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 Bootstrap MonorepoAutonomous polyglot monorepo bootstrap meta-prompt. TRIGGERS - new monorepo, polyglot setup, scaffold Python+Rust+Bun, monorepo from scratch. Use when this capability is needed.
- tomevault-io Bundle Claude Md Writer
Escribe y mejora archivos CLAUDE.md siguiendo best practices de Anthropic. Este skill se activa cuando el usuario dice "crear CLAUDE.md", "mejorar CLAUDE.md", "actualizar CLAUDE.md", "revisar CLAUDE.md", "escribir instrucciones del proyecto", "create CLAUDE.md", "improve CLAUDE.md", "review CLAUDE.md", "write project instructions", "optimize docs for Claude", "auditar CLAUDE.md", "audit CLAUDE.md", "limpiar CLAUDE.md", "dead weight", o configura un nuevo repositorio. Use when this capability is needed.
- tomevault-io Bundle Library Skills
Use Library Skills to discover, install, refresh, repair, check, and manage agent skills from installed packages. Use when this capability is needed.
- tomevault-io Bundle Tokamak Network Agent Skills Thanos L2
Thanos L2 Development
- tomevault-io Bundle Trade It MCP
Trade It connects MCP clients directly to the user's brokerage accounts. Use the tools below to search assets, review account balances, and place real trades through natural language. Use when this capability is needed.
- tomevault-io Bundle Add Opencode Model
REQUIRED when adding OpenCode Zen models - provides a script that fetches accurate context, max tokens, pricing, and capabilities from the API. Use this skill whenever the user asks to add, register, or configure a new OpenCode Zen model. Do NOT guess model specifications—always fetch real data from the API. Use when this capability is needed.
- tomevault-io Bundle Weather Query
Answer weather queries with a fixed demo response. Use when this capability is needed.
- tomevault-io Bundle Gz Session Handoff
Create and resume session handoff documents for agent context preservation across engineering sessions. Use when this capability is needed.
- tomevault-io Bundle U9401066 Automl Stat MCP Code Reviewer
程式碼審查技能
- tomevault-io Bundle U9401066 Automl Stat MCP Ddd Architect
DDD 架構輔助技能
- tomevault-io Bundle U9401066 Automl Stat MCP Git Precommit
Git 提交前工作流（編排器）
- tomevault-io Bundle Update Claude Learnings
Extract learnings about Claude Code behavior from a session and add them to the project's CLAUDE.md file. Use for behavioral rules, workflow patterns, and project-specific instructions that apply to the main Claude Code agent. Invoke via /update-claude-learnings after sessions revealing behavioral patterns. Use when this capability is needed.
- tomevault-io Bundle Plan Revision
规划修订导航。触发：用户通知"analysis-agent已分析完成"或需要plan-agent查看analysis-agent复审结果并修订预定清单时使用；评估analysis-agent分析结果并修订draft-plan.md。 Use when this capability is needed.
- tomevault-io Bundle Create Grader
Create a multi-layer grader (MultiGraderDefinition) for evaluating an agent given its source code. Use when user wants to build evaluation criteria for an agent. Use when this capability is needed.
- tomevault-io Bundle Vibiz MCP
How to use the Vibiz MCP server from Claude Code — the 40 tools, the target.vibiz arg, the OAuth auth flow, and the post-media-to-social workflow. Use when this capability is needed.
- tomevault-io Bundle Describe Changes
Describe very high level changes required to implement discussed functionality (functionality, test, docs) Use when this capability is needed.
- tomevault-io Bundle Gh Issue Publish
Publish a GitHub issue from a markdown file in temp/gh_issues/ created by gh-issue-bug or gh-issue-improvement skills Use when this capability is needed.
- tomevault-io Bundle Web3 Blockchain Development
Production-grade Web3 development with Solidity smart contracts, ethers.js/web3.js integration, DApp architecture, security patterns, and AI-enhanced blockchain development (ChatWeb3, Aider + Gemini 2024) Use when this capability is needed.
- tomevault-io Bundle Inquiry Prompts
Generate research agent prompts from INQ QUESTION.md files for Phase 1 deliberation Use when this capability is needed.
- tomevault-io Bundle Remote Browser
Controls a local browser from a sandboxed remote machine. Use when the agent is running in a sandbox (no GUI) and needs to navigate websites, interact with web pages, fill forms, take screenshots, or expose local dev servers via tunnels. Use when this capability is needed.
- tomevault-io Bundle Comment Audit
Audit code comments and agent-facing docs against a repository's comment policy. Use when asked to review comments, audit stale or redundant comments, check AIDEV-NOTE anchors, evaluate comment-policy.md / CLAUDE.md / AGENTS.md compliance, or inspect changed files for comments that should be kept, deleted, updated, or investigated. Use when this capability is needed.
- tomevault-io Bundle Analyzing Domain Model
Use when analyzing domain entities, value objects, aggregates, and business rules encoded in the model
- tomevault-io Bundle Colin4k1024 Tsp Agent Patterns Catalog
Agent Patterns Catalog
- tomevault-io Bundle Cui Documentation
General documentation standards for README, AsciiDoc, and technical documentation Use when this capability is needed.
- tomevault-io Bundle Liaison
Translate multi-agent ecosystem activity into human-readable status briefings, decision requests, and progress summaries. Use for 'status update', 'brief me', 'what happened', 'summarize progress'. Use when this capability is needed.
- tomevault-io Bundle Agent Spec Builder
Build a Prompt Hardener agent_spec.yaml from an existing codebase (from-code) or through an interactive interview (from-questions). Use when the user wants to create, generate, or scaffold an agent spec, or when they mention agent_spec.yaml creation. Generates agent_spec.yaml, evidence.md, and open_questions.md with confidence tracking and evidence trails. Use when this capability is needed.
- tomevault-io Bundle Bmad Method
Business Model and Architecture Design methodology for aligning technical architecture with business model sustainability and scalability Use when this capability is needed.
- tomevault-io Bundle Dagba IOS MCP Swift Concurrency Avdlee
Swift Concurrency
- tomevault-io Bundle Orchestration Template
Reference template for multi-agent orchestrated skills. Use as a pattern when creating complex skills that need parallel execution. Use when this capability is needed.
- tomevault-io Bundle Diffdock
Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction. Use when this capability is needed.
- tomevault-io Bundle Prompt Improver
Transform any rough prompt, task description, or job into an optimized AI instruction prompt. Use when users ask to "improve this prompt", "make this better for an AI", "optimize this for Claude/GPT", or provide raw instructions that need refinement into a well-structured prompt following best practices. Use when this capability is needed.
- tomevault-io Bundle Kud
Interactive crypto deep-research framework with agent-agent and human-agent collaboration for superior research outcomes Use when this capability is needed.
- tomevault-io Bundle Flutter Code Gen
Run Dart build_runner for code generation of Mappable classes and JSON serialization. Use after adding or modifying data model classes that require generated code. Use when this capability is needed.
- tomevault-io Bundle Capture
Quick capture to GTD inbox from CLI or natural language Use when this capability is needed.
- tomevault-io Bundle Swiftui View Refactor
Refactor and review SwiftUI view files with strong defaults for small dedicated subviews, MV-over-MVVM data flow, stable view trees, explicit dependency injection, and correct Observation usage. Use when cleaning up a SwiftUI view, splitting long bodies, removing inline actions or side effects, reducing computed `some View` helpers, or standardizing `@Observable` and view model initialization patterns. Use when this capability is needed.
- tomevault-io Bundle Ollama Inference Test
Test and benchmark local Ollama inference - status, test, benchmark. Check model availability, run generation/classification tests, measure response time. Use when user says "test Ollama", "Ollama status", "benchmark inference". 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 bootstrap-monorepo, claude-md-writer, library-skills. 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.