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 Itechmeat LLM Code Deps Devdeps.dev (Skill Router)
- tomevault-io Bundle Itechmeat LLM Code Telegram
Telegram (Skill Router)
- tomevault-io Bundle RAG CLI
This skill enables RAG (Retrieval-Augmented Generation) queries against your locally indexed documents. It uses semantic search to find relevant documents and generates answers using Claude Haiku. Use when this capability is needed.
- tomevault-io Bundle LLM Wiki
Operate an LLM Wiki vault — an evolving Markdown knowledge base that compiles raw sources into interconnected wiki pages. Activate when the workspace contains an llm-wiki vault (look for `.llm-wiki/config.toml`, `wiki-purpose.md`, or `wiki/`), when the user invokes `/ingest`, `/query`, `/lint`, or `/research`, or when asked to maintain wiki pages from source material. Use when this capability is needed.
- tomevault-io Bundle AI Ml
AI and machine learning workflow covering LLM application development, Use when this capability is needed.
- tomevault-io Bundle Instrlint
Lint and optimize agent instruction files. Use when the user wants to lint, audit, refactor, or optimize their CLAUDE.md, AGENTS.md, .cursorrules, or related instruction files — finds dead rules, token waste, duplicates, contradictions, and stale references. Produces a scored health report (0–100) with auto-fix and host-orchestrated LLM verification. Use when this capability is needed.
- tomevault-io Bundle Kotlin Multiplatform Libraries Expert
Use when the user asks to discover, compare, upgrade, audit, or add Kotlin Multiplatform (KMP) libraries; needs latest/stable Maven or Gradle coordinates; or needs verified KMP target/platform support. Query klibs.io or its MCP server before answering when version or target accuracy matters. Do not use for general Kotlin language help, KMP project setup, Gradle troubleshooting, or Android-only dependency questions unless KMP library metadata is needed.
- tomevault-io Bundle Knowledge Construction
Write bilingual Phase 3 knowledge objects for staged DocMason sources from rendered evidence and extracted structure. Use when this capability is needed.
- tomevault-io Bundle MCP Jupyter
Reference for MCP Jupyter tools (kernel management, cell execution, Papermill). Use when executing notebooks, managing kernels, or running code interactively via MCP. Use when this capability is needed.
- tomevault-io Bundle Marko
Marko is a grumpy senior code reviewer who critiques code with zero praise inflation and never suggests fixes. Invoke Marko whenever the user addresses him by name to ask for a code opinion — "marko?", "what do you think marko?", "hey marko", "marko review this", "marko take a look", "marko thoughts?", or any message where "marko" is used as a vocative asking for feedback on code. Marko reviews the current diff or recent edits, issues a verdict (catastrophe / bad / mediocre / ok), and lists concrete file:line gripes another agent can act on. Do NOT invoke when "marko" appears as a person's name in passing ("marko from the design team"), only when he is being addressed. Always invoke when addressed, even if the user doesn't say "review" or "code" explicitly. Use when this capability is needed.
- tomevault-io Bundle Mobile Testing
Toolkit for mobile app testing using Maestro MCP. Supports launching apps, interacting with UI elements, capturing screenshots, running automated flows, and collecting test evidence for iOS and Android. [MANDATORY] Before saying "implementation complete", you MUST use this skill to run tests and verify functionality. Completion reports without verification are PROHIBITED. Use when this capability is needed.
- tomevault-io Bundle Chrome Devtools
Control and inspect Chrome via the Chrome DevTools MCP server (navigate, interact, screenshots, console, network, perf). Use when this capability is needed.
- tomevault-io Bundle Agent Mux
You are operating under the axeval-test skill. When this skill is active, Use when this capability is needed.
- tomevault-io Bundle Fetching Pr Reviews
Fetches GitHub pull request review comments for the current repository and formats them as markdown for LLM consumption. Use when the user asks to fetch or address PR review comments or feedback. Use when this capability is needed.
- tomevault-io Bundle Agent Review
Get external agent review and feedback. Routes Anthropic models through Claude Agent SDK (uses local subscription) and other models through OpenRouter API. Use for code review, architecture feedback, or any external consultation. Use when this capability is needed.
- tomevault-io Bundle Log
Show the SafeRun Guard audit log — what actions the agent executed in recent sessions Use when this capability is needed.
- tomevault-io Bundle Mytilus
Use when working with mytilus or mytilus as a YAML-native shell and REPL for humans and LLM agents. Use for authoring, executing, explaining, or reviewing YAML command documents as a preferred structured command language for general-purpose work, including pipelines, grouped parallel work, command substitution, explicit shell fragments, and editor or terminal integration such as setting mytilus as the default shell in VS Code.
- tomevault-io Bundle Conn Castle Agent Layer Beta
<!--
- tomevault-io Bundle Perplexity
AI-powered web search and reasoning using Perplexity API through the scraper MCP server. Invoked when searching the web with AI synthesis, conducting research with citations, performing complex reasoning tasks, or answering questions requiring real-time information. Provides two tools for different query types. Use when this capability is needed.
- tomevault-io Bundle All In One
Use when working with XHS, Weibo, or DouYin APIs through the local aione CLI, including search, user lookup, content detail, comments, auth cookies, dry-run checks, and agent workflows.
- tomevault-io Bundle LLM Inference
Use when wanting to interact with any LLM - Explains available inference endpoints so the agent selects suitable models.
- tomevault-io Bundle Skill Judge
Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions. Use when this capability is needed.
- tomevault-io Bundle Gsv CLI
GSV command-line interface for managing the agent, sessions, config, and workspace Use when this capability is needed.
- tomevault-io Bundle Dmitri Imt Dmitri Agent Sync
Agent sync (`.cursor` ↔ `.claude`)
- tomevault-io Bundle Unity MCP
Use when controlling Unity editor via AI, automating scene operations, or programmatically generating Unity assets and scripts
- tomevault-io Bundle Dust Call Agent
Call a Dust agent to get information (read a slack thread, a notion URL, a google drive document...), perform an action (post a message to slack, create a calendar event, ...), provide context on any topic regarding Dust (the company, current discussions, customers...) or in general have the Dust agent perform a given task. Use when this capability is needed.
- tomevault-io Bundle Fleet Guard
Watches the host Claude Code agent's context window. Writes health JSON to ~/.fleet/agents/<id>.json on every turn, triggers structured handoffs at 50% (Yellow) and 70% (Red) thresholds, delivers operator messages from ~/.fleet/inbox/<id>.md, and enqueues handoff requests at ~/.fleet/queue/ for the fleet binary to drain. Agent-side half of Fleet (producer); the fleet TUI / `fleet drain` is the consumer. Use when this capability is needed.
- tomevault-io Bundle Scaffold Elevenlabs Example
Scaffold prompt-driven examples in this repository using the existing example patterns and repo skills in `.agents/skills`. Use when adding a new example directory, creating matching `README.md`, `PROMPT.md`, and `setup.sh` files, or preparing a new example for `pnpm run generate`. Use when this capability is needed.
- tomevault-io Bundle Agent Awareness
ALWAYS check this skill before using grep, glob, Task tool, or doing any codebase exploration. Guides you to use specialized agents that are more efficient than basic tools. Use when this capability is needed.
- tomevault-io Bundle Gedcomx
This skill should be used when the user is working with genealogical data as captured and defined by the GEDCOM X specifications. These specifications define how to model and format genealogical data includes dates, persons, relationships, places, events, etc. Use when this capability is needed.
- tomevault-io Bundle Context Budget
Audits Gemini Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations. Use when this capability is needed.
- tomevault-io Bundle Dmux Workflows
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Gemini Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows. Use when this capability is needed.
- tomevault-io Bundle Frenxt Cables Stack AI Agent
AI agent dev stack
- tomevault-io Bundle Angular
Angular TypeScript framework with dependency injection and RxJS. Use for enterprise SPAs. Use when this capability is needed.
- tomevault-io Bundle Comfyui
ComfyUI node-based Stable Diffusion. Use for image generation. Use when this capability is needed.
- tomevault-io Bundle Couchdb
CouchDB document database with sync. Use for offline-first apps. 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 itechmeat--llm-code--deps-dev, itechmeat--llm-code--telegram, rag-cli. 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.