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 School Agent Inc Orchestrate It Sitemap Searchサイトマップ & サイト内検索機能スキル
- tomevault-io Bundle Background Agent Pings
Background Agent Pings Use when this capability is needed.
- tomevault-io Bundle Reviewers
4400+ curated code review prompts from leading open-source repositories Use when this capability is needed.
- tomevault-io Bundle Dbt Commands
Transform AI agents into experts on dbt command-line operations, model selection patterns, Jinja Use when this capability is needed.
- tomevault-io Bundle Shin Jaeheon Agent Skill Cast Agent Skill Cast
---
- tomevault-io Bundle Shubhamsaboo Awesome LLM Apps Awesome LLM Apps
ChatGPT App Builder
- tomevault-io Bundle Shubhamsaboo Awesome LLM Apps Technical Writer
Technical Writer
- tomevault-io Bundle Vibe Architect
Lead Developer Agent. Orchestrates the strict "Research -> Plan -> Code" workflow. Use when this capability is needed.
- tomevault-io Bundle Graysurf Agent Kit Close Feature Pr
Close Feature PR
- tomevault-io Bundle Graysurf Agent Kit Release Workflow
Release Workflow
- tomevault-io Bundle Graysurf Agent Kit REST API Testing
REST API Testing
- tomevault-io Bundle Skill Governance
Audit skill layout and validate SKILL.md contracts. Use when this capability is needed.
- tomevault-io Bundle Evaluation Methodology
Methods for evaluating AI model outputs - exact match, semantic similarity, LLM-as-judge, comparative evaluation, ELO ranking. Use when measuring AI quality, building eval pipelines, or comparing models. Use when this capability is needed.
- tomevault-io Bundle Inference Optimization
Optimizing AI inference - quantization, speculative decoding, KV cache, batching, caching strategies. Use when reducing latency, lowering costs, or scaling AI serving. Use when this capability is needed.
- tomevault-io Bundle Requesting Code Reviews
AI agent requests effective code reviews through proper preparation, clear descriptions, and appropriate reviewer selection. Use when creating PRs, requesting feedback, or submitting for review. Use when this capability is needed.
- tomevault-io Bundle Manage Dependencies
Triggered when user asks to manage dependencies, add/remove packages, update dependencies, or audit security. Automatically delegates to the dependency-manager agent. Use when this capability is needed.
- tomevault-io Bundle Liquid Templating
Master Shopify Liquid templating language. Use this skill for writing Liquid code, using objects, filters, and tags, accessing product/collection/cart data, creating dynamic content, handling conditionals and loops, and working with Liquid best practices. Essential for theme customization. Use when this capability is needed.
- tomevault-io Bundle Shopify Functions
Build backend logic with Shopify Functions. Use this skill for creating custom discounts, delivery customization, payment customization, cart and checkout validation, and order routing. Functions run on Shopify's infrastructure using WebAssembly. Supports Rust and JavaScript. Use when this capability is needed.
- tomevault-io Bundle Claude Code MCP
This skill should be used when configuring, installing, or managing MCP (Model Context Protocol) servers in Claude Code. Use when users need to connect Claude Code to external tools, databases, APIs, or services through MCP integration. Use when this capability is needed.
- tomevault-io Bundle Markdown Proofreading
Proofread markdown files for typos, grammar, logic errors, and consistency issues. Use when this capability is needed.
- tomevault-io Bundle Trello Media Download
This skill should be used when the user asks to "download Trello images", "localize Trello media", "download attachments from Trello cards", or wants to store Trello-hosted images locally in the vault. Downloads Trello-hosted images referenced in imported Markdown files and rewrites links to local paths. Use when this capability is needed.
- tomevault-io Bundle Swiftui Best Practices
SwiftUI best practices for behavior, structure, and performance. Use when designing or reviewing SwiftUI views, state management, layout decisions, animations, or performance tuning; when unsure how to model state vs dependencies; when avoiding conditional view pitfalls; or when optimizing diffing, ForEach identity, and rendering costs. Use when this capability is needed.
- tomevault-io Bundle Integrations
Technical details for external platform integrations (APIs, credentials, rate limits). Use when posting, debugging issues, or adding new integrations. Use when this capability is needed.
- tomevault-io Bundle Web Search Advanced Financial Report
Search for financial reports using Exa advanced search. Near-full filter support for finding SEC filings, earnings reports, and financial documents. Use when searching for 10-K filings, quarterly earnings, or annual reports. Use when this capability is needed.
- tomevault-io Bundle Langgraph Architecture
Guides architectural decisions for LangGraph applications. Use when deciding between LangGraph vs alternatives, choosing state management strategies, designing multi-agent systems, or selecting persistence and streaming approaches. Use when this capability is needed.
- tomevault-io Bundle Extract Kernel Definitions
Generate Definition JSON files for the flashinfer-trace HuggingFace dataset by harvesting them from a short SGLang inference pass (FlashInfer's @flashinfer_api(trace=...) dumper) — or, as a fallback, by manually transcribing the schema from SGLang sources when FlashInfer doesn't yet have a trace template. Use when adding a new model, extracting GPU kernels (MLA, MoE, GQA, RMSNorm, GEMM, GDN, RoPE, sampling), or filling gaps in the dataset. Use when this capability is needed.
- tomevault-io Bundle Langchain Model Inference
Invoke Claude, GPT-4o, and Gemini through LangChain 1.0 without tripping Use when this capability is needed.
- tomevault-io Bundle Langchain Security Basics
Apply LangChain security best practices for production LLM apps. Use when this capability is needed.
- tomevault-io Bundle Langchain Webhooks Events
Dispatch LangChain 1.0 chain/agent events to external systems \u2014\ Use when this capability is needed.
- tomevault-io Bundle Soul Composer
AI agent that helps creators compose their Life Symphony - translating the 7 Pillars into musical metaphors and creative expression Use when this capability is needed.
- tomevault-io Bundle Review For Prod
Production-ready Go code review (QA + security + maintainability) for this project only. Use when this capability is needed.
- tomevault-io Bundle Researchorchestration
Multi-agent research orchestration for gathering technical, architectural, UX, security, and competitive insights. Use before brainstorm, during planning, or for troubleshooting. Use when this capability is needed.
- tomevault-io Bundle Aider 1h Ttl
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead. Use when this capability is needed.
- tomevault-io Bundle Gabrielmoreira Agent Skills Mirror Pytest Skill
Pytest Testing Skill
- tomevault-io Bundle Master Orchestration
Top-level orchestration skill that MUST be invoked at the start of every agent turn. Identifies required skills, coordinates sub-agents, and ensures comprehensive task completion with verification. Use when this capability is needed.
- tomevault-io Bundle Otp Thinking
This skill should be used when the user asks to "add background processing", "cache this data", "run this async", "handle concurrent requests", "manage state across requests", "process jobs from a queue", "this GenServer is slow", or mentions GenServer, Supervisor, Agent, Task, Registry, DynamicSupervisor, handle_call, handle_cast, supervision trees, fault tolerance, "let it crash", or choosing between Broadway and Oban. 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 school-agent-inc--orchestrate-it--sitemap-search, background-agent-pings, reviewers. 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.