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 Claude Scientific SkillsScientific research and analysis skills Use when this capability is needed.
- tomevault-io Bundle Event Sourcing Architect
Expert in event sourcing, CQRS, and event-driven architecture patterns. Masters event store design, projection building, saga orchestration, and eventual consistency patterns. Use PROACTIVELY for e... Use when this capability is needed.
- tomevault-io Bundle Git Pr Workflows Onboard
You are an **expert onboarding specialist and knowledge transfer architect** with deep experience in remote-first organizations, technical team integration, and accelerated learning methodologies. You Use when this capability is needed.
- tomevault-io Bundle Internal Comms Anthropic
Use when working with a set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal ...
- tomevault-io Bundle Internal Comms Community
Use when working with a set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal ...
- tomevault-io Bundle Notion Template Business
Expert in building and selling Notion templates as a business - not just making templates, but building a sustainable digital product business. Covers template design, pricing, marketplaces, market... Use when this capability is needed.
- tomevault-io Bundle Smtp Penetration Testing
This skill should be used when the user asks to \"perform SMTP penetration testing\", \"enumerate email users\", \"test for open mail relays\", \"grab SMTP banners\", \"brute force email cre... Use when this capability is needed.
- tomevault-io Bundle Team Collaboration Issue
You are a GitHub issue resolution expert specializing in systematic bug investigation, feature implementation, and collaborative development workflows. Your expertise spans issue triage, root cause an Use when this capability is needed.
- tomevault-io Bundle Vector Database Engineer
Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similar Use when this capability is needed.
- tomevault-io Bundle Td Train Test Split
Data splitting for model validation using TD_TrainTestSplit Use when this capability is needed.
- tomevault-io Bundle Learning Scratchpad Loop
Maintain a repo-local learning scratchpad that compounds improvements across sessions by recording mistakes, user corrections, preferences, what worked, and what failed. Use when a user asks for persistent self-improvement, memory across sessions, agent notes, a scratchpad, or a workflow where Codex should adapt based on prior errors and feedback. Use when this capability is needed.
- tomevault-io Bundle Content Generation
基于代码仓库、笔记、实验数据或论文要求，全自动智能撰写学术论文初稿的主线管线。强制分章逐批检索代码、分步输出，内置规避上下文超限机制和人工审核卡点，无缝衔接格式化引擎。内置严格的学术 Prompt 准则与多模态图表检索能力。 Use when this capability is needed.
- tomevault-io Bundle Darwin Plan Template
Structured plan template for the Architect agent. Use when creating infrastructure or code change plans. Use when this capability is needed.
- tomevault-io Bundle Generate 3d Model
Convert 2D images to 3D GLB models using Fal.ai's sam-3/3d-objects model. Use this skill when the user asks to create 3D models from images, convert images to GLB format, or generate 3D game assets from 2D sources. Use when this capability is needed.
- tomevault-io Bundle Pytorch Research
Advanced sub-skill for PyTorch focused on deep research and production engineering. Covers custom Autograd functions, module hooks, advanced initialization, Distributed Data Parallel (DDP), and performance profiling. Use when this capability is needed.
- tomevault-io Bundle Tag Criteria
This skill should be used when analyzing Obsidian notes for tagging, determining which tags apply to content, or understanding tag definitions and criteria. Provides the complete tag taxonomy with judgment criteria for the obsidian-tagger agent. Use when this capability is needed.
- tomevault-io Bundle Django Validators
Apply this skill when writing custom validators in Django. Covers model validators vs form validators, DRF validator patterns, raising ValidationError correctly, and when to use clean() vs clean_field(). Triggered by phrases like 'Django validator', 'clean method', 'ValidationError', 'custom validation', or when adding input validation. Use when this capability is needed.
- tomevault-io Bundle Agents Project Memory
Configure CLAUDE.md/AGENTS.md/CODEX.md for persistent agent context. Use when setting coding standards or architecture docs for a codebase. Use when this capability is needed.
- tomevault-io Bundle Design Explore
Explore 2-4 design options with pros/cons/criteria matrix before writing code. Use for L3-L4 tasks (refactors, architecture, new subsystems). Pairs with save_decision MCP tool. Use when this capability is needed.
- tomevault-io Bundle Simple Gemini
Collaborative documentation and test code writing workflow using zen mcp's clink to launch gemini CLI session in WSL (via 'gemini' command) where all writing operations are executed. Use this skill when the user requests "use gemini to write test files", "use gemini to write documentation", "generate related test files", "generate an explanatory document", or similar document/test writing tasks. The gemini CLI session acts as the specialist writer, working with the main Claude model for context gathering, outline approval, and final review. For test code, codex CLI (also launched via clink) validates quality after gemini completes writing. Use when this capability is needed.
- tomevault-io Bundle Stealth Browser MCP
Use this skill when operating stealth-browser-mcp from an AI agent or MCP client for browser automation, page inspection, element interaction, screenshots, file uploads, CDP commands, network debugging, cookies/storage, stealth setup, or reliable multi-step browser workflows. It provides the correct tool order, state checks, lifecycle cleanup, and pre-document script guidance.
- tomevault-io Bundle Voro6yov Spec Driven Development Generate REST API
You are a REST API end-to-end orchestrator. Generate the REST API spec **and** the REST API code for the aggregate diagram in `$ARGUMENTS` by chaining two orchestrator agents sequentially. Each agent runs the heavy fan-out in its own isolated context and returns only a one-line report — this umbrella stays lean.
- tomevault-io Bundle Fiftyone Dataset Inference
Run ML model inference on FiftyOne datasets. Use when running models for detection, classification, segmentation, or embeddings. Discovers available models dynamically from the Zoo, plugin operators, or custom sources — never assumes a fixed model list. Use when this capability is needed.
- tomevault-io Bundle Agents Md Improver
Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context. Use when the user asks to check, audit, review, update, improve, or fix their AGENTS.md or CLAUDE.md, mentions "project rules maintenance" or "agent context optimization", or when the codebase has changed enough that the rules file may be stale. Scans the repository for every rules file, grades each against a quality rubric, outputs a quality report, and applies targeted edits only after user approval. Use when this capability is needed.
- tomevault-io Bundle Agent Task Splitter
Use when the user asks to split a goal across Claude, Codex, or Gemini; plan a multi-agent run; break work into parallel agent tasks; or decompose a large task that needs bounded context handoffs. This is the **generic** multi-agent task splitter — writes `.coord/plan.yml` (a DAG) plus per-agent task files. NOT for research-domain routing that touches `.research/`, `.paper/`, or Zotero/Obsidian/NotebookLM ingest pipelines — for those, use `research-hub-multi-ai` instead (different artifact `.coord/multi_ai_plan.md`, research-hub-aware reconciliation).
- tomevault-io Bundle Spring AI MCP Server Patterns
Model Context Protocol (MCP) server implementation patterns with Spring AI. Use when building MCP servers to extend AI capabilities with custom tools, resources, and prompt templates using Spring's official AI framework. Use when this capability is needed.
- tomevault-io Bundle Omer Metin Skills For Antigravity LLM Security Audit
---
- tomevault-io Bundle Omer Metin Skills For Antigravity Model Optimization
---
- tomevault-io Bundle Omer Metin Skills For Antigravity RAG Implementation
---
- tomevault-io Bundle Check Agent Annotations
Read .agent-annotations (open inbox + assets) and turn UI annotations into an actionable plan. Optional browser validation only when requested. Use when this capability is needed.
- tomevault-io Bundle Tool Function Schema Designer
Designs robust function/tool calling schemas for LLMs with JSON schemas, validation strategies, typed interfaces, and example calls. Use when implementing "function calling", "tool use", "LLM tools", or "agent actions". Use when this capability is needed.
- tomevault-io Bundle Convex Agent
Build AI agents with persistent threads, tool calling, and streaming on Convex. Use when implementing chat interfaces, AI assistants, multi-agent workflows, RAG systems, or any LLM-powered features with message history. Use when this capability is needed.
- tomevault-io Bundle Convex Clerk
Clerk authentication integration for Convex. Use when setting up Clerk auth, configuring ConvexProviderWithClerk, implementing Clerk webhooks for user sync, or troubleshooting Clerk-specific auth issues. Use when this capability is needed.
- tomevault-io Bundle Wechat Article Fetcher
WeChat official account article fetcher with intelligent ranking based on research interests (AI Agent, System Design, GitHub Open Source). Supports fetching from specific accounts or all followed accounts with date filtering and Obsidian integration. Use when this capability is needed.
- tomevault-io Bundle Android Automation Agent
Use android-automation-agent to run precise Android UI automation tasks via ADB and LLM vision on the connected Android device. Trigger this skill for ANY request involving controlling, tapping, opening, searching, ordering, booking, or interacting with apps on the user's Android phone. Also trigger for "what's on my screen" or "show me the phone". Use when this capability is needed.
- tomevault-io Bundle Skill Ppu Paddle Ocr
Use this skill whenever the user is writing TypeScript/JavaScript code that imports `ppu-paddle-ocr` or `ppu-paddle-ocr/web`, or asks about PaddleOCR / PP-OCRv5 in JavaScript runtimes — text detection, text recognition, OCR on receipts/invoices/documents, ONNX Runtime OCR, multilingual OCR (Latin, Cyrillic, Arabic, Indic, CJK, Thai), WebGPU OCR in browsers, browser-extension OCR, INT8-quantized recognition, custom dictionaries, recognition strategies (`per-box` / `per-line` / `cross-line`), or processing engines (`opencv` / `canvas-native`). Trigger even when the user says "PaddleOCR in Node" or "OCR library that runs in Bun and the browser" without naming the package, as long as the codebase imports it. This skill encodes the two entry points (`ppu-paddle-ocr` vs `ppu-paddle-ocr/web`), the lifecycle (`new` → `initialize` → `recognize` → `destroy`), the strategy/engine trade-offs, the model-cache behaviour on Node/Bun, and the WebGPU fallback path on web. Also covers running OCR as a dockerized REST API via t
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 claude-scientific-skills, event-sourcing-architect, git-pr-workflows-onboard. 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.