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 Tdd Diagnose複雑なバグの並列仮説調査。Subagent/Agent Teams両モード対応。「原因調査」「investigate」「diagnose」で起動。 Use when this capability is needed.
- tomevault-io Bundle Tdd Parallel
クロスレイヤー並列開発オーケストレータ。Agent Teamsでレイヤー別にRED/GREEN/REFACTORを並列実行。「parallel」「並列開発」で起動。 Use when this capability is needed.
- tomevault-io Bundle Box AI Agent
Create, update, or invoke a persistent Box AI Studio agent for memory recall. The "memory librarian" agent has locked instructions ("answer only from the indexed workspace, cite file IDs, never speculate"). Enterprise Advanced only. Use when the user wants a fixed-behavior AI assistant over their memory workspace, with locked guardrails instead of ad-hoc prompts. Use when this capability is needed.
- tomevault-io Bundle Context7 Usage
This skill should be used when the user asks to "check documentation", "latest API", "library docs", "context7", or needs up-to-date library documentation. Provides Context7 MCP usage patterns. Use when this capability is needed.
- tomevault-io Bundle Deep Researcher
Parallel multi-agent research with citations. Use when conducting deep research, competitive analysis, or investigating complex topics. Use when this capability is needed.
- tomevault-io Bundle Do
Classify user requests and route to the correct agent + skill. Primary entry point for all delegated work. Use when this capability is needed.
- tomevault-io Bundle Nq Rdl Agent Skills Rust Explain
Rust Explain — Read & Navigate Rust Code
- tomevault-io Bundle Reflect Performance Review
Reflect, Evaluate, Fine-tune, Learn, Evolve, Correct, Transform — nightly automated performance review Use when this capability is needed.
- tomevault-io Bundle Cudaq Guide
CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications. Use when this capability is needed.
- tomevault-io Bundle Browsing
Use when you need direct browser control - teaches Chrome DevTools Protocol for controlling existing browser sessions, multi-tab management, form automation, and content extraction via use_browser MCP tool
- tomevault-io Bundle Gitbutler Multi Agent
This skill should be used when coordinating multiple AI agents working concurrently, handling agent handoffs, transferring commits between agents, or when "multi-agent", "concurrent agents", "parallel agents", "agent collaboration", or "parallel execution" are mentioned with GitButler. Provides virtual branch patterns for parallel execution without coordination overhead. Use when this capability is needed.
- tomevault-io Bundle Stack Debug
Troubleshoots Outfitter Stack issues including Result handling, MCP problems, CLI output, exit codes, and logging. Use when debugging stack-specific issues, unexpected errors, wrong output modes, or when "debug Result", "MCP not working", "wrong exit code", or "logging issue" are mentioned. Use when this capability is needed.
- tomevault-io Bundle Dep Scan
This document describes the skill profile an AI agent should use when reviewing or modifying `dep-scan`. Use when this capability is needed.
- tomevault-io Bundle Shared Base Rules
Mandatory baseline rules for any agent. Must be loaded before any work Use when this capability is needed.
- tomevault-io Bundle P988744 Nlp Skills LLM Knowledge
LLM Knowledge - 知識庫
- tomevault-io Bundle Dna Builder Script MCP Debug
Use when an AI agent needs to debug dna-builder script runtime through the script MCP server, including running/stopping scripts, checking runtime state, reading status/console, finding the default script directory, and iterating a closed-loop workflow from single-frame capture to state-machine tuning.
- tomevault-io Bundle Parfenovvs Lazylogcat Lazylogcat
lazylogcat (AI agent guide)
- tomevault-io Bundle Limps Planning
Guide for using limps MCP tools to plan, track, and update work across plans and agents. Use when this capability is needed.
- tomevault-io Bundle Paulkinlan Co Do Code Simplifier
Code Simplifier Agent
- tomevault-io Bundle Bump Deps
This skill should be used when the user asks to "update dependencies", "update npm packages", "bump dependencies", "upgrade node packages", "check for outdated packages", "update package.json", or mentions dependency updates, npm/pnpm/yarn/bun package upgrades, or taze CLI usage. Use when this capability is needed.
- tomevault-io Bundle Petrovc AI Agent Kit Code Review
Code Review Skill
- tomevault-io Bundle Bci Colored Operad
Brain-Computer Interface with colored operad security boundaries. Maximally isolated EEG/neural data processing via VM→Container→Process enclosure with GF(3) conservation for Agent-O-Rama neural pathways. Use when this capability is needed.
- tomevault-io Bundle Plurigrid Asi Browser Navigation
Browser Automation with agent-browser
- tomevault-io Bundle Catcolab Decapodes
CatColab Decapodes - Discrete Exterior Calculus for PDE modeling on meshes via Decapodes.jl integration. Model physics equations compositionally with automatic code generation. Use when this capability is needed.
- tomevault-io Bundle Plurigrid Asi Firecrawl Patterns
Firecrawl MCP Skill
- tomevault-io Bundle Pre Agent Ontology
Pre-Agent Ontology Skill Use when this capability is needed.
- tomevault-io Bundle Posbright Quantia AI Agent Debug
AI Agent 调试与诊断
- tomevault-io Bundle Furedea Agent Harness Git Workflow
Git Workflow
- tomevault-io Bundle Mithril Cache Agent
Build mithril-cache for torch.compile caching. Use when implementing content-addressable storage, cache keys, eviction, or framework hooks. Use when this capability is needed.
- tomevault-io Bundle Mithril Dedup Agent
Build mithril-dedup for ML dataset deduplication. Use when implementing MinHash, LSH, clustering, or document I/O. Use when this capability is needed.
- tomevault-io Bundle Get Time
Get the current local time in various formats. Use when the user asks for the current time, what time it is, the date, or needs timestamp information. Works across claude.ai web, Claude Desktop, and Claude Code environments. Use when this capability is needed.
- tomevault-io Bundle Mcdevtool
当用户希望使用 MCDK-MCP 对网易 Minecraft 基岩版 Addon、Python2 Mod、UI、玩法逻辑或资源效果进行测试、回归验证、日志分析时，使用本 Skill。 Use when this capability is needed.
- tomevault-io Bundle Graysurf Agent Kit API Test Runner
API Test Runner (REST + GraphQL)
- tomevault-io Bundle Macos Agent Ops
Use Homebrew-installed macos-agent to run repeatable app automation checks and routine tasks on macOS. Use when this capability is needed.
- tomevault-io Bundle Creatorskill
Create or update Pi prompt templates and Agent skills from a short user brief. Produces minimal, well-structured SKILL.md or prompt files that follow Agent Skills best practices. Use when this capability is needed.
- tomevault-io Bundle Autosnippet Guard
Guard checks code against project Recipe standards via MCP tool autosnippet_guard (auto-routes by code/files params). Use when the user wants to audit, lint, or verify code compliance. 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 tdd-diagnose, tdd-parallel, box-ai-agent. 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.