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 Neverinfamous Memory Journal MCP GRAPHQLGraphQL Best Practices
- tomevault-io Bundle Mcts Simulate
Execute the SIMULATION (rollout) phase of MCTS using LLM as heuristic policy to evaluate a node Use when this capability is needed.
- tomevault-io Bundle Nholder88 AI Agent Workflows Impl Csharp
C# / .NET Implementation
- tomevault-io Bundle Nholder88 AI Agent Workflows Impl Python
Python Implementation
- tomevault-io Bundle Writing User Stories
Use when an agent needs to write user stories for a project
- tomevault-io Bundle Multi LLM Consult
Consult external LLMs (Gemini, OpenAI/Codex, Qwen) for second opinions, alternative plans, independent reviews, or delegated tasks. Use when a user asks for another model's perspective, wants to compare answers, or requests delegating a subtask to Gemini/Codex/Qwen. Use when this capability is needed.
- tomevault-io Bundle Cpmparty
Multi-perspective discussion with named agent personas. Bring your whole team into one conversation — PM, Architect, Developer, UX Designer, Test Engineer, and more. Use for brainstorming, decision-making, or exploring trade-offs from diverse viewpoints. Triggers on "/cpm:party". Use when this capability is needed.
- tomevault-io Bundle Design Experiment
Plan LLM fine-tuning and evaluation experiments. Use when the user wants to design a new experiment, plan training runs, or create an experiment_summary.yaml file. Use when this capability is needed.
- tomevault-io Bundle Migration Generator
Create database migrations from model changes, schema diffs, and migration best practices. Use when this capability is needed.
- tomevault-io Bundle Cyanheads MCP TS Core Release And Publish
Preconditions
- tomevault-io Bundle Lc Curate Context
Create optimized llm-context rules for specific tasks by analyzing codebase content and generating minimal file selection patterns Use when this capability is needed.
- tomevault-io Bundle General
General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. Use when you need to perform comprehensive searches across codebase, find files that are not obvious in first few searches, or execute multi-step tasks requiring multiple tools and approaches. Use when this capability is needed.
- tomevault-io Bundle Archon Manager
Master Archon MCP for strategic project management, task tracking, and knowledge base operations. The strategic layer (WHAT/WHEN) that coordinates with Skills (HOW). Use when managing projects, tracking tasks, querying knowledge bases, or implementing the Archon+Skills two-layer architecture. Use when this capability is needed.
- tomevault-io Bundle Agent Patterns
This skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination", "parallel agents", "report format", "agent communication", or needs to understand how agents coordinate within the sprint system. Use when this capability is needed.
- tomevault-io Bundle Davepoon Buildwithclaude Canva Automation
Canva Automation via Rube MCP
- tomevault-io Bundle Openai Docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.
- tomevault-io Bundle Statsmodels
Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis. Use when this capability is needed.
- tomevault-io Bundle Clawkey
Verifiable human ownership for OpenClaw agents. Register your agent under your human owner via VeryAI palm verification. Use when this capability is needed.
- tomevault-io Bundle Comanda
Generate, visualize, and execute declarative AI pipelines using the comanda CLI. Use when creating LLM workflows from natural language, viewing workflow charts, editing YAML workflow files, or processing/running comanda workflows. Supports multi-model orchestration (OpenAI, Anthropic, Google, Ollama, Claude Code, Gemini CLI, Codex). Use when this capability is needed.
- tomevault-io Bundle Demerzels Lab Elsamultiskillagent Fast Io
Fast.io MCP Server
- tomevault-io Bundle Demerzels Lab Elsamultiskillagent Raglite
RAGLite — a local RAG cache (not a memory replacement)
- tomevault-io Bundle Pm Orchestrator
Central orchestrator for multi-agent development. Manages task distribution, context passing, iteration cycles, and Gantt scheduling. Use this skill when coordinating team work, assigning tasks, or managing project iterations. Use when this capability is needed.
- tomevault-io Bundle Checkpoint Commit
Slash command that creates governance checkpoint commits. Analyzes changes, validates .gitignore, and creates formatted checkpoint commits linked to Change Requests. Trigger with /checkpoint-commit [CR-XXXX] [summary]. Use when this capability is needed.
- tomevault-io Bundle Seedance Prompt Zh
为即梦 Seedance 2.0 多模态AI视频生成模型撰写高质量提示词。当用户需要使用文本、图片、视频、音频等多模态输入创作视频提示词时触发。涵盖@引用语法、运镜复刻、特效模仿、视频延长、视频编辑、音乐卡点、电商广告、短剧创作、科普教育等场景。 Use when this capability is needed.
- tomevault-io Bundle Debug Prod Issues
Debug production issues on Vercel using logs, database inspection, and proper deployment waiting Use when this capability is needed.
- tomevault-io Bundle Implementing Defense In Depth
AI agent designs layered security architecture with multiple independent protective barriers ensuring no single point of failure. Use when building security systems, reviewing architecture, or hardening applications. Use when this capability is needed.
- tomevault-io Bundle Test Enforcement
Use when working with the agent enforces mandatory test completion before any task or feature can be marked as done, ensuring code quality through strict validation gates and evidence-based completion criteria.
- tomevault-io Bundle Audit Quality
Triggered when user asks to audit code quality, assess maintainability, or review overall code quality. Automatically delegates to the quality-auditor agent. Use when this capability is needed.
- tomevault-io Bundle Handle Errors
Triggered when user asks to standardize error handling, create error types, improve error messages, or implement error recovery. Automatically delegates to the error-handler agent. Use when this capability is needed.
- tomevault-io Bundle Improve Types
Triggered when user asks to create TypeScript types, improve type safety, handle complex types, or ensure type consistency. Automatically delegates to the type-specialist agent. Use when this capability is needed.
- tomevault-io Bundle Integrate API
Triggered when user asks to integrate third-party APIs, handle API authentication, manage rate limiting, or create API clients. Automatically delegates to the api-integrator agent. Use when this capability is needed.
- tomevault-io Bundle Navigate Code
Triggered when user asks to navigate codebase, find code patterns, trace dependencies, map code relationships, or understand code structure. Automatically delegates to the code-navigator agent. Use when this capability is needed.
- tomevault-io Bundle Research Docs
Triggered when user asks to research library documentation, look up API references, find framework docs, or needs technical documentation. Uses Context7 MCP. Automatically delegates to the docs-researcher agent. Use when this capability is needed.
- tomevault-io Bundle Resolve Build
Triggered when user asks to resolve build errors, fix compilation issues, or troubleshoot build problems. Automatically delegates to the build-error-resolver agent. Use when this capability is needed.
- tomevault-io Bundle AI Agent Config
Manage AI coding skills across platforms (Claude Code, Antigravity, Cursor, Windsurf) using ai-agent-config CLI. Use when the user wants to sync skills to/from GitHub, install to multiple platforms, add custom skill sources, or configure skill management settings. Use when this capability is needed.
- tomevault-io Bundle API GRAPHQL
Work with Shopify GraphQL APIs including Admin API and Storefront API. Use this skill for querying and mutating Shopify data, managing products, orders, customers, handling pagination, working with metafields, and understanding rate limits. Covers authentication, queries, mutations, and webhooks. 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 neverinfamous--memory-journal-mcp--graphql, mcts-simulate, nholder88--ai-agent-workflows--impl-csharp. 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.