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 MlxRunning and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging Face models to MLX format, fine-tuning with LoRA/QLoRA on Apple Silicon, or serving models via HTTP API. Use when this capability is needed.
- tomevault-io Bundle Jackspace Claudeskillz Typescript MCP
TypeScript MCP Server on Cloudflare Workers
- tomevault-io Bundle Solarwinds Logs
Search and analyze DealerVision production logs via SolarWinds Observability API. Use when investigating errors, debugging issues, checking system health, or when the user mentions logs, SolarWinds, production errors, or system monitoring. Requires the `logs` CLI tool to be installed. Use when this capability is needed.
- tomevault-io Bundle Jarydyd Chutes Chutes MCP Portability
Chutes MCP + Portability for Hermes **[BETA]**
- tomevault-io Bundle Scientific Paper
Writes and edits scientific and academic papers in LaTeX following rigorous research methodology. Use when the user asks to write, edit, expand, structure, or review any academic paper, research paper, technical report, or LaTeX document. Triggers on mentions of papers, LaTeX, .tex files, abstracts, literature reviews, methodology sections, theorems, proofs, citations, or BibTeX. Covers the full research lifecycle from problem formulation through publication-ready output. Use when this capability is needed.
- tomevault-io Bundle RAG Architect
Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying reranking, and evaluating retrieval quality. Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, context augmentation, similarity search, or embedding-based indexing. Use when this capability is needed.
- tomevault-io Bundle Init Agents
Scaffold a tailored Claude Code agent team into the current repo — detects the stack, proposes agents/commands/hooks, then writes and wires them into .claude/ and CLAUDE.md. Use when this capability is needed.
Audited - tomevault-io Bundle Design Of Experiments
Expert guidance for Design of Experiments (DOE) in Python - interactive goal-driven design selection, classical DOE (factorial, response surface, screening), Bayesian optimization with Gaussian processes, model-driven optimal designs, active learning, and sequential experimentation; includes pyDOE3, pycse, BoTorch, Ax, scikit-optimize, statsmodels Use when this capability is needed.
- tomevault-io Bundle Exploration Strategy
This skill should be used when exploring codebases, finding patterns, searching for code, gathering context, or understanding code structure before planning or implementation. Use when this capability is needed.
- tomevault-io Bundle Parallel Setup
One-time setup of parallel/ directory for multi-agent development Use when this capability is needed.
- tomevault-io Bundle Setup MCP Auth
Configure authentication for an existing FastMCP server Use when this capability is needed.
- tomevault-io Bundle Backend Engineer
Plan and review safe backend extensions for existing services (Cloudflare Workers + Hono primary). Use this skill when patching or adding backend features in an existing codebase. Use when this capability is needed.
- tomevault-io Bundle Codex Home Audit
Audit a Codex home directory for control-plane drift, risky state, and cleanup opportunities across config, agents, hooks, skills, plugins, and telemetry. Use when the user wants a dated Codex home health review. Use when this capability is needed.
- tomevault-io Bundle Og Image Builder
Generate brand-aligned Open Graph images for existing routes by inspecting a web codebase and rendering assets with Playwright components. Use when a user asks for route-specific OG image generation or refresh in an existing app. Use when this capability is needed.
- tomevault-io Bundle Skill Scaffolder
Create new skills following pitlane-agent conventions. Use when adding new functionality that requires skill scaffolding, script generation, or test creation. Use when this capability is needed.
- tomevault-io Bundle Jsperger LLM R Skills Metaprogramming
R Metaprogramming with rlang
- tomevault-io Bundle Jsperger LLM R Skills Tidy Evaluation
Tidy Evaluation Programming Patterns
- tomevault-io Bundle Feature Orchestrator
Orchestrate feature implementation through planning, agent delegation, and user checkpoints. Use when starting work on a Jira ticket or implementing a feature with structured review gates. Triggers on "implement feature", "work on ticket", "orchestrate", or ticket IDs like PROJ-12345. CRITICAL - This skill coordinates agents, it does NOT implement directly. Use when this capability is needed.
- tomevault-io Bundle Jwilger Agent Skills Mutation Testing
Mutation Testing
- tomevault-io Bundle Ml Engineer
Use when building ML pipelines, training models, evaluating LLMs, setting up RAG systems, or designing model deployment architectures — with validation at every stage
- tomevault-io Bundle Portfolio Manager
Orchestrator agent that coordinates backtesting, paper trading, and validation workflows Use when this capability is needed.
- tomevault-io Bundle Pcc
Parallel Claude Coordinator - Create implementation plans with Sonnet scouts for exploration and Opus agents for implementation. Use for complex multi-file tasks requiring parallel coordination. Use when this capability is needed.
- tomevault-io Bundle Model Thinking
Mental models toolkit for clearer thinking, better decisions, and problem-solving. Use when users face complex problems, need decision support, want to analyze situations from multiple angles, organize information, understand systems, predict outcomes, or learn about specific mental models. Triggers include phrases like "help me think through", "analyze this problem", "what models apply here", "how should I decide", "evaluate options", or direct model references (e.g., "use second-order thinking", "apply inversion"). 中文觸發：「思維模型」、「幫我分析」、「決策分析」、「多角度思考」、「怎麼判斷」、「幫我想清楚」、「系統思考」、「風險評估」。 Use when this capability is needed.
- tomevault-io Bundle Browser Testing
Use agent-browser CLI for UI testing - screenshots, element interaction, visual verification Use when this capability is needed.
- tomevault-io Bundle Claude Peers Bible
Master guide to Claude Peers — the built-in MCP server for multi-instance communication, coordination, and parallel development workflows Use when this capability is needed.
- tomevault-io Bundle Kilo Org Kilo Marketplace MCP Builder
MCP Server Development Guide
- tomevault-io Bundle Klever Dev
End-to-end Klever blockchain development — smart contracts (Rust/WASM), transaction building (@klever/connect, klever-go-sdk), deployment via ksc + koperator, and on-chain interaction via MCP tools. Use when the task involves KLV, KDA tokens, klv1 addresses, Klever smart contracts, or Klever node/API interaction. Use when this capability is needed.
- tomevault-io Bundle Lsp Bridge
Query VS Code Language Server features through a local HTTP bridge. Use this skill whenever you need to investigate compilation errors, find references to a symbol, look up type information or documentation, navigate to definitions, declarations, or implementations, list document or workspace symbols, get available code actions (quick fixes, refactorings), check function signatures, preview rename edits, explore call hierarchies, understand type hierarchies, get code completion suggestions, inspect inlay hints, get folding ranges, or read the currently open file. Works with ANY programming language that has an LSP extension in VS Code — Java, Python, TypeScript, JavaScript, Go, Rust, C#, C++, Ruby, and more. Always use this skill when the user mentions compiler errors, diagnostics, code navigation, type checking, symbol lookup, call graphs, or code structure analysis in a VS Code workspace. Use when this capability is needed.
- tomevault-io Bundle Update Documentation
How to add or change project documentation. Use when adding docs, updating docs, or when the user asks how documentation should be organized or where to put new docs. Use when this capability is needed.
- tomevault-io Bundle Largo2z9 Phantomos Connect MCP Server
connect-mcp-server, orchestrator
- tomevault-io Bundle QA Testing
QA engineer with expertise in software testing methodologies, test design, and quality assurance practices. Use this skill when planning tests, writing test cases, or improving test coverage and quality. Use when this capability is needed.
- tomevault-io Bundle Web Page Workflow
使用本项目MCP 与 Firecrawl MCP 处理普通网页资产提取与原型还原的流程规范；在执行网页页面地图发现、主题/数据/文档提取与还原时使用。 Use when this capability is needed.
- tomevault-io Bundle Citations Retrieval
Document citations and RAG (Retrieval-Augmented Generation) patterns for Claude. Activate for source attribution, document grounding, citation extraction, and contextual retrieval. Use when this capability is needed.
- tomevault-io Bundle Paw Pr
Final PR activity skill for PAW workflow. Creates comprehensive final PR to base branch with pre-flight validation, scaled descriptions, and merge guidance. Use when this capability is needed.
- tomevault-io Bundle Flutter Layout
Builds Flutter layouts using the constraint system and layout widgets. Use when creating or refining the UI structure of a Flutter application.
- tomevault-io Bundle View Model
Build or refactor Flutter state management with the view_model package, including ViewModel/ViewModelBinding mixins, ViewModelSpec sharing, watch/read semantics, lifecycle, pause-resume, testing, and code generation. 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 mlx, jackspace--claudeskillz--typescript-mcp, solarwinds-logs. 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.