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 Memory UltimateComplete memory system for AI agents. Human-like architecture with daily logs, sleep consolidation, SQLite + FTS5, importers for WhatsApp/ChatGPT/VCF. Everything an agent needs to remember across sessions. Use when this capability is needed.
- tomevault-io Bundle Kentoshimizu Sw Agent Skills Sh Style Guide
SH Style Guide
- tomevault-io Bundle Kumo Issue
File a GitHub issue on the kumo-coding-agent repo to report a gap, bug, or feature request for the Kumo data science agent (context docs, skills, or verticals). Use when someone says "report a problem with the agent", "the agent got something wrong", "file an issue", or "request a new skill". Use when this capability is needed.
- tomevault-io Bundle Libgdx Asset Manager
Use when writing libGDX Java/Kotlin code involving AssetManager — loading assets (Texture, TextureAtlas, Sound, Music, BitmapFont, Skin, Model, TiledMap, ParticleEffect, ShaderProgram, I18NBundle), async loading screens, reference counting, screen transitions, custom loaders, or FreeType font loading via AssetManager. Use when debugging assets not loading, double-dispose crashes, missing textures after Android resume, or loading screen patterns.
- tomevault-io Bundle Marketplace Optimizer
Optimizes this Claude Code marketplace using specialized sub-agents. Each agent is an expert for one element type (skills, commands, agents, hooks, mcp) and loads only relevant documentation. A marketplace agent validates cross-references and latest features. Triggers on "optimize marketplace", "sync with best practices", or when user wants to improve plugin quality. Use when this capability is needed.
- tomevault-io Bundle Run Python Safely
Execute Python code safely by checking for dangerous operations first. ALWAYS use when running agent-generated Python code. Use when this capability is needed.
- tomevault-io Bundle Agent Line Bot
Complete personal finance management. Track expenses, recurring subscriptions, savings goals, multi-currency support, and smart insights. Use when this capability is needed.
- tomevault-io Bundle Agent Friendly Commands
Use these when you want low-noise lint/test output (good for LLM/CI logs) while staying aligned with repo policy. Use when this capability is needed.
- tomevault-io Bundle Paw Planning
Implementation planning activity skill for PAW workflow. Creates phased implementation plans with clear success criteria, documentation phase planning, and strategic architectural descriptions. Use when this capability is needed.
- tomevault-io Bundle Paw Workflow
Reference documentation for PAW multi-phase implementation workflows. Provides activity tables, artifact structure, stage guidance, and PR routing patterns. Workflow enforcement rules are in PAW.agent.md. Use when this capability is needed.
- tomevault-io Bundle Hooks Test
Test skill demonstrating hooks functionality. Shows PreToolUse, PostToolUse, and Stop hooks in action. Use when this capability is needed.
- tomevault-io Bundle Lucaswall Adva Administracion Tools Improve
Tools Improve - Agent, Skill & CLAUDE.md Assistant
- tomevault-io Bundle Performance Tracking
Track agent, skill, and model performance metrics for optimization. Use when measuring agent success rates, tracking model latency, analyzing routing effectiveness, or optimizing cost-per-task. Trigger keywords - "performance", "metrics", "tracking", "success rate", "agent performance", "model latency", "cost tracking", "optimization", "routing metrics". Use when this capability is needed.
- tomevault-io Bundle Proxy Mode Reference
Reference guide for using external AI models via claudish CLI. Use when running multi-model reviews, understanding how /team invokes external models, or debugging external model integration issues. Includes routing prefixes for MiniMax, Kimi, GLM direct APIs. Use when this capability is needed.
- tomevault-io Bundle Task External Models
Quick-reference for using external AI models in orchestration workflows. External models are invoked via Bash+claudish CLI (deterministic, 100% reliable). Use when confused about how to run external models, "claudish with Bash", "external model in /team", or "how to specify external model". Trigger keywords - "external model", "claudish", "Bash claudish", "external LLM", "model parameter". Use when this capability is needed.
- tomevault-io Bundle Runbook Authoring
Runbook authoring workflow for clear, executable operational procedures for on-call responders. Use when incident response, rollback, failover, or maintenance steps must be documented before production use; do not use for production feature logic design. Use when this capability is needed.
- tomevault-io Bundle Kiraneswaran Engineering Skills Agent Workflow
---
- tomevault-io Bundle Kotlin Kotlin Agent Skills Kotlin Agent Skills
kotlinx.collections.immutable 0.5.x Migration
- tomevault-io Bundle Lambdatest Agent Skills Openapi Spec Generator
OpenAPI / Swagger Specification Generator
- tomevault-io Bundle Langcare Langcare MCP Fhir Care Gap Identifier
Care Gap Identifier
- tomevault-io Bundle Langcare Langcare MCP Fhir Problem List Review
Problem List Review
- tomevault-io Bundle Langcare Langcare MCP Fhir Soap Note Generator
SOAP Note Generator
- tomevault-io Bundle Inertia Types
Create TypeScript type definitions and i18n translation namespace for a Goravel entity. Maps Go model fields to TS interfaces and creates the translation JSON file. Use when this capability is needed.
- tomevault-io Bundle Env And Assets Bootstrap
Rigor Setup skill for README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for repo scanning, full orchestration, paper interpretation, final run reporting, or generic environment setup that is not tied to a specific reproduction target. Use when this capability is needed.
- tomevault-io Bundle Create Custom Agent
Prompt for creating custom agent files (.agent.md) Use when this capability is needed.
- tomevault-io Bundle Create Custom Skill
Create a new GitHub Copilot Agent Skill (SKILL.md) with an appropriate folder structure and usage guidance. Use when this capability is needed.
- tomevault-io Bundle Paw Impl Review
Implementation review activity skill for PAW workflow. Reviews implementation for quality, adds documentation, and returns structured verdict. Use when this capability is needed.
- tomevault-io Bundle Paw Plan Review
Plan review activity skill for PAW workflow. Reviews implementation plans for feasibility, completeness, and spec alignment before implementation proceeds. Use when this capability is needed.
- tomevault-io Bundle Paw Spec Review
Specification review skill for PAW workflow. Validates Spec.md against quality criteria and returns structured feedback for iteration. Use when this capability is needed.
- tomevault-io Bundle Lowyshin Giip Dev Agent Phase 6 UI Integration
Phase 6: UI Implementation + API Integration
- tomevault-io Bundle Language Runtime Selection
Use when selecting or reviewing programming language and runtime choices against workload shape, type safety, concurrency, memory behavior, deployment model, ecosystem maturity, observability, security, lifecycle, and maintainability.
- tomevault-io Bundle Claudemem Orchestration
Use when orchestrating multi-agent code analysis with claudemem. Run claudemem once, share output across parallel agents. Enables parallel investigation, consensus analysis, and role-based command mapping.
- tomevault-io Bundle Model Tracking Protocol
MANDATORY tracking protocol for multi-model validation. Creates structured tracking tables BEFORE launching models, tracks progress during execution, and ensures complete results presentation. Use when running 2+ external AI models in parallel. Trigger keywords - "multi-model", "parallel review", "external models", "consensus", "model tracking". Use when this capability is needed.
- tomevault-io Bundle Llm4s Scala
LLM4S Scala functional LLM interfaces with Effect system integration. Use when building LLM applications in Scala with ZIO or Cats Effect, implementing type-safe AI pipelines with functional error handling, creating composable prompt systems in Scala, or leveraging Scala's type system for robust AI applications. Use when this capability is needed.
- tomevault-io Bundle Mapbox Data Visualization Patterns
Patterns for visualizing data on maps including choropleth maps, heat maps, 3D visualizations, data-driven styling, and animated data. Covers layer types, color scales, and performance optimization. Use when this capability is needed.
- tomevault-io Bundle AI Hedge Fund
Run virattt/ai-hedge-fund for multi-agent analysis and convert output into a risk-defined plan. 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-memory-ultimate, kentoshimizu--sw-agent-skills--sh-style-guide, kumo-issue. 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.