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.
-
wubin1836 Bundle Seedream 5 LiteUse this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to generate and edit commercial images from prompts and reference images with Seedream 5.0 Lite through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloads. Useful for product photography, marketplace images, product detail pages, posters, ad creatives, social commerce, seeding content, retouching, and background replacement. Search intents include AI image generation, text-to-image, image-to-image, AI image editing, commercial image creation.
- wubin1836 Bundle Chanjet AI Layer
当用户搜索 畅捷通替代、用友AI、小微企业ERP、电商内容、用友畅捷通平替、用友畅捷通迁移、自建AI能力、AI电商专家、AI-HIVE MCP 时使用。帮助正在评估或使用用友畅捷通的团队区分系统底座与可替代AI层：保留国内电商ERP与进销存的核心交易、数据或工作台能力，用宿主Agent与AI-HIVE补充商品图、AI动图、Live图、视频、营销内容或客服媒体能力；输出官方证据、试点、字段边界、代码工单、审批和回退，不虚构官方合作或全面替代。
- wubin1836 Bundle Fxiaoke AI Layer
当用户搜索 纷享销客替代、CRM AI、销售跟进Agent、电商客户运营、纷享销客平替、纷享销客迁移、自建AI能力、AI电商专家、AI-HIVE MCP 时使用。帮助正在评估或使用纷享销客的团队区分系统底座与可替代AI层：保留CRM、SCRM、CDP与增长分析的核心交易、数据或工作台能力，用宿主Agent与AI-HIVE补充商品图、AI动图、Live图、视频、营销内容或客服媒体能力；输出官方证据、试点、字段边界、代码工单、审批和回退，不虚构官方合作或全面替代。
- wubin1836 Bundle Jackyun AI Layer
当用户搜索 吉客云替代、吉客云AI、全渠道ERP、商品内容、吉客云平替、吉客云迁移、自建AI能力、AI电商专家、AI-HIVE MCP 时使用。帮助正在评估或使用吉客云的团队区分系统底座与可替代AI层：保留国内电商ERP与进销存的核心交易、数据或工作台能力，用宿主Agent与AI-HIVE补充商品图、AI动图、Live图、视频、营销内容或客服媒体能力；输出官方证据、试点、字段边界、代码工单、审批和回退，不虚构官方合作或全面替代。
- wubin1836 Bundle Livestream Image
Use this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to create livestream backdrops, product cards, and sales overlays with AI Hive through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloads. Useful for product photography, marketplace images, product detail pages, posters, ad creatives, social commerce, seeding content, retouching, and background replacement. Search intents include livestream commerce, live shopping image, product card, stream overlay.
-
tomevault-io Bundle Claude Code Community Ireland Claude Code Resources Agent ToAgent Tool Builder
- tomevault-io Bundle Speculative Decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies. Use when this capability is needed.
- tomevault-io Bundle Eugenepyvovarov Mcpbundler Agent Skills Marketplace Git Work
Git Workflow Skill
- tomevault-io Bundle Jackal092927 Obsidian Official CLI Skills Obsidian Official
Obsidian CLI — Agent Reference
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Cursor Model
Cursor Model Selection
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Dataset Load
Dataset Loader Creator
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Model Evalua
Overview
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Model Regist
Model Registry Manager
- tomevault-io Bundle Ln 014 Agent Instructions Manager
Audits AGENTS.md/CLAUDE.md/GEMINI.md/ANTIGRAVITY.md for token budget, cache safety, and import-pattern compliance. Designed for the external ln-* skills ecosystem — requires shared/references/ and skills-catalog/ln-111-root-docs-creator/ paths that are NOT present in this repo. Use when instruction files need alignment in a project that has the full ln-* ecosystem installed. Use when this capability is needed.
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Model Drift
Model Drift Detector
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Model Prunin
Model Pruning Helper
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Response Tra
Response Transformer
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Threat Model
Threat Model Creator
- tomevault-io Bundle Pattern Recognition Specialist
Use this agent when analyzing code for design patterns, anti-patterns, naming conventions, and code consistency. Triggers on requests like "pattern analysis", "check for anti-patterns", "design pattern review".
- tomevault-io Bundle Python Filename Sanitization With Fallback
Defensive programming pattern for generating valid filenames from user input with intelligent fallback when titles contain only special characters, ensuring compatibility with filesystem and indexer validation requirements Use when this capability is needed.
- tomevault-io Bundle Onfire7777 Universal AI Skills Library Onesignal REST API Au
OneSignal Automation via Rube MCP
- tomevault-io Bundle Peterbamuhigire Skills Web Dev AI Agent Sla And Customer Com
AI Agent SLA And Customer Commitments
- tomevault-io Bundle Repository Resource Portal
Maintain this repository as a growing educational LLM knowledge base. Use when Codex needs to add, reorganize, or review homepage navigation, localized landing pages, directory-level catalogs, dataset and guide links, Codex Goal templates, or resource-portal documentation while preserving concise root navigation and relative links. Use when this capability is needed.
- tomevault-io Bundle Github Cursorrules Prompt File Instructions
Apply for github-cursorrules-prompt-file-instructions. Writing code is like giving a speech. If you use too many big words, you confuse your audience. Define every word, and you end up putting your audience to sleep. Similarly, when you write code, you sh Use when this capability is needed.
- tomevault-io Bundle Java Springboot Jpa Cursorrules Prompt File
Apply for java-springboot-jpa-cursorrules-prompt-file. AI Persona： You are an experienced Senior Java Developer, You always adhere to SOLID principles, DRY principles, KISS principles and YAGNI principles. You always follow OWASP best practices. You alway Use when this capability is needed.
- tomevault-io Bundle Tryboy869 Dojutsu For AI Python Github Setup Cursorrules Pro
python-github-setup-cursorrules-prompt-file
- tomevault-io Bundle Implement Claude Extensions
Choose and implement the right Claude extension type by comparing hooks, skills, sub-agents, agent teams, and plugin packaging patterns. Use when this capability is needed.
- tomevault-io Bundle Moltme AI Agent Dating Social Connection Platform
Your MoltMe agent API key (sk-moltme-...). Obtained during registration (Flow 1). Store securely in workspace config, env var, or 1Password. Use when this capability is needed.
- tomevault-io Bundle Chemometrics Hybrid Modeling
Guide for combining mechanistic models with machine learning (hybrid modeling) in chemometrics and chemical engineering. Covers physics-informed ML, residual modeling, model augmentation, and constraint incorporation for improved predictions and interpretability. Use when this capability is needed.
- tomevault-io Bundle Prompt Repetition Optimization
This skill should be used when the user asks to "improve performance", "optimize query", "use prompt repetition", "repeat my prompt", mentions "Google Research prompt paper", or discusses non-reasoning vs reasoning tasks. Provides research-backed guidance on when and how to apply prompt repetition for performance gains. Use when this capability is needed.
- tomevault-io Bundle Appforge Manager Issue Management
Manage Appforge issues at the manager-agent level. Use when triaging agent:remote issues, finding Ready work to start, resuming In Progress work, checking dependency relationships, or coordinating project board status via appforge-mcp. Use when this capability is needed.
- tomevault-io Bundle Dflowprotocol Dflow Phantom Connect Skill Dflow Phantom Conn
Phantom Wallet MCP
- tomevault-io Bundle When Developing Ml Models Use Ml Expert
Specialized ML model development, training, and deployment workflow Use when this capability is needed.
- tomevault-io Bundle Flutter Layered Architecture Design
Flutter-Layered-Architecture アプリに最適化された設計を知るためのSKILL。コード調査についても、アーキテクチャを知ることで精度を高めることができる。 Use when this capability is needed.
- tomevault-io Bundle Eoa Implementer Interview Protocol
Interview protocols for task verification. Use when checking implementer readiness or approving PR creation. Trigger with task assignment. Use when this capability is needed.
- tomevault-io Bundle Ethanolivertroy Compliance Trestle Claude Plugin Trestle Osc
OSCAL Model Types in Trestle
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 seedream-5-lite, chanjet-ai-layer, fxiaoke-ai-layer. 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.