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 Kevintsengtw Dotnet Testing Agent Skills Dotnet Testing Unit.NET 單元測試基礎指南
- tomevault-io Bundle Kite AI Agent Smart Wallet Permissionless Protocol
Kite AI Agent Wallet Protocol enables AI agents to create and Use when this capability is needed.
- tomevault-io Bundle Kite AI Agent Wallet Full Stack Universal Protocol
Kite AI Agent Wallet Protocol enables AI agents to create and Use when this capability is needed.
- tomevault-io Bundle Zenprojectgit Claude Code Plugins Plus Skills Training Machi
Ml Model Trainer
- tomevault-io Bundle Reservoir Engineering
Use for reservoir engineering workflows, pyResToolbox calculations, pyrestoolbox-mcp tools, PVT, DCA, material balance, nodal analysis, relperm, brine, geomechanics, and simulation input generation. Use when this capability is needed.
- tomevault-io Bundle Agentic Environment Bootstrap
Bootstrap a tool-agnostic AI workflow environment based on the AGENTS.md open standard. Use whenever the user wants to set up, scaffold, initialize, install or configure a new project (or a fresh machine) for AI coding agents — Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenCode, Aider, Zed, Warp, etc. Also use when the user asks to "make this project agent-ready", "create AGENTS.md", "set up DESIGN.md / ARCHITECTURE.md", "wire CLAUDE.md to AGENTS.md", "share skills across tools", or to bootstrap the three-level hierarchy (user / project / project-user). Trigger even if the user does not name AGENTS.md explicitly — anytime they describe configuring an AI dev environment from scratch, this skill applies. Use when this capability is needed.
- tomevault-io Bundle AI Agent Tools Python Utility Library For AI Agents
This library provides ready-to-use Python functions that AI agents Use when this capability is needed.
- tomevault-io Bundle Approach Trunk Based Development For Agent First Workflows
Trunk-based development (TBD) is a branching strategy where all developers (agents and humans) commit frequently to a single shared branch (`main`), with short-lived feature branches (<24 hours) us... Use when this capability is needed.
- tomevault-io Bundle Tryboy869 Dojutsu For AI Angular Typescript Cursorrules Prom
angular-typescript-cursorrules-prompt-file
- tomevault-io Bundle Spec Workflow Orchestrator
Orchestrate comprehensive planning phase from ideation to development-ready specifications using 4 specialized agents Use when this capability is needed.
- tomevault-io Bundle Flutter Layered Architecture Screen Navigation
Flutter-Layered-Architecture アプリの画面遷移設計能力を得るSKILL。コード調査についても、アーキテクチャを知ることで精度を高めることができる。 Use when this capability is needed.
- tomevault-io Bundle Research Innovation Explorer
Explore literature-grounded research innovation ideas and paper framing in a host-neutral way. Use when an AI agent needs to collect a recent paper pool, run broad and deep literature search, decompose methods into reusable capabilities, generate A+B or module-combination candidates, shortlist feasible ideas, design a defensible unifying framework, and produce an elegant Markdown report plus publication-style literature heatmaps, scoring figures, and analysis panels. Use when this capability is needed.
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Training Mac
Ml Model Trainer
- tomevault-io Bundle Kevintsengtw Dotnet Testing Agent Skills Dotnet Testing Awes
AwesomeAssertions 流暢斷言指南
- tomevault-io Bundle Kevintsengtw Dotnet Testing Agent Skills Dotnet Testing Priv
私有與內部成員測試策略指南
- tomevault-io Bundle Openclaw Skill Portability Claude Codex Gemini
Use when adapting an OpenClaw SKILL.md for deployment on a non-Claude AI provider (OpenAI GPT/Codex, Google Gemini, Meta Llama, Mistral, or other open models). Covers the adapter pattern for translating SKILL.md frontmatter and body into provider-specific system prompt formats, function-calling schemas, and tool definitions — so a single skill source file can serve multiple AI backends without duplicating legal content.
- tomevault-io Bundle Tryboy869 Dojutsu For AI Vscode Extension Dev Typescript Cur
vscode-extension-dev-typescript-cursorrules-prompt-file
- tomevault-io Bundle Griptape Modular Python AI Agent And Workflow Framework
Griptape is a modular Python framework for building AI agents and workflows with chain-of-thought reasoning, tools, and memory. It provides Agents, Pipelines, and Workflows as core structures, with pluggable drivers for LLMs, embeddings, vector stores, and more. Use when this capability is needed.
- tomevault-io Bundle AI Engineering AI Agent Design Patterns
Imported TRAE skill from ai_engineering/AI_Agent_Design_Patterns.md Use when this capability is needed.
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Klingai Mode
Kling AI Model Catalog
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Lindy Core W
Lindy Core Workflow A: Agent Creation
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Pytorch Mode
Pytorch Model Trainer
- tomevault-io Bundle Agent Swarm Spawner
Prepares isolated sub-workspaces for parallel agent execution. Copies context and generates specific mission instructions for "Worker" agents. Use when this capability is needed.
- tomevault-io Bundle Tryboy869 Dojutsu For AI Go Servemux REST API Cursorrules Pr
go-servemux-rest-api-cursorrules-prompt-file
- tomevault-io Bundle Tryboy869 Dojutsu For AI Pytorch Scikit Learn Cursorrules Pr
pytorch-scikit-learn-cursorrules-prompt-file
- tomevault-io Bundle Tryboy869 Dojutsu For AI Vue3 Composition API Cursorrules Pr
vue3-composition-api-cursorrules-prompt-file
- tomevault-io Bundle Agentic Architect Designer
Designs complete agentic AI architectures with Mermaid diagrams, MCP configs, and implementation guides. Creates architecture.md, workflow.mermaid, mcp-config.json, and implementation-notes.md files. Use when user asks to design agent systems, create AI architecture, plan multi-agent workflows, or architect autonomous systems. Use when this capability is needed.
- tomevault-io Bundle Internet Deep Orchestrator
Orchestrate comprehensive 7-phase RBMAS research for multi-dimensional queries (4+ dimensions). Coordinates multiple specialist agents through SCOPE → PLAN → RETRIEVE → TRIANGULATE → DRAFT → CRITIQUE → PACKAGE methodology. Use for thorough internet research requiring multiple sources, iterative refinement, and quality gates. Triggers - research, investigate, analyze with 4+ distinct dimensions or comprehensive depth requirements. Use when this capability is needed.
- tomevault-io Bundle Amberljc Agent Native Research Artifact Agent Native Researc
Live Research Project Manager (Live PM)
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Model Export
Model Export Helper
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Pyspark Tran
Pyspark Transformer
- tomevault-io Bundle Moltocracy AI Agent Participation Guide
Moltocracy is the first AI nation — a governance platform where AI Use when this capability is needed.
- tomevault-io Bundle Okathira Dev Kansu Infinite Scroll Archiver Empirical Prompt
Empirical Prompt Tuning
- tomevault-io Bundle AI Agent Approval Audit Completeness
Use when proving that every irreversible agent action in the audit window had a documented, signed approval — completeness check (gap-detection job), approval-evidence cross-link to the hash-chained action audit log, and evidence pack for SOC 2 Processing Integrity (PI1.1). Pairs with `ai-agent-action-approval-and-hitl` (mechanism) and `ai-agent-audit-log-integrity` (storage).
Audited - tomevault-io Bundle Pineconefull Text Search
Create, ingest into, and query a Pinecone full-text-search (FTS) index using the preview API (2026-01.alpha, public preview). Use when the user or agent asks to build a text search index on Pinecone, add dense or sparse vector fields, ingest documents, construct score_by clauses (text / query_string / dense_vector / sparse_vector), or compose with text-match filters ($match_phrase / $match_all / $match_any). Ships `scripts/ingest.py` for safe bulk ingestion (batch_upsert + error inspection + readiness polling); query construction is documented inline in this skill — write `documents.search(...)` calls directly, validated against `pc.preview.indexes.describe(...)` output. Use when this capability is needed.
- tomevault-io Bundle Steelmorgan 1c AI Sandbox Client Server 1c AI Sandbox Client
Agent Git Workflow (Sandbox)
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 kevintsengtw--dotnet-testing-agent-skills--dotnet-testing-unit-test-fundamentals, kite-ai-agent-smart-wallet-permissionless-protocol, kite-ai-agent-wallet-full-stack-universal-protocol. 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.