate MCP servers into workflows. Use when this capability is needed.
- tomevault-io Bundle Delegation
Agent delegation best practices for constructing effective subagent prompts with proper scoping Use when this capability is needed.
- tomevault-io Bundle Jph4cks Redhound Arsenal Impacket
impacket Agent Skill
- tomevault-io Bundle Copy Agent
Copy an agent from Product Forge to user or project level Use when this capability is needed.
- tomevault-io Bundle Prompt Engineering
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
- tomevault-io Bundle Interview Me
Use this skill to analyze underspecified requests through a short interview and surface missing tradeoffs, assumptions, and approval gates before implementation when a prompt is underdefined and guessing would be risky.
- tomevault-io Bundle Zotero MCP Code
Search Zotero library using code execution for efficient multi-strategy searches without crash risks. Use this skill when the user needs comprehensive Zotero searches with automatic deduplication and ranking. Use when this capability is needed.
- tomevault-io Bundle Spawn Agent
Spawn worker agents (Gemini CLI or Codex CLI) to keep main context clean. Use for implementation, codebase research, context gathering, or any scoped work that would pollute the orchestrator's context. 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 hissal--agent-plugins--repo-setup, hive-mcp, hjemmesidekongen--ai--mcp-creator. 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.