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 Sniper CheckUse when validating code quality after modifications. Runs sniper agent in isolated forked context for clean, fast validation.
- tomevault-io Bundle Deepseek
DeepSeek AI models for coding. Use for code AI. Use when this capability is needed.
- tomevault-io Bundle Insomnia
Insomnia API client for REST and GraphQL. Use for API testing. Use when this capability is needed.
- tomevault-io Bundle Intellij
IntelliJ IDEA JetBrains IDE with smart completion. Use for JVM development. Use when this capability is needed.
- tomevault-io Bundle Monolith
Monolithic architecture single deployment. Use for simple systems. Use when this capability is needed.
- tomevault-io Bundle Passport
Passport.js authentication middleware. Use for Node.js auth. Use when this capability is needed.
- tomevault-io Bundle Phpstorm
PhpStorm PHP IDE with debugging. Use for PHP development. Use when this capability is needed.
- tomevault-io Bundle Rubymine
RubyMine Ruby IDE with Rails support. Use for Ruby development. Use when this capability is needed.
- tomevault-io Bundle Selenium
Selenium browser automation framework. Use for web testing. Use when this capability is needed.
- tomevault-io Bundle Solidity
Solidity smart contract development for Ethereum and EVM chains. Use for .sol files. Use when this capability is needed.
- tomevault-io Bundle Flashpaste
Use when the user wants to take a screenshot, paste an image into a terminal AI agent (Claude Code, Codex, Aider), hand content off between tmux panes, or debug clipboard issues on GNOME Wayland. flashpaste provides one unified CLI (`flashpaste shoot`, `flashpaste paste`, `flashpaste daemon`, `flashpaste doctor`, `flashpaste mcp`, `flashpaste dispatch`) plus an MCP server giving the agent real eyes (screenshots returned as PNG content) and hands (clipboard read/write + cross-pane paste).
- tomevault-io Bundle Syfthub CLI
Execute SyftHub CLI commands for privacy-preserving AI interactions. Use when the user wants to (1) authenticate with SyftHub platform, (2) browse or list AI endpoints and users, (3) query AI models with RAG (retrieval-augmented generation), (4) manage aggregator or accounting service configurations, (5) update the CLI, or (6) any task involving the `syft` command-line tool. Triggers on requests like "login to syfthub", "list endpoints", "query alice/gpt", "syft ls", "syft query", or any mention of the syft CLI. Use when this capability is needed.
- tomevault-io Bundle Guardrails Safety Filter Builder
Implements content safety filters with PII redaction, policy constraints, prompt injection detection, and safe refusal templates. Use when adding "content moderation", "safety filters", "PII protection", or "guardrails". Use when this capability is needed.
- tomevault-io Bundle CLI Gh
This skill should be used when the user mentions "gh CLI", "gh command", asks to "view repository info", "trigger workflows", "search GitHub", "manage codespaces", "check PR status", "list issues", or asks about GitHub CLI usage and automation from the command line. Use when this capability is needed.
- tomevault-io Bundle Asi Agent Orama
ASI Agent-O-Rama Skill Use when this capability is needed.
- tomevault-io Bundle Catsharp Galois
CatSharp Scale Galois Connections between agent-o-rama and Plurigrid ACT via Mazzola's categorical music theory Use when this capability is needed.
- tomevault-io Bundle Cider Embedding
Semantic embeddings for Clojure code navigation via CIDER Use when this capability is needed.
- tomevault-io Bundle Skill Evolution
Patterns for evolutionarily robust skills that adapt across agent generations. Darwin-Godel machine principles for self-improving skill ecosystems. Use when this capability is needed.
- tomevault-io Bundle Plurigrid Asi Vllm Deployment
vLLM Model Serving and Inference
- tomevault-io Bundle Rust Test Tools
Dynamic check toolkit beyond cargo test — cargo-careful (Miri fallback for FFI), loom (concurrency model checker), proptest (property tests), cargo-fuzz (libFuzzer), cargo-mutants (mutation testing). Use when authoring tests for unsafe code, custom atomics/locks, packet parsers, or before promoting an AI-generated module past basic test coverage. Use when this capability is needed.
- tomevault-io Bundle Consultant Context
Shared context loader for all consultant agents. Loads config, project-context, and workflow-status. Use automatically when any consultant agent starts. Use when this capability is needed.
- tomevault-io Bundle Skill Lookup
Activates when the user asks about Agent Skills, wants to find reusable AI capabilities, needs to install skills, or mentions skills for Claude. Use for discovering, retrieving, and installing skills. Use when this capability is needed.
- tomevault-io Bundle AI Switch
Use when working with a portable workflow for handing off a coding project between AI agents (Claude Code, Codex CLI, Gemini CLI, Cursor, etc.) without losing context. Uses PROGRESS.md + git as the single source of truth. When the user mentions switching agents, running out of quota, saving progress, or resuming work, route to the appropriate sub-skill — ai-switch-stop (save + commit) or ai-switch-start (read + report). Triggers on "ai-switch", "switch agent", "save progress", "resume from checkpoint", "hand off AI", "out of quota".
- tomevault-io Bundle Setup Agent Replay
Set up a local agent replay server for Raindrop Workshop. Use when the user wants Workshop to replay a captured trace against their real local agent code and tools. Creates/updates `.raindrop/agents.yaml`, scaffolds a language-appropriate replay server, registers the project with `raindrop replay register`, and verifies `/health`. Use when this capability is needed.
- tomevault-io Bundle Discover MCP
Automatically discover MCP (Model Context Protocol) skills when building MCP servers, designing tools, implementing resources/prompts, or testing MCP integrations. Activates for MCP server development tasks. Use when this capability is needed.
- tomevault-io Bundle Convex Performance Audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification. Use when this capability is needed.
- tomevault-io Bundle Shuoshuo Notes
说说笔记单一综合 skill。默认走 HTTP API，MCP 仅在明确已启用时使用。覆盖发布、搜索、分页、详情、更新、删除、置顶、登录、令牌、状态、配置、日历与 RSS。 Use when this capability is needed.
- tomevault-io Bundle Maestro Design
Use when the user wants to brainstorm, design, plan, choose wording, or decide a workflow, skill, harness, card/task/feature, architecture, UX, or agent-process change in a project using Maestro before implementation.
- tomevault-io Bundle Memex
Scaffold or audit the memex (vault + AGENTS.md + spec templates + bundled skills) in any repo — an externalized, navigable project memory for agents (Claude Code, Codex, Cursor, OpenCode, etc.). Agent-agnostic. Idempotent — safe to run repeatedly. Use when the user wants to set up, verify, or fix the memex in a project. Use when this capability is needed.
- tomevault-io Bundle Ririnto Sinon MCP Integration
MCP Integration
- tomevault-io Bundle Roznet Flyfun Apps Agent Test
Aviation Agent Test Improvement
- tomevault-io Bundle Expert
General Apache Cassandra expertise for questions, CQL analysis, best practices, vnodes, and guidance. Use for general Cassandra questions that don't fit diagnose, optimize, or data-model. Use when this capability is needed.
- tomevault-io Bundle Sceneview IOS
Build 3D and AR apps on Apple platforms (iOS, macOS, visionOS) with SceneViewSwift — the SwiftUI wrapper around RealityKit. Use whenever the user asks for "3D in SwiftUI", "AR with ARKit in SwiftUI", a model viewer for iOS, or any Apple-platform 3D/AR app where the dependency is the `SceneViewSwift` Swift Package from `github.com/sceneview/sceneview`. For Jetpack Compose / Android use the `sceneview` skill instead; for the browser use `sceneview-web`. Skip for plain ARKit-SDK / SceneKit / Unity / Unreal / RealityKit-without-SceneViewSwift work. Use when this capability is needed.
- tomevault-io Bundle Building Agents Construction
Step-by-step guide for building goal-driven agents. Creates package structure, defines goals, adds nodes, connects edges, and finalizes agent class. Use when actively building an agent. Use when this capability is needed.
- tomevault-io Bundle Using Signalize
Use when code imports `@spearwolf/signalize` or `@spearwolf/signalize/decorators`, mentions `signalize`/`Signalize`, or when writing/reviewing fine-grained reactivity code with signals, effects, memos, links, SignalGroup, or the @signal/@memo decorators. Covers the API surface, the synchronous reactivity model, lifecycle bundles, lazy/eager memos, dynamic vs static effect deps, and the quirks LLMs most often get wrong.
- tomevault-io Bundle Context Optimize
提高长时间或复杂会话的上下文效率和缓存稳定性。 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 sniper-check, deepseek, insomnia. 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.