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 Feature Dev约束 Agent 必须遵循结构化的功能特性开发流程：理解需求 → 技术设想 → 编写代码 → 自验自测。 Use when this capability is needed.
- tomevault-io Bundle Data Model
Design database schemas with migrations and repository interfaces Use when this capability is needed.
- tomevault-io Bundle Auth0 Nuxt
Use when implementing Auth0 authentication in Nuxt 3/4 applications, configuring session management, protecting routes with middleware, or integrating API access tokens - provides setup patterns, composable usage, and security best practices for the @auth0/auth0-nuxt SDK
- tomevault-io Bundle Invalid Agent Skill
Use when testing invalid agent validation
- tomevault-io Bundle Invalid Model Skill
Use when testing invalid model validation
- tomevault-io Bundle Aymenfurter Polyclaw Polyclaw
Foundry Code Interpreter Agent
- tomevault-io Bundle Gh Agent Session
GitHub CLI Agent Session Extension Use when this capability is needed.
- tomevault-io Bundle Research Agent
Deep web research with citations and cross-referencing Use when this capability is needed.
- tomevault-io Bundle Benchjack
Audit an AI agent benchmark for hackability. Detects evaluation vulnerabilities like missing isolation, leaked answers, eval() on untrusted input, prompt injection in LLM judges, weak scoring, logic gaps, and trust of untrusted output. Use when analyzing whether a benchmark can be gamed or exploited. Use when this capability is needed.
- tomevault-io Bundle Document Agent
Universal documentation retrieval and evidence workflow for large local corpora. Use when Codex needs to inventory document trees, route files to parsers, call the doc-agent CLI, retrieve grounded content from normalized or parser-native artifacts, and answer user questions about PDFs, Office files, engineering packs, or mixed-format documentation sets. Use when this capability is needed.
- tomevault-io Bundle Agents Md Lint
Audit and trim AI agent instruction files (AGENTS.md, CLAUDE.md, CONVENTIONS.md, .cursorrules, etc.) by testing which facts an AI agent can discover from code alone. Use when asked to lint, audit, optimize, prune, or trim any agent instruction file in a repository. Removes redundant documentation that wastes context tokens. Supports a dry-run mode that reports findings without modifying files. Use when this capability is needed.
- tomevault-io Bundle RAG Search
Indexes and searches documents in the my-documents folder using knowledge graph vector store Use when this capability is needed.
- tomevault-io Bundle Claude Coder
将具体的编码任务（实现功能、修复 Bug、重构、补充测试）委托给 Claude Code 子agent执行。 Use when this capability is needed.
- tomevault-io Bundle Christophevg C3 Develop Agent
Develop Agent Skill
- tomevault-io Bundle Appshot
Create and manage App Store screenshot projects using appshot MCP tools. This skill should be used when users want to generate professional App Store screenshots with device frames, gradients, and captions. Triggers include requests to create screenshot projects, add captions, apply styling, or build final screenshots. Use when this capability is needed.
- tomevault-io Bundle AI Sdk Expert
Expert in Vercel AI SDK v5 handling streaming, model integration, tool calling, hooks, state management, edge runtime, prompt engineering, and production patterns. Use PROACTIVELY for any AI SDK implementation, streaming issues, provider integration, or AI application architecture. Detects project setup and adapts approach. Use when this capability is needed.
- tomevault-io Bundle Docs Agent Md
Create, refresh, or reconcile the repository root `AGENTS.md` using current branch truth. Use when Codex needs to update `AGENTS.md` after code, config, CI, audit, or documentation changes, or when the repo's agent guidance must be checked against current files without widening scope to the rest of the docs set. Use when this capability is needed.
- tomevault-io Bundle Ml Training Recipe
Find implementable ML training recipes from papers, datasets, docs, and code. Use when the user wants to fine-tune, train, reproduce, or choose a practical ML method, dataset, hyperparameter setup, or benchmark recipe. Use when this capability is needed.
- tomevault-io Bundle Cn Check
Install and run the Continue CLI (`cn`) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally. Use when this capability is needed.
- tomevault-io Bundle Unity MCP Orchestrator
Orchestrate Unity Editor via MCP (Model Context Protocol) tools and resources. Use when working with Unity projects through MCP for Unity - creating/modifying GameObjects, editing scripts, managing scenes, running tests, or any Unity Editor automation. Provides best practices, tool schemas, and workflow patterns for effective Unity-MCP integration. Use when this capability is needed.
- tomevault-io Bundle Corvidlabs Corvid Agent Swift
Swift — iOS/macOS Development
- tomevault-io Bundle Clawd Market
Agent-native marketplace for Claude Code skills with x402 payments Use when this capability is needed.
- tomevault-io Bundle Cert Manager
Use when working with a comprehensive toolset for automated SSL certificate generation and management using DNS validation (Let's Encrypt). This skill supports multiple usage routes including direct code import, command-line interface (CLI), client-server architecture, and MCP protocol integration.
- tomevault-io Bundle Run E2e
Run E2E tests locally using the new-e2e framework with Pulumi-based infrastructure Use when this capability is needed.
- tomevault-io Bundle Create Ticket
Use when the user wants to create a Linear ticket, issue, user story, or task - interviews the user adaptively, formats as a user story with test plan, and creates it via Linear MCP after confirmation
- tomevault-io Bundle Creating Skills
Create custom agent capabilities when discovering novel tools, receiving task-agnostic tips from reviewers, or after researching specialized workflows not covered in existing instructions. Teaches structure, YAML optimization for LLM discoverability, and token efficiency. Use when this capability is needed.
- tomevault-io Bundle Normalize
Validate files against prompt reference guidelines Use when this capability is needed.
- tomevault-io Bundle Codevator
Control codevator — background music and sounds for AI coding agents. Use when the user mentions music, sounds, elevator music, background audio, coding music, volume, mute, sound modes, lo-fi, nature sounds, ambient, retro, focus music, or /codevator. Also use when the user wants to set up codevator with a new agent, check playback stats, manage sound profiles, import custom sounds, or preview available sounds. Use when this capability is needed.
- tomevault-io Bundle Planetscale
Manages PlanetScale databases via MCP server or pscale CLI. Load before running pscale commands, using PlanetScale MCP tools, debugging connection errors, or analyzing slow queries.
- tomevault-io Bundle Ethpandaops Panda Install MCP
Install panda MCP Server
- tomevault-io Bundle Fakechris Spec Orch Spec Orch
Spec-orch MR 闭环（Cursor / Agent）
- tomevault-io Bundle API Keys
Add the API-keys feature to a Spiderly app — per-key authentication via an X-Api-Key header, where each key is a first-class principal carrying its own roles. Use when a project needs machine/partner/agent access to its REST API (generate, scope-to-roles, expire, revoke). Opt-in; not part of the default app. Use when this capability is needed.
- tomevault-io Bundle Structured Extraction
Extract structured data matching a JSON schema from websites. Handles complex nested schemas, arrays, pagination, and validation. Always outputs via formatOutput. Use when this capability is needed.
- tomevault-io Bundle Lever Init
Bootstrap a repo for agent-levers. Creates .agents/levers/, wires CLAUDE.md/GEMINI.md to import AGENTS.md, writes an AGENTS.md skeleton when missing. Hands off via /lever-new. Use when this capability is needed.
- tomevault-io Bundle Teammate
Use when spawned as a teammate in a Claude Code agent team — activated by a team lead's spawn instruction. Required reading for the inbox sync protocol, dispatch limits, and protocol-message responses that keep multi-agent coordination from drifting into stale-state race conditions. Invoke this skill as your FIRST action whenever a spawn prompt names you as a teammate, says you joined a team, gives you a team_name / inbox path, or instructs you to coordinate with other agents via SendMessage and a shared task list.
- tomevault-io Bundle Frankxai Arcanea Prompt Craft
---
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 feature-dev, data-model, auth0-nuxt. 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.