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 Ecos Permission ManagementUse when requesting EAMA approval for agent lifecycle ops (spawn, terminate, hibernate, wake, plugin install). Trigger with permission requests.
- tomevault-io Bundle Eia Code Review Patterns
Use when reviewing pull requests. Trigger with PR review or code quality requests.
- tomevault-io Bundle Eia Github Projects Sync
Use when managing team tasks through GitHub Projects V2 or synchronizing project state via GraphQL API. Trigger with /sync-projects or when updating project items.
- tomevault-io Bundle Langgraph Overview
理解 LangGraph：用于构建有状态、长期运行 Agent 的低级编排框架，具有持久执行、流式传输和人机交互能力 Use when this capability is needed.
- tomevault-io Bundle Workflow Plan Phases
Creates a structured implementation plan document with properly sized phases for efficient sub-agent execution.
- tomevault-io Bundle Research Coordinator
Coordinate a research task by choosing the right workflow and dispatching to specialized agents. Use when the user has a broad or complex research request that may involve multiple steps. Use when this capability is needed.
- tomevault-io Bundle LLM Streaming Response Handler
Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI/Anthropic/Claude streaming APIs. Use for chatbots, AI assistants, Use when this capability is needed.
- tomevault-io Bundle Danielrami703 Swift Concurrency Agent Skill Swift Concurrenc
Swift Concurrency
- tomevault-io Bundle Huggingface Accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard. Use when this capability is needed.
- tomevault-io Bundle Btc Indicator Monitor Teneo
Real-time BTC price monitoring agent that sends alerts when price crosses key technical indicator levels. Monitors SMA, EMA, RSI, Bollinger Bands, and 15+ other indicators. Checks every 20 seconds w Use when this capability is needed.
- tomevault-io Bundle Claude Agent Team Workflows
Universal multi-agent workflow orchestration using Claude Code Agent Teams. Use when this capability is needed.
- tomevault-io Bundle Eia Github Thread Management
Use when managing PR review threads. Reply does NOT auto-resolve threads. Trigger with /manage-threads.
- tomevault-io Bundle Eoa Orchestration Patterns
Use when coordinating work among multiple developers. Trigger with orchestration requests.
- tomevault-io Bundle Swedish Accounting Compliance
Swedish accounting law and compliance reference for developers building accounting software. Use this skill whenever working on features that touch Swedish bookkeeping rules, tax compliance, chart of accounts, financial reporting, or regulatory requirements. Triggers include any mention of BFL, BFNAR, BAS kontoplan, SIE4, K2/K3, momsdeklaration, Skatteverket integration, verifikationer, löpande bokföring, årsbokslut, årsredovisning, bokföringsskyldighet, or Swedish accounting compliance in general. Also trigger when the user is checking whether a feature, data model, or workflow complies with Swedish accounting law, or when implementing tax calculations, invoice requirements, or financial reporting for Swedish entities. Use this skill even if the user just asks "is this compliant?" or "what does the law say about X?" in a Swedish accounting context. This skill is a compliance oracle, not an end-user guide. Use when this capability is needed.
- tomevault-io Bundle Obra Systematic Debugging
Use when errors are unclear, flaky, or regressions occur; apply a disciplined debugging loop in VS Code Copilot Agent mode.
- tomevault-io Bundle Flux Point Studios Cardano Agent Skills Aiken Smart Contract
aiken-smart-contracts
- tomevault-io Bundle Managing Knowledge Graphs
Graph RAG patterns, entity extraction with LLMs, relationship mapping, Use when this capability is needed.
- tomevault-io Bundle Agent Create
Author a new Claude Code agent/subagent with domain expert principles, routing mesh integration, proactive trigger design, and quality-checked output. Researches existing agents for routing mesh neighbors and domain best practices. Use when this capability is needed.
- tomevault-io Bundle European Parliament API
European Parliament API integration patterns, data source navigation, response validation, and cache optimization Use when this capability is needed.
- tomevault-io Bundle Langchain Langgraph
Use when working with LangChain or LangGraph in this repo, especially for agent construction, middleware, state graphs, persistence, memory, retrieval, runtime context, or durable execution patterns.
- tomevault-io Bundle Helixdevelopment Helixagent Deploying Machine Learning Model
Model Deployment Helper
- tomevault-io Bundle Helixdevelopment Helixagent Orchestrating Multi Agent System
Orchestrating Multi Agent Systems
- tomevault-io Bundle De Slop
This skill should be used to remove AI-generated artifacts and unnecessary code before committing. Integrates with desloppify CLI for quantitative scoring and directed fixes. Falls back to LLM-based pattern detection when desloppify is unavailable. Use when this capability is needed.
- tomevault-io Bundle Judgment Eval
Evaluates agent judgment quality through scenario-based testing in-conversation. Use when the user wants to test, validate, or stress-test an agent, skill, or command definition — e.g. "test this agent", "evaluate this skill", "does this prompt handle edge cases", "check this agent's judgment", or after writing or modifying any agent/skill/command .md file. Use when this capability is needed.
- tomevault-io Bundle AI Agent Strict Mode Configuration
Configures strict compilation modes to shift error checking from runtime to build-time for AI agents. Prevents runtime failures by enabling compiler-level type checking, null safety, and implicit type detection. Trigger when setting up AI agent development environments or when agents generate code that needs reliability guarantees.
- tomevault-io Bundle Data Integrity Guardian
Use this agent when reviewing database migrations, data models, or any code that manipulates persistent data. Specializes in validating referential integrity, transaction boundaries, and data validation rules. Triggers on requests like "data integrity review", "database safety check".
- tomevault-io Bundle Windsurf Auto Model Switcher
Switch Windsurf Cascade AI models programmatically. Apply when needing to change models from workflows or scripts. Use when this capability is needed.
- tomevault-io Bundle Agent MCP Server Builder
Création de serveurs MCP (Model Context Protocol) pour exposer des outils, ressources et prompts aux LLMs. Se déclenche avec "MCP", "Model Context Protocol", "MCP server", "MCP tool", "MCP resource", "serveur MCP", "connecter Claude à", "exposer une API à Claude", "claude desktop config". Use when this capability is needed.
- tomevault-io Bundle Weeknotes Blog Post Composer
Compose weeknotes blog posts in Jekyll-style Markdown from multiple data sources including Mastodon and Linkding. Use this skill when the user requests to create, draft, or generate weeknotes content for a blog post. Use when this capability is needed.
- tomevault-io Bundle Lubu Labs Langchain Agent Skills Langgraph Testing Evaluatio
LangGraph Testing & Evaluation
- tomevault-io Bundle Flutter Explain Codebase
Explains a Flutter project codebase in a structured, developer-friendly way, including architecture, state management, data flow, navigation, dependencies, risks, and prioritized next actions. Use when this capability is needed.
- tomevault-io Bundle TS Ddd Bounded Context
Map bounded contexts for a TypeScript DDD project — identify context boundaries, define ubiquitous language, map relationships (ACL, Partnership, Shared Kernel, etc.), and surface aggregate roots and domain events. Trigger when the user says "map the domain", "define bounded contexts", "what are the aggregates", "design the domain model", "identify the ubiquitous language", "how should we split this domain", or when planning a new feature that touches multiple domain areas. Also trigger when the user describes a business process and wants to know how to structure it in DDD. Use when this capability is needed.
- tomevault-io Bundle Validating UI Features
Provides step-by-step procedures for validating UI features - theme toggle, new chat, cancel stream, markdown rendering, and token usage info.
- tomevault-io Bundle Enterprise Crm Orchestrator
Coordinates all skills to build the Multi-Agent Enterprise CRM. Use when this capability is needed.
- tomevault-io Bundle Muhammadwaheedairi The Evolution Of Todo Building MCP Server
---
- tomevault-io Bundle Muhammadwaheedairi The Evolution Of Todo Multi Agent Pattern
---
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 ecos-permission-management, eia-code-review-patterns, eia-github-projects-sync. 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.