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 Deepgram JS Conversational SttUse when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription. Covers `client.listen.v2.createConnection()` / `connect()`, Flux models, and turn events like `TurnInfo`. Use `deepgram-js-speech-to-text` for standard v1 ASR and `deepgram-js-voice-agent` for full-duplex assistants. Triggers include "flux", "v2 listen", "conversational STT", "turn detection", "end of turn", "EOT", and "listen.v2".
- tomevault-io Bundle Deevsdeevs Agent System Polars Expertise
Polars
- tomevault-io Bundle Minara
Minara Agent API offers crypto trading analysis, swap intent conversion, perpetual trading suggestions, and prediction market analysis. Supports API Key and x402 (pay-per-use USDC). Use when this capability is needed.
- tomevault-io Bundle Edit Tool
Creates, modifies, and orchestrates Claude Code tools (skills, agents, scripts). Use when user requests creating, updating, improving, or editing any Claude Code extension — skills, sub-agents, slash commands, script wrappers. Triggers include "create/make/new skill/command/agent/script", "tool for X", "slash command", "sub-agent", file paths with /skills/, /agents/. For plugin version bumps and release metadata, route directly to edit-plugin.
- tomevault-io Bundle Stack Detection
Detects project technology stacks by analyzing package manifests, config files, directory structures, and code patterns. Produces a structured stack profile for agent adaptation. Covers technology detection, framework identification, project type analysis. Use when this capability is needed.
- tomevault-io Bundle Cognitive Mode
Comprehensive cognitive mode management skill for the VERILINGUA x VERIX x DSPy x GlobalMOO integration. Enables automatic mode selection, frame configuration, VERIX epistemic notation, and GlobalMOO optimization. Use this skill when configuring AI behavior for specific task types, optimizing prompt engineering, or ensuring epistemic consistency in responses. Use when this capability is needed.
- tomevault-io Bundle Visual Testing
Screenshot-based visual comparison and regression testing using claude-in-chrome MCP. Captures, compares, and validates UI states to detect layout shifts, visual bugs, and design regressions across viewports. Use when this capability is needed.
- tomevault-io Bundle AI Architecture
AI application architecture - gateway, orchestration, model routing, observability, deployment patterns. Use when designing AI systems, scaling applications, or building production infrastructure. Use when this capability is needed.
- tomevault-io Bundle Edge Deployment
Edge deployment strategies including mobile optimization, embedded systems, TFLite, Core ML, and resource-constrained inference. Use when this capability is needed.
- tomevault-io Bundle Developing MCP Servers
Creates Model Context Protocol servers with tools, resources, and prompts for AI assistant integration. Use when extending Claude with custom capabilities, building AI tool integrations, or exposing APIs to AI assistants.
- tomevault-io Bundle Solving Problems
AI agent applies a 5-phase systematic framework for tackling complex problems when conventional approaches fail. Use when stuck, blocked, or troubleshooting issues. Use when this capability is needed.
- tomevault-io Bundle Workflow Config System
Use when working with the agent implements a centralized workflow configuration system for Git workflows, enabling set-once-use-everywhere automation for trunk-based development, gitflow, and github-flow patterns with integrated testing automation.
- tomevault-io Bundle Migrate Code
Triggered when user asks to migrate code, upgrade dependencies, or assist with code migrations. Automatically delegates to the migration-assistant agent. Use when this capability is needed.
- tomevault-io Bundle Research Web
Triggered when user asks to research information online, search for articles, find solutions, research companies, or gather web information. Uses Exa MCP. Automatically delegates to the web-researcher agent. Use when this capability is needed.
- tomevault-io Bundle Mixseek Team Config
MixSeekのチーム設定ファイル（team.toml）を生成します。「チームを作成」「エージェント設定を生成」「Web検索チームを作って」「分析チームを設定」といった依頼で使用してください。Leader AgentとMember Agentの構成を定義します。 Use when this capability is needed.
- tomevault-io Bundle Dungle Scrubs Agent Config Lua Standards
Lua Best Practices
- tomevault-io Bundle Claude Code Skill Development
This skill should be used when the user asks to "create a skill", "write a skill", "build a skill", or wants to add new capabilities to Claude Code. Use when developing SKILL.md files, organizing skill content, or improving existing skills. Do NOT use for plugin development, hook creation, agent creation, or slash command creation — those have dedicated skills. Use when this capability is needed.
- tomevault-io Bundle Eco2 Team Backend Chat Agent Persistence
Chat Agent Persistence Guide
- tomevault-io Bundle Te Guide
Use this skill when users ask "how does tool executor work", "how to use execute_code", "workspace API", "MCP client examples", "search_tools examples", "context-efficient patterns", or need guidance writing code for the Tool Executor sandbox.
- tomevault-io Bundle Epp
External Prompt Protocol - Cryptographically signed agent-to-agent communication Use when this capability is needed.
- tomevault-io Bundle Skill Teaching
This skill should be used when the user asks to "sync skills to agent", "share skills with agent", "push skills to target", "teach agent skills", or requests synchronizing Claude Code skills with other AI agents in the project. Use when this capability is needed.
- tomevault-io Bundle Eugene1g Agent Safehouse Agent Safehouse
Release
- tomevault-io Bundle Spawn Implementation Agents
Guide for efficient agent orchestration during implementation to conserve main agent context Use when this capability is needed.
- tomevault-io Bundle Compress Memory
Use when shrinking always-loaded memory files (AGENTS.md, CLAUDE.md, .cursorrules) via caveman grammar — refuses sensitive paths, round-trips via .original.md backup.
- tomevault-io Bundle Condense Memory
Use when shrinking always-loaded memory files (AGENTS.md, CLAUDE.md, .cursorrules) via telegraph grammar — refuses sensitive paths, round-trips via .original.md backup.
- tomevault-io Bundle Freeplay Plan
Analyze a codebase to map its LLM implementation for Freeplay migration. Examines prompts, model configs, tool use, sessions, and agent patterns. Use when user wants to understand their LLM usage, inventory prompts, plan a migration, audit LLM patterns, or before integrating with Freeplay \u2014 even if they just say 'analyze my code' or 'what LLM stuff do I have'. Use when this capability is needed.
- tomevault-io Bundle Enterprise Search Source
Manages connected MCP sources for Tandem search. Detects available sources, guides users to connect new ones, handles source priority ordering, and manages rate limiting awareness.
- tomevault-io Bundle Setup Multi Agent
Bootstrap a new project with multi-CLI agent config — drops AGENTS.md / CLAUDE.md / GEMINI.md from the cc-templates templates/ directory into a target project, patches its .gitignore, and prints verification commands. The "multi-agent" here means multi-CLI (Claude Code + Codex CLI + Gemini CLI), not multiple internal sub-agents. Use when this capability is needed.
- tomevault-io Bundle Agent Artifacts
Agent artifact placement conventions. Use when creating plans, tasks, research, reviews, brainstorms, or any agent-generated files. Ensures artifacts go to docs/.claude/ (gitignored) instead of polluting the repo. Use when this capability is needed.
- tomevault-io Bundle Gologo13 Agent Skills Add Error Handling
Add Error Handling
- tomevault-io Bundle Gologo13 Agent Skills Database Migration
Database Migration
- tomevault-io Bundle Google AI Edge Litert Torch Litert Torch
LiteRT Model Equivalence Test
- tomevault-io Bundle Memory Contract
Unified Memory Contract for Flowbaby integration. Defines when and how to retrieve and store memory. Load at session start - memory is core to agent reasoning, not optional. Use when this capability is needed.
- tomevault-io Bundle Shipyard Executing Plans
Use when you have a written implementation plan to execute, either in the current session with builder/reviewer agents or in a separate session with review checkpoints. Also use when the user says "build this", "implement this", "execute the plan", "run the plan", or when a plan file has been loaded with independent tasks suitable for agent dispatch.
- tomevault-io Bundle Flutter Animation
Implements animated effects, transitions, and motion in a Flutter app. Use when adding visual feedback, shared element transitions, or physics-based animations. Use when this capability is needed.
- tomevault-io Bundle Flutter Databases
Manages local data persistence using SQLite or other database solutions. Use when a Flutter app needs to store, query, or synchronize large amounts of structured data on the device.
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 deepgram-js-conversational-stt, deevsdeevs--agent-system--polars-expertise, minara. 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.