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 Lambdatest Agent Skills Flutter Testing SkillFlutter Testing Skill
- tomevault-io Bundle Lambdatest Agent Skills Robot Framework Skill
Robot Framework Skill
- tomevault-io Bundle Langcare Langcare MCP Fhir Referral Generator
Referral Generator
- tomevault-io Bundle Cuml Machine Learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets. Use when this capability is needed.
- tomevault-io Bundle Gemini Embed
Generate text embeddings using Google Gemini API for RAG, semantic similarity, classification, and clustering tasks. Invoke when user wants to embed text, create embeddings, or convert text to vectors with Gemini. Use when this capability is needed.
- tomevault-io Bundle Converting Mcps To Skills
Connect to MCP (Model Context Protocol) servers and create skills for repeated use. Load when a user wants to use an MCP server, connect to external tools via MCP, or when they mention MCP, model context protocol, or specific MCP servers. Use when this capability is needed.
- tomevault-io Bundle Syncing Memory Filesystem
Manage git-backed memory repos. Load this skill when working with git-backed agent memory, setting up remote memory repos, resolving sync conflicts, or managing memory via git workflows. Use when this capability is needed.
- tomevault-io Bundle Systems Cartographer
Ground-up conceptual modeling partner for complex systems. Use when asked to rethink a system's conceptual model, define core nouns and invariants, reconcile mismatched terms across APIs/UI, map lifecycles/edges, or create a shared vocabulary and boundaries for a refactor or redesign. Use when this capability is needed.
- tomevault-io Bundle Verify Release Readiness
Verify release readiness by detecting changed skills, checking version updates, and running validation scripts. Use before creating releases or publishing to marketplace. Use when this capability is needed.
- tomevault-io Bundle Provider Implementation
Implementing providers for Beluga AI v2 registries. Use when creating LLM, embedding, vectorstore, voice, or any other provider. Use when this capability is needed.
- tomevault-io Bundle Paw Review Gap
Systematically identifies gaps in correctness, safety, testing, and maintainability, categorizing findings by severity. Use when this capability is needed.
- tomevault-io Bundle Paw Transition
Workflow transition gate for PAW. Handles stage boundaries, session policy, preflight checks, and next activity determination. Use when this capability is needed.
- tomevault-io Bundle Context Fork Skill
Demonstrates forked context execution. This skill runs in an isolated sub-agent context with its own conversation history and tool access. Use when this capability is needed.
- tomevault-io Bundle Example Calculator
Use when working with a simple calculator skill demonstrating SKILL.md format
- tomevault-io Bundle Onebot Ops
OneBot (QQ/Lagrange) 渠道运维与使用规范。消息收发通过 Channel outbound 与 deliver 完成，不依赖 Agent 工具。 Use when this capability is needed.
- tomevault-io Bundle Flutter Native Interop
Interoperates with native platform APIs on Android, iOS, and the web. Use when accessing device-specific features not available in Dart or calling existing native code. Use when this capability is needed.
- tomevault-io Bundle Flutter Platform Views
Embeds native Android, iOS, or macOS views into a Flutter app. Use when integrating complex native components like maps or web views. Use when this capability is needed.
- tomevault-io Bundle Update Coding Agent Preferences
Apply persistent or repo-local coding-agent instruction changes across Codex and Claude in tandem, including related skill updates when a preference changes a skill's behavior or workflow. Use when the user asks to add, revise, or remove preferences in `AGENTS.md`, `CLAUDE.md`, or matching skill files and the change must be classified as global botfiles policy, project-local policy, or skill-specific guidance. Use when this capability is needed.
- tomevault-io Bundle Cross Plugin Detective
Use when integrating detective skills across plugins. Maps agent roles to appropriate detective skills (developer → developer-detective, architect → architect-detective). Reference this to connect agents with claudemem investigation capabilities.
- tomevault-io Bundle Task Complexity Router
Complexity-based task routing for optimal model selection and cost efficiency. Use when deciding which model tier to use, analyzing task complexity, optimizing API costs, or implementing tiered routing. Trigger keywords - "routing", "complexity", "model selection", "tier", "cost optimization", "haiku", "sonnet", "opus", "task analysis". Use when this capability is needed.
- tomevault-io Bundle Prompt Skill
Create interactive terminal prompts using questionary for user input. Use when building forms, selection menus, and confirmation dialogs. Use when this capability is needed.
- tomevault-io Bundle Prompt Dsl
Domain-specific language for categorical prompt composition with functor combinators and natural transformation operators. Use when building composable prompt templates, implementing typed prompt algebras, creating reusable prompt patterns with categorical structure, or designing prompt DSLs that preserve composition properties. Use when this capability is needed.
- tomevault-io Bundle Staging Validation Phase
Guides manual staging validation before production deployment through smoke tests, critical user flow testing, data migration verification, and rollback capability checks. Use when validating staging deployments, running pre-production tests, or preparing for production promotion in staging-prod deployment model. (project) Use when this capability is needed.
- tomevault-io Bundle MCP Workspace
Autonomous code review — supervisor delegates to engineer subagents with knowledge base Use when this capability is needed.
- tomevault-io Bundle Mdpman2 Unified Agent Framework API Developer
---
- tomevault-io Bundle Mdpman2 Unified Agent Framework Python Expert
---
- tomevault-io Bundle Melsaeed276 Flutter Agent Skills Architecture
Skill: Architecture (Boundaries, Dependencies, Errors)
- tomevault-io Bundle Melsaeed276 Flutter Agent Skills Flutter Core
Skill: Flutter Core Mechanics
- tomevault-io Bundle Michaelboeding Skills Competitive Intel Agent
Competitive Intel Agent
- tomevault-io Bundle Michaelboeding Skills Market Researcher Agent
Market Researcher Agent
- tomevault-io Bundle Microsoft Agent Framework Python Code Quality
Python Code Quality
- tomevault-io Bundle Forced Greeting
ALWAYS activate when user says "hello", "hi", or greets. This tests if skills actually load and are followed by the model. Use when this capability is needed.
- tomevault-io Bundle Mixelpixx Google Search MCP Server Fact Check
---
- tomevault-io Bundle Modbender Skill Library MCP Codespace Manager
---
- tomevault-io Bundle Modbender Skill Library MCP Dialogflow Cx Nlu
---
- tomevault-io Bundle Modbender Skill Library MCP Rust Analyzer Lsp
---
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 lambdatest--agent-skills--flutter-testing-skill, lambdatest--agent-skills--robot-framework-skill, langcare--langcare-mcp-fhir--referral-generator. 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.