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 Agent Context SystemPersistent local-only memory for AI coding agents. AGENTS.md (committed) + .agents.local.md (gitignored) = context that persists across sessions. Read both at start, update scratchpad at end, promote stable patterns over time. Use when this capability is needed.
- tomevault-io Bundle Angelburgosrosado Hermes Agent Git Workflow
Git Workflow
- tomevault-io Bundle Blocklet Url Analyzer
Analyze Blocklet Server related URLs, identify their type (daemon/service/blocklet), and locate the corresponding development repository. Supports analysis of IP DNS domains and regular domains. Use when this capability is needed.
- tomevault-io Bundle Prompt Mastery
This skill should be used when the user asks to "generate an image", "create an image", "optimize a prompt", "improve my prompt", "make my prompt better", mentions "nanobanana", "image prompt", "prompt engineering for images", or needs guidance on crafting professional AI image prompts. Provides the 6 core rules from analyzing 1,186 viral prompts. Use when this capability is needed.
- tomevault-io Bundle Az9713 Claude Code Agent Swarm Task Manager
Task Manager CLI
- tomevault-io Bundle Activerecord
This skill should be used when the user asks about "ActiveRecord", "database queries", "associations", "validations", "migrations", "scopes", "callbacks", "N+1 queries", "eager loading", "includes", "joins", "eager_load", "preload", "database optimization", "model relationships", "has_many", "belongs_to", "has_one", "polymorphic associations", "pluck", "exists", or needs guidance on database-related Rails topics. Use when this capability is needed.
- tomevault-io Bundle Building Router
Router for 3D building game mechanics in Three.js. Use when creating survival games, sandbox builders, base builders, or any game with player-constructed structures. Routes to 9 specialized skills for performance, physics, multiplayer, terrain, decay, UX, platform support, and design reference. Start here for building mechanics projects. Use when this capability is needed.
- tomevault-io Bundle Form Validation
Schema-first validation with Zod, timing patterns (reward early, punish late), async validation, and error message design. Use when implementing form validation for any framework. The foundation skill that all framework-specific skills depend on. Use when this capability is needed.
- tomevault-io Bundle Gsap Sequencing
Complex GSAP timelines including labels, callbacks, nested timelines, and position parameters. Use when orchestrating multi-step animations, building animation sequences, or creating coordinated motion. Essential for cinematic animations and complex UI choreography. Use when this capability is needed.
- tomevault-io Bundle Postfx Composer
EffectComposer setup and architecture for Three.js post-processing pipelines. Use when setting up multi-pass rendering, combining effects, creating custom passes, managing render targets, or building reusable effect stacks. Foundation skill for all post-processing work. Use when this capability is needed.
- tomevault-io Bundle Router Template
Template for creating router skills. Use as a starting point when building a new router that dispatches to multiple specialized skills. Copy and customize for your domain. Use when this capability is needed.
- tomevault-io Bundle Ac Branch Pi Model
AC branch pi-model power flow equations (P/Q and |S|) with transformer tap ratio and phase shift, matching `acopf-math-model.md` and MATPOWER branch fields. Use when computing branch flows in either direction, aggregating bus injections for nodal balance, checking MVA (rateA) limits, computing branch loading %, or debugging sign/units issues in AC power flow. Use when this capability is needed.
- tomevault-io Bundle Erlang Concurrency
Use when erlang's concurrency model including lightweight processes, message passing, process links and monitors, error handling patterns, selective receive, and building massively concurrent systems on the BEAM VM.
- tomevault-io Bundle Search Attractions
Retrieve attractions by city from the bundled dataset. Use this skill when surfacing points of interest or building sightseeing suggestions for a destination. Use when this capability is needed.
- tomevault-io Bundle Search Restaurants
Retrieve restaurants by city from the bundled dataset. Use this skill when recommending places to eat or validating dining options for a destination. Use when this capability is needed.
- tomevault-io Bundle Speaker Clustering Methods
Choose and implement clustering algorithms for grouping speaker embeddings after VAD and embedding extraction. Compare Hierarchical clustering (auto-tunes speaker count), KMeans (fast, requires known count), and Agglomerative clustering (fixed clusters). Use Hierarchical clustering when speaker count is unknown, KMeans when count is known, and always normalize embeddings before clustering. Use when this capability is needed.
- tomevault-io Bundle Hardware Io
Hardware interfacing and peripheral management for Zephyr RTOS. Covers the sensor subsystem (channels, triggers, fetch/get), pin control (Pinctrl) and multiplexing, GPIO management using Devicetree specs, and SoC-level hardware configurations. Trigger when adding new hardware components, configuring pinmux, or developing sensor-based applications. Use when this capability is needed.
- tomevault-io Bundle Specialized
Specialized hardware interfaces and system reliability for Zephyr RTOS. Covers LVGL GUI development, Audio I2S/Codecs, Watchdog timers, and Fault Injection. Trigger when building human-machine interfaces (HMI), audio devices, or high-reliability mission-critical systems. Use when this capability is needed.
- tomevault-io Bundle Extension Architect
Expert system for creating and validating Gemini CLI extensions. Capable of scaffolding directory structures, generating manifests, and validating compliance with best practices. Use when this capability is needed.
- tomevault-io Bundle Blazemeter API Reference
Comprehensive reference for BlazeMeter REST APIs, including authentication, identifiers, and API endpoints. Use when working with BlazeMeter APIs for (1) Understanding BlazeMeter REST API structure, (2) Authenticating API requests, (3) Obtaining identifiers (Workspace ID, Project ID, Test ID, etc.), (4) Using Test Data API, (5) Using Cloning API, (6) Using Export API, (7) Using Service Virtualization Bulk Operations APIs, or any other API tasks. Use when this capability is needed.
- tomevault-io Bundle Blazemeter Usage Billing
Guide for BlazeMeter Usage & Billing, including credit types and charging. Use when working with usage and billing for (1) Understanding BlazeMeter credit types (VU, VUH, Tests), (2) Calculating credit consumption for different test types, or any other usage and billing tasks. Use when this capability is needed.
- tomevault-io Bundle Arxiv MCP Server
Search arXiv papers, download full text, follow citations, and run local semantic search. Use when this capability is needed.
- tomevault-io Bundle MCP Server Enhancement
Guide for safely adding new MCP tools to the AI Counsel server Use when this capability is needed.
- tomevault-io Bundle Kirby Panel And Blueprints
Designs Kirby blueprints and Panel UI, including blueprint reuse/extends, programmable blueprints, and custom Panel fields/sections/areas. Use when changing the Panel experience or schema. Use when this capability is needed.
- tomevault-io Bundle Perform Forge Review
Create AI-assisted code reviews on GitHub, GitLab, or Forgejo. Use when asked to review a PR/MR, analyze code changes, or provide review feedback. Use when this capability is needed.
- tomevault-io Bundle Summoning The User
Use when an agent encounters a blocking decision or when proceeding without user input could lead to wasted work - helps Claude determine when to block and request user input versus making reasonable assumptions
- tomevault-io Bundle Butterbase
AI-native, open-source backend-as-a-service with a built-in Model Context Protocol server. Postgres, auth, storage, functions, AI gateway. Use when this capability is needed.
- tomevault-io Bundle Cacheforge AI Cacheforge Skills Rug Checker
Rug Checker — Agent Skill Definition
- tomevault-io Bundle Ccw CLI Tools
CLI tools execution specification (gemini/claude/codex/qwen/opencode) with unified prompt template, mode options, and auto-invoke triggers for code analysis and implementation tasks. Supports configurable CLI endpoints for analysis, write, and review modes. Use when this capability is needed.
- tomevault-io Bundle Erewok Bmo Agent Setup Documentation Driver
Documentation Driver
- tomevault-io Bundle Agent Docs Writing
Use when reading, creating, or updating agent documentation, module docs, roadmaps, or AGENTS.md. Understands the full .augment/, agents/, and copilot-instructions structure.
- tomevault-io Bundle Ontology Engineering
Build, validate, and govern RDF/OWL ontologies using the Open Ontologies MCP server. Use when the user asks to create, modify, query, or manage ontologies, knowledge graphs, or RDF data. Use when this capability is needed.
- tomevault-io Bundle Sui Architect
Use when planning SUI Move architecture, generating technical specs, or designing object/module structure before writing code. Triggers on "design", "architect", "plan the contracts", "object model", "module structure", "how should I structure", or any SUI system design task. For new projects from scratch, use sui-full-stack (which calls this skill at Phase 1). For ecosystem tool/stack selection (Walrus vs IPFS, zkLogin vs Passkey), use sui-tools-guide.
- tomevault-io Bundle Cursor Custom Prompts
Create effective custom prompts for Cursor AI using project rules, prompt Use when this capability is needed.
- tomevault-io Bundle Langchain Deep Agents
Build a LangGraph 1.0 Deep Agent \u2014 planner + subagents + virtual\ Use when this capability is needed.
- tomevault-io Bundle Graph Thinking
Mental model for visualizing complex relationships and connections between 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 agent-context-system, angelburgosrosado--hermes-agent--git-workflow, blocklet-url-analyzer. 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.