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 Lumina RAG KnowledgeManage Lumina's retrieval-augmented generation and knowledge ingestion workflow. Use when editing server/src/services/knowledgeBase.ts, server/src/services/pineconeClient.ts, server/src/scripts/knowledgeCli.ts, server/src/models/KnowledgeSource.ts, files under server/knowledge, manifest-based sync inputs, or debugging grounded answers, retrieval relevance, source lifecycle, and inline citations. Use when this capability is needed.
- tomevault-io Bundle Finance Cleanup
Use when the user wants to clean up transactions, fix categories, find missing recurring charges, or do general transaction hygiene in Copilot Money.
- tomevault-io Bundle Interactive Widgets
Interactive widget systems for AI applications including LLM-driven widget generation, dynamic UI components, form builders, and streaming response widgets. Use when asking about 'interactive widgets', 'dynamic UI', 'LLM widgets', 'widget generation', 'streaming widgets', 'form widgets', 'AI response widgets', 'structured responses', or 'widget protocol'. Use when this capability is needed.
- tomevault-io Bundle Juandelossantos Another Agent Skills Code Review And Quality
Code Review and Quality
- tomevault-io Bundle Code Verification
Multi-agent code verification workflow using a main agent and sub-agent loop. Use when verifying code against requirements, acceptance criteria, or quality standards. Triggers on requests to verify, validate, or check code against specifications, checklists, or instructions. Use when this capability is needed.
- tomevault-io Bundle Bocato Swift Testing Agent Skill Swift Testing Agent Skill
Swift Testing
- tomevault-io Bundle Cc Workflow AI Editor
AI workflow editor for CC Workflow Studio. Create and edit visual AI agent workflows through interactive conversation using MCP tools (get_workflow_schema, get_current_workflow, apply_workflow). Use when the user wants to create a new workflow, modify an existing workflow, or edit the workflow canvas in CC Workflow Studio via the built-in MCP server. Use when this capability is needed.
- tomevault-io Bundle Memories Off
管理基于 Markdown 实体的本地知识库。提供库观察、实体检索、按需加载章节、精确编辑及显式关系管理能力。支持长期记忆与持续学习。 Use when this capability is needed.
- tomevault-io Bundle AI Agent Architect
Use when designing, building, or debugging LLM-based agent systems — tool use, function calling, multi-agent orchestration, memory, RAG, evaluation harnesses, and agent safety.
- tomevault-io Bundle Agent Harness
AI agent の action space・tool 定義・observation format を設計し、completion rate を上げる。 agent harness を構築・最適化するときの語彙と判断軸を提供する。 Use when this capability is needed.
- tomevault-io Bundle Alicloud AI Image Qwen Image Test
Minimal image generation smoke test for Model Studio Qwen image. Use when this capability is needed.
- tomevault-io Bundle Construct AI Primary Z Docs Paperclip Agent Reconciliation
Agent Reconciliation Skill
- tomevault-io Bundle Verify Local Config Before Claims
Verify repository configuration locally before making conclusions about MCP/server setup. Use when asked to diagnose configuration, profile routing, auth behavior, endpoints, env vars, or profile IDs/aliases in this workspace. Use when this capability is needed.
- tomevault-io Bundle Whisper Video Transcribe Workaround
When Whisper (CLI or Python) gets stuck on video files during transcription — output dir stays empty, process runs at low CPU/memory with no progress — the workaround is to extract audio first with ffmpeg, then transcribe the WAV. Use this when Whisper hangs or times out on a video file. Use when this capability is needed.
- tomevault-io Bundle Nemo Curator
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora. Use when this capability is needed.
- tomevault-io Bundle Davila7 Claude Code Templates Screenshot Feature Extractor
Screenshot Analyzer (Multi-Agent)
- tomevault-io Bundle Call Report Writer Agent
AI agent for call report writer agent tasks. Use when this capability is needed.
- tomevault-io Bundle Demerzels Lab Elsamultiskillagent Linkedin Job Application
LinkedIn Job Application Bot Agent
- tomevault-io Bundle Lucky Raffle Agent Teneo
Use when working with a payment-based raffle agent. Join the raffle and have a chance to win! Send \"@raffle-agent raffle info\" for details.
- tomevault-io Bundle Moltmoon Sdk
Complete OpenClaw-ready operating skill for @moltmoon/sdk. Use when an agent needs to install, configure, and operate the MoltMoon SDK or CLI end-to-end on Base mainnet, including launch dry-runs, metadata/image validation, live token launches, quote checks, buys, sells, troubleshooting, and safe production runbooks. Use when this capability is needed.
- tomevault-io Bundle Typhoon Starknet Account
Create a Starknet account to your agent through Typhoon anonymous deployer and interact with Starknet contracts (read/write + preflight). Use when this capability is needed.
- tomevault-io Bundle Flutter Implement JSON Serialization
Create model classes with fromJson/toJson using dart:convert and Dart 3 pattern matching. Use when manually mapping JSON to classes, parsing HTTP responses, or choosing between manual and code-generated serialization. Use when this capability is needed.
- tomevault-io Bundle Langchain Architecture V2
LangChain Architecture workflow skill. Use this skill when the user needs Master the LangChain framework for building sophisticated LLM applications with agents, chains, memory, and tool integration and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off. Use when this capability is needed.
- tomevault-io Bundle Helpscout Navigator
Use when searching HelpScout tickets, customers, or organizations. Provides correct tool selection, required sequencing, and prevents common mistakes. Triggers on "search helpscout", "find tickets", "check support inbox", "helpscout conversations", "look up customer", "find organization", "customer history".
- tomevault-io Bundle Ekroon Agent Skills Migrate Agents To Copilot Instructions
Migrate AGENTS.md to GitHub Copilot Instructions
- tomevault-io Bundle Eia Integration Protocols
Use when accessing shared utilities and protocols. Trigger with cross-skill reference requests.
- tomevault-io Bundle Eoa Messaging Templates
AI Maestro message templates for emasoft plugins. Use when sending task assignments, status reports, or escalations between agents. Trigger with messaging requests. Use when this capability is needed.
- tomevault-io Bundle RAG Agent Creator
Create RAG-enhanced Claude Code agents with structured knowledge bases, retrieval strategies, and domain expertise Use when this capability is needed.
- tomevault-io Bundle Deepagents Overview
理解 Deep Agents 框架 - 它们是什么、如何使用 createDeepAgent 创建，以及 agent harness 架构，包括内置的规划、文件系统和子代理中间件。 Use when this capability is needed.
- tomevault-io Bundle Obra Using Superpowers
Use when working in VS Code Copilot Agent mode and you want the Superpowers workflow (plans, verification, debugging, TDD) applied consistently.
- tomevault-io Bundle Typescript Satisfies Operator
Guides proper usage of TypeScript's satisfies operator vs type annotations. Use this skill when deciding between type annotations (colon) and satisfies, validating object shapes while preserving literal types, or troubleshooting type inference issues. Use when this capability is needed.
- tomevault-io Bundle Flux Point Studios Cardano Agent Skills Cardano CLI Doctor
cardano-cli-doctor
- tomevault-io Bundle Github CLI Code Review
Use GitHub CLI (gh) and SonarQube MCP tools to fetch PR details, review comments, threads, and quality gate status for the current branch before addressing code review feedback. Use when this capability is needed.
- tomevault-io Bundle Gathering Requirements
5-layer requirements elicitation for Cursor agent system generation Use when this capability is needed.
- tomevault-io Bundle Generating Cursorrules
.cursorrules file generation skill Use when this capability is needed.
- tomevault-io Bundle Managing Vision Agents
Image analysis with multi-modal LLMs (GPT-4V, Gemini Vision), object 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 lumina-rag-knowledge, finance-cleanup, interactive-widgets. 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.