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

Arena

Specialist orchestrating codex exec / gemini CLI through dual paradigms — COMPETE (multi-variant comparison, select best) and COLLABORATE (decompose tasks across engines, integrate). Supports Solo/Team/Quick execution modes. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Judge

Automated code review agent using codex review CLI. Handles PR review automation and pre-commit checks. Detects bugs, security vulnerabilities, logic errors, and intent misalignment. Complements Zen's refactoring suggestions. Use when code review or quality checks are needed. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Nexus

専門AIエージェントチームを統括するオーケストレーター。要求を分解し、最小のエージェントチェーンを設計し、AUTORUNモードではAgent toolで各専門エージェントを実セッションとしてスポーンして最終アウトプットまで自動進行する。複数エージェント連携が必要な時に使用。 Use when this capability is needed.

Sep 17
tomevault-io Bundle

Radar

Edge-case test addition, flaky test repair, and coverage improvement. Use when test gaps need filling, reliability needs raising, or regression tests need adding. Multi-language support (JS/TS, Python, Go, Rust, Java). Use when this capability is needed.

Sep 17
tomevault-io Bundle

Rally

Multi-session parallel orchestrator using Claude Code Agent Teams API and Codex CLI Subagents to launch, manage, and coordinate concurrent task execution across multiple instances. Use when parallel work is needed. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Relay

Messaging integration, bot development, and real-time communication design+implementation agent. Handles channel adapter patterns, webhook handlers, WebSocket servers, event-driven architecture, and bot command frameworks. Use when messaging integration, bot development, or real-time communication is needed. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Sigil

Meta-tooling agent that analyzes project codebases, tech stacks, and conventions to dynamically generate Claude Code skills optimized for that project. Places skills in both .claude/skills/ and .agents/skills/ to boost dev efficiency. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Voice

ユーザーフィードバック収集、NPS調査設計、レビュー分析、感情分析、フィードバック分類、インサイト抽出レポート。フィードバックループの確立が必要な時に使用。 Use when this capability is needed.

Sep 17
tomevault-io Bundle

Psi

Plan-spec-implement workflow for structured development. Only use when explicitly directed by user or when mentioned in project AGENTS.md file. Generates ephemeral plans in ~/.dot-agent/, applies specs to project docs, then implements test-first. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Synapse

Codex-led multi-model workflow (Codex + Claude + Gemini). Use when the user asks to run `synapse <cmd> ...` to generate draft diffs/audits and persist artifacts to `./.synapse/**`. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Antfarm Workflows

Multi-agent workflow orchestration for OpenClaw. Use when user mentions antfarm, asks to run a multi-step workflow (feature dev, bug fix, security audit), or wants to install/uninstall/check status of antfarm workflows. Use when this capability is needed.

Sep 17
tomevault-io Bundle

E2e UI Fix

Fix bugs from e2e-ui:execute bug reports with Playwright MCP verification Use when this capability is needed.

Sep 17
tomevault-io Bundle

Llk Test Runner Skill

Delegates LLK test runs to the llk-test-runner agent using @.cursor/agents/llk-test-runner.md. Use when the user asks to run tests or mentions LLK tests. Ensure test commands run to completion before reading terminal output (no polling). Use when this capability is needed.

Sep 17
tomevault-io Bundle

Llmskill

Sync skills from tinywasm/devflow/skills to all installed LLM agents (Claude, Gemini). Run after creating or modifying any SKILL.md file in devflow/skills/. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Opendata API

Query the OpenData API for data research and analysis. Use when fetching dataset rows, filtering, sorting, aggregating, inspecting columns, composing cross-dataset joins, exploring graph intelligence, or building data pipelines against OpenData endpoints. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Test Ps

Test xw ps command for listing model instances Use when this capability is needed.

Sep 17
tomevault-io Bundle

Zagora

Build type-safe, error-safe functions in TypeScript with full inference, typed errors, and zero async overhead. Use when creating robust libraries or APIs where type safety and predictable error handling matter, as an alternative to plain TypeScript validation or RPC frameworks. Use when this capability is needed.

Sep 17
tomevault-io Bundle

MCP Server

This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "develop MCP tools", "implement MCP resources", or discusses building something with the Model Context Protocol. It provides comprehensive guidance for designing, creating, testing, and deploying MCP servers. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Agent Audit

Audits Claude Code agent configuration against latest best practices. Works on any project. Manual via /agent-audit. Use when this capability is needed.

Audited Sep 17
tomevault-io Bundle

Coding Agent

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Skill Report

Skill coverage and health reporting for Bosun. Use when generating skill reports, analyzing skill coverage gaps, reviewing skill health metrics, or auditing reference completeness. Also use when planning skill improvements, reporting on plugin status, checking agent-to-skill mappings, identifying orphaned skills, or measuring skill quality over time. Essential for plugin maintainers and Bosun development planning. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Create Tia Agent

Guides users through creating a new TIA XMPP agent based on mistral-minimal. Use when the user wants to create, build, set up, or scaffold a new agent, bot, or when they ask how to get started with TIA. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Dianel555 Dskills Ace Tool

ACE-Tool - Semantic Code Search & Prompt Enhancement

Sep 17
tomevault-io Bundle

Controller

Use when supervising a worker agent in another terminal. Loads MACS controller operating rules and decision priorities.

Sep 17
tomevault-io Bundle

Overseer

Manage tasks via Overseer codemode MCP. Use when tracking multi-session work, breaking down implementation, or persisting context for handoffs. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Ekadetov LLM Wiki LLM Wiki

LLM Wiki

Sep 17
tomevault-io Bundle

Stf Analysis

Analyze State Transition Function implementations for correctness, threading issues, non-determinism, and simplification opportunities. Use when analyzing STF code, checking threading model, finding non-determinism sources, or reviewing execution layer. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Add Benchmark

Use when adding or updating a benchmark adapter in the Exgentic repository. Follow the repository benchmark principles, keep the benchmark contract protocol-agnostic, prefer the thinnest possible wrapper that makes the benchmark accessible to any Exgentic agent, reuse external harness assets and scoring where possible, and validate the adapter with representative smoke tests before finishing.

Sep 17
tomevault-io Bundle

Mle Workflow

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks. Use when this capability is needed.

Sep 17
tomevault-io Bundle

MCP Tools

MCP tools for Xcode automation and Apple documentation access. XcodeBuildMCP for builds, apple-docs for WWDC and API docs. Use when building projects, searching documentation, or accessing WWDC content. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Managing MCP Servers

Provides comprehensive guidance for managing MCP (Model Context Protocol) servers using the claude mcp CLI. Covers adding servers across scopes (project, local, user), transport types (stdio, sse, http), security best practices, and common patterns. Strongly recommends project scope for team consistency and version control.

Sep 17
tomevault-io Bundle

Fysoul17 Pyx Scan Pyx Scan

PYX Scan — Agent Skill Safety Check

Sep 17
tomevault-io Bundle

Auth0

Auth0 identity platform. Use for authentication. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Caddy

Caddy automatic HTTPS web server. Use for simple web serving. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Fiber

Fiber Express-inspired Go web framework. Use for Go APIs. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Flask

Flask Python microframework with blueprints and extensions. Use for lightweight APIs. Use when this capability is needed.

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 arena, judge, nexus. 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.