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 Pydantic AI Agent CreationCreate PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation. Use when this capability is needed.
- tomevault-io Bundle Generate Wrapper
Generate production-ready CLI wrapper code for an MCP server following progressive disclosure patterns Use when this capability is needed.
- tomevault-io Bundle Generate Prompt
Generates reusable Prompt Template files (.github/prompts/*.prompt.md) with variable substitution for ad-hoc, high-frequency tasks. Use when the user needs quick, repeatable prompts for common operations (explain code, fix bug, add tests, refactor, document). Creates templates with handlebars variables, optimized context structure, and strict output constraints. Not for complex workflows (use skills) or persistent roles (use agents).
- tomevault-io Bundle Cavit99 Mlx LLM Cheatsheet Mlx LLM Cheatsheet
MLX
- tomevault-io Bundle Handoff Log Update
Append a structured entry to the handoff log when an agent completes work, is blocked, or needs to pass ownership. Use when this capability is needed.
- tomevault-io Bundle Code Reviewer Start
Non-interactive multi-agent review of the current branch vs its base. Supports --delta (only new commits/changes since last review) and --full (whole branch). Runs Claude/Codex/Gemini/opencode in parallel, arbiter synthesises results, validates findings.json, appends the ledger, writes FINAL_REVIEW_RESULTS.md, and hands off to the main session with a structured menu. Use when this capability is needed.
- tomevault-io Bundle Charleshoskinson Danceswithclaws Coding Agent
Coding Agent (bash-first)
- tomevault-io Bundle Orchestra Cross Agent Sync
Coordinate consistent behavior across heterogeneous agents (Claude, Copilot, Codex, Cursor, Windsurf, Gemini, Antigravity) using a shared source-of-truth model. Use when this capability is needed.
- tomevault-io Bundle Confighub Cub Scout AI Agent Readonly Context
ai-agent-readonly-context
- tomevault-io Bundle Curating Context
Produces a public handoff document (committed, tone-firewalled, token-budgeted) and captures private context for future sessions. Use when wrapping up a session, switching focus, handing off to another agent or person, saving progress before context is lost, or when someone says "let's write a handoff". Use when this capability is needed.
- tomevault-io Bundle Editorial Review
Runs deterministic quality gates (token count, readability, completeness via bito) and agent-based editorial judgment (conference-talk test, tone drift, assumed context) on documentation artifacts. Use before committing docs, when reviewing written artifacts for quality or tone, when checking if documentation is ready to ship, or as the final gate in any writing skill's workflow.
- tomevault-io Bundle Agent Design Best Practices
Best practices for designing Claude Code agent files (.claude/agents/*.md). This skill should be used when writing or reviewing agent markdown files to ensure proper design with focused domains, correct tool access, reusable definitions, and separation of capabilities from lifecycle. Combines Anthropic's official guidance with battle-tested patterns from agent team usage. Use when this capability is needed.
- tomevault-io Bundle Optimize Classifier
Analyze your Model Matchmaker override patterns and tune the local classifier to match your preferences. Use after collecting 50+ recommendations. Use when this capability is needed.
- tomevault-io Bundle Sp Instructor Agent
Use when a user provides a vague or draft prompt and needs a SMART POLE Instructor to teach, diagnose SP-flaws, coach follow-up reasoning, and optionally produce a final optimized prompt on request.
- tomevault-io Bundle Cyanheads Git MCP Server Release And Publish
Preconditions
- tomevault-io Bundle Goap Agent
Invoke for complex multi-step tasks requiring intelligent planning and multi-agent coordination. Use when tasks need decomposition, dependency mapping, parallel/sequential/swarm/iterative execution strategies, or coordination of multiple specialized agents. Use when this capability is needed.
- tomevault-io Bundle Loop Agent
Execute workflow agents iteratively for refinement and progressive improvement until quality criteria are met. Use when tasks require repetitive refinement, multi-iteration improvements, progressive optimization, or feedback loops until convergence. Use when this capability is needed.
- tomevault-io Bundle Dance Cmdr Claude Swarm Workflow Swarm Spark
Swarm-Spark Executor — Agent Profile Injection
- tomevault-io Bundle Darylmcd Roslyn Backed MCP MCP Server Stress
Darylmcd Roslyn Backed Mcp Mcp Server Stress
- tomevault-io Bundle Dnd5e Srd
Retrieval-augmented generation (RAG) skill for the D&D 5e System Reference Document (SRD). Use when answering questions about D&D 5e core rules, spells, combat, equipment, conditions, monsters, and other SRD content. This skill provides agentic search-based access to the SRD split into page-range markdown files. Use when this capability is needed.
- tomevault-io Bundle Davepoon Buildwithclaude Docusign Automation
DocuSign Automation via Rube MCP
- tomevault-io Bundle Davepoon Buildwithclaude Telegram Automation
Telegram Automation via Rube MCP
- tomevault-io Bundle Autogpt Agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems. Use when this capability is needed.
- tomevault-io Bundle Fastmcp Server
Complete guide for building MCP servers with FastMCP 3.0 - tools, resources, authentication, providers, middleware, and deployment. Use when creating Python MCP servers or integrating AI models with external tools and data. Use when this capability is needed.
- tomevault-io Bundle Ddunnock Claude Plugins Streaming Output MCP
Streaming Output MCP Skill
- tomevault-io Bundle Debs Obrien Learn Agent Skills Readme Wizard
README Wizard
- tomevault-io Bundle Deepgram Rust Conversational Stt
Use when implementing Deepgram Flux conversational STT from the Rust SDK, including flux_request APIs, turn events, FluxResponse handling, and turn-detection tuning for voice-agent-style pipelines.
- tomevault-io Bundle Demerzels Lab Elsamultiskillagent Base Agent
Base Chain Trading Agent
- tomevault-io Bundle Bort Agent
Interact with BORT AI agents on BNB Chain via BAP-578. Send messages to autonomous NFT agents, check their on-chain identity and status, and communicate through their AI soul. Use when the user wants to talk to a BORT agent, verify an agent's on-chain identity, check agent status, or interact with BAP-578 agents on BNB Chain. Use when this capability is needed.
- tomevault-io Bundle Moltmotion
Molt Motion Pictures platform skill. Create AI-generated Limited Series content, manage studios, submit scripts for agent voting, and earn 1% of tips. Wallet-based auth, x402 payments. Use when this capability is needed.
- tomevault-io Bundle Moltslist
Agent marketplace for trading services, tools, and tasks using virtual credits. Use when this capability is needed.
- tomevault-io Bundle Relayplane
Intelligent AI model routing proxy. Cut API costs 50-80% with automatic model selection. Haiku for simple tasks, Opus for complex ones. Use when this capability is needed.
- tomevault-io Bundle Skillcraft
Create, design, and package Clawdbot skills. Use when asked to "make/build/craft a skill for X", or when extracting ad-hoc functionality ("turn my script/agent instructions/library into a skill"). Applies Clawdbot-specific integration concerns (tool calling, memory, message routing etc.) to build reusable skills that compose. Use when this capability is needed.
- tomevault-io Bundle Anonymize Doc
Detect and anonymize PII (SSN, cards, emails, phones, names) and business data (companies, revenue, costs, pricing). Use when handling sensitive files or user requests anonymization. Check-only or full anonymization with 5 strategies (mask/hash/pseudo/token/mixed). GDPR/HIPAA aware. Use when this capability is needed.
- tomevault-io Bundle Digital Stoic Org Agent Skills Frame Problem
Frame
- tomevault-io Bundle Digital Stoic Org Agent Skills Openspec Sync
OpenSpec Sync
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 pydantic-ai-agent-creation, generate-wrapper, generate-prompt. 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.