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 Playwright Screenshot InspectorLLM-powered visual testing expert for automated screenshot capture, analysis, and UI verification using Playwright with multimodal AI inspection. Use when this capability is needed.
- tomevault-io Bundle Langchain Agents Middleware
Use when building or productionising any agent — adding retries, fallbacks, summarization, human-in-the-loop, PII redaction, call limits, or custom hooks. Middleware is THE composition primitive for modern LangChain agents (v1+); covers built-ins plus the custom middleware authoring API.
- tomevault-io Bundle Typescript Javascript
TypeScript and JavaScript development standards for modern web and Node.js development. Covers strict TypeScript configuration, type safety patterns, ESM modules, async/await, testing with Jest/Vitest, and security best practices. Use when working with .ts, .tsx, .js, .mjs files, package.json, tsconfig.json, or when asking about TypeScript/JavaScript best practices. Use when this capability is needed.
- tomevault-io Bundle Terminal Bench Strategies
Comprehensive strategies and patterns for maximizing Terminal-Bench 2.0 task completion. Contains battle-tested approaches from top-performing agents. Use when this capability is needed.
- tomevault-io Bundle Long Context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs. Use when this capability is needed.
- tomevault-io Bundle Evaluating Llms Harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs. Use when this capability is needed.
Audited - tomevault-io Skill Nemo Guardrails
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
Audited - tomevault-io Bundle X Followers Followings Teneo
Use when working with an agent that helps you extract followers and followings from X profiles.
- tomevault-io Bundle Eoa Developer Communication
Trigger with developer communication needs. Use when communicating with human developers in code reviews, issues, technical discussions, and status updates. Covers effective communication patterns. Use when this capability is needed.
- tomevault-io Bundle Code Recon
This skill provides a structured methodology for building that context efficiently. Use when this capability is needed.
- tomevault-io Bundle Flutter Navigator V1 Imperative
Standard Flutter navigation using Navigator 1.0 (push/pop). Use when this capability is needed.
- tomevault-io Bundle Solidity Function Audit Team
Agent team variant of solidity-function-audit with human-in-the-loop review. Uses agent teams for inter-agent messaging, shared task list with dependencies, plus interactive design decision capture (Stage 0), findings review (Stage 4), and dispute re-evaluation (Stage 5). Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. Use when this capability is needed.
- tomevault-io Bundle Genai Acceptance Review
Review workflow for AI/LLM output usage to prevent over-trust, injection, and unsafe automation. Use when this capability is needed.
- tomevault-io Bundle Markdown Customizations
Use this skill when creating or editing GitHub Copilot customization Markdown files (agent profiles, prompt files, instruction files, and skills).
- tomevault-io Bundle Update Review Instructions
Generates or updates GitHub Copilot review instruction files in .github/instructions/ for a selected project scope. Analyzes current conventions from .claude/rules/, DESIGN-GUIDELINES.md, and existing skill structures to produce evidence-based, scope-specific review guidelines under the 4,000 character code review limit.
- tomevault-io Bundle Sddevelopment Be Quickstart Agent Augmented Development Dele
Delegate: Specialist Agent Handoff
- tomevault-io Bundle Observability Monitoring Slo Implement
You are an SLO (Service Level Objective) expert specializing in implementing reliability standards and error budget-based practices. Design SLO frameworks, define SLIs, and build monitoring that ba... Use when this capability is needed.
- tomevault-io Bundle Startup Business Analyst Business Case
Generate comprehensive investor-ready business case document with Use when this capability is needed.
- tomevault-io Bundle Create Agent Markdown
Create high-quality AI agent definition files that follow the Agent Skills specification. Produces behavioral prompts with real mental models, decision frameworks, and domain expertise — not generic filler. Use when this capability is needed.
- tomevault-io Bundle Tryboy869 Dojutsu For AI Code Guidelines Cursorrules Prompt
code-guidelines-cursorrules-prompt-file
- tomevault-io Bundle Pydanticai Type Safe AI Agent Framework
PydanticAI is an AI agent framework built by the Pydantic team that brings FastAPI-style ergonomics to GenAI development. It provides type-safe, model-agnostic agent construction with structured outputs, dependency injection, and seamless integration with Pydantic Logfire for observability. Use when this capability is needed.
- tomevault-io Bundle Orch Discussion
Orchestrator discussion preset — structured multi-agent discussion protocol for collaborative problem solving. Coordinates N-way discussions between specialist agents through Propose, Challenge, and Synthesize phases to reach consensus. Use this skill when facilitating multi-agent discussions, debates, design evaluations, or collaborative analysis requiring multiple perspectives. Use when this capability is needed.
- tomevault-io Bundle Developing Wpf Customcontrols
Develops WPF CustomControls using Parts and States Model best practices. Use when creating templatable controls with TemplatePart, TemplateVisualState, OnApplyTemplate, or VisualStateManager. Use when this capability is needed.
- tomevault-io Bundle Langchain Agents Observability
Use when debugging an agent's behaviour, reading LangSmith traces, setting up tracing in production (LangSmith + OpenTelemetry), wiring distributed tracing across services, or diagnosing common failure modes.
- tomevault-io Bundle Pyvene Interventions
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
- tomevault-io Bundle Huggingface Tokenizers
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training. Use when this capability is needed.
- tomevault-io Bundle Diversioteam Agent Skills Marketplace Login Cta Attribution
Login CTA Attribution Skill
- tomevault-io Bundle Project Feature Explainer
Expert guidance for explaining project features. Use this skill when you need to provide a comprehensive explanation of how a specific feature works, including summaries, deep dives, usage examples, and sequence/workflow diagrams. This skill has references directory which contains additional instructions `checklist.md`, `example-output.md` and `explanation-template.md` that MUST be used for every analysis. Use when this capability is needed.
- tomevault-io Bundle Hechtcarmel Jetbrains Index MCP Plugin Jetbrains Index MCP P
IDE Index MCP - Agent Guide
- tomevault-io Bundle Jayalexandermg Skilljacked AI Agent Project Context Document
AI Agent Project Context Documentation
- tomevault-io Bundle Madguyevans Creator Resale Agent Skill Hub Resale Agent Skil
broker-recognize: Photo → Product Info
- tomevault-io Bundle Gemini Extension Development
Expert guide for building and managing Gemini CLI Extensions. Covers extension anatomy, GEMINI.md context, commands, MCP integration, and publishing. Use when creating Gemini extensions, linking local extensions, packaging MCP servers, or installing extensions from GitHub. Delegates to gemini-cli-docs. Use when this capability is needed.
- tomevault-io Bundle Skill Boilerplate
Define a standard per-skill local data layout at <project_root>/.skills-data/<skill-name> and required SKILL.md guidance for env/config/deps/tools. Use when starting a new skill and you must specify where to store data, env files, local binaries, and dependencies. Use when this capability is needed.
- tomevault-io Bundle X Bookmarks Manager
Read X/Twitter bookmarks using the bird CLI, verify the active account via `bird whoami`, and return bookmarks as JSON. Use when the user asks to list, search, summarize, or export X bookmarks, or when you must validate the active X account before fetching bookmarks. Use when this capability is needed.
- tomevault-io Bundle Langchain4j RAG Implementation Patterns
Provides Retrieval-Augmented Generation (RAG) implementation patterns with LangChain4j for Java. Generates document ingestion pipelines, embedding stores, vector search, and semantic search capabilities. Use when building chat-with-documents systems, document Q&A over PDFs or text files, AI assistants with knowledge bases, semantic search over document repositories, or knowledge-enhanced AI applications with source attribution.
- tomevault-io Bundle Langchain4j Vector Stores Configuration
Provides configuration patterns for LangChain4J vector stores in RAG applications. Use when building semantic search, integrating vector databases (PostgreSQL/pgvector, Pinecone, MongoDB, Milvus, Neo4j), implementing embedding storage/retrieval, setting up hybrid search, or optimizing vector database performance for production AI applications.
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 playwright-screenshot-inspector, langchain-agents-middleware, typescript-javascript. 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.