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 Niloykumarbarman Everything Claude Code Agent Eval---
- tomevault-io Bundle Categorize Transactions
Review and categorize uncategorized bank transactions, match them with invoices, and verify bookkeeping entries. Use when the user wants to review transactions, categorize expenses, do bookkeeping, or reconcile their bank account. Use when this capability is needed.
- tomevault-io Bundle Agent Context File Writer
Writes a high-quality CLAUDE.md, .cursorrules, or .windsurfrules file that gives a coding agent the right project context, conventions, and constraints to work effectively. Use when this capability is needed.
- tomevault-io Bundle Nstbrowser AI Agent
Browser automation CLI for Nstbrowser profiles. Use when the user needs Nstbrowser profile management, temporary browsers, proxy-aware automation, or browser actions that must run through the Nstbrowser desktop client. Use when this capability is needed.
- tomevault-io Bundle Omer Metin Skills For Antigravity Agent Evaluation
---
- tomevault-io Bundle Omer Metin Skills For Antigravity LLM Npc Dialogue
---
- tomevault-io Bundle Agent Context Audit
Codex instruction 구조의 밀도와 건강도를 감사합니다. AGENTS.md 길이, 계층 깊이, 중복 규칙, 커버리지 부족을 찾을 때 사용합니다. Use when this capability is needed.
- tomevault-io Bundle Agent Context Guide
Codex용 계층형 컨텍스트 아키텍처를 설계하고 설명합니다. AGENTS.md 루트/하위/override 분리, CONTEXT.md 보조 문서화, 토큰 효율 개선이 필요할 때 사용하고 단순 파일 편집만 할 때는 사용하지 않습니다. Use when this capability is needed.
- tomevault-io Bundle Open Finance AI Agent Skills Bank Account Analysis
ניתוח חשבון בנק - Bank Account Analysis
- tomevault-io Bundle Github Action Diagnose
诊断昇腾（Ascend）NPU 集群上 GitHub Actions 执行失败的原因，定位基础设施故障与根因分析 Use when this capability is needed.
- tomevault-io Bundle Local LLM Fine Tuning
Guides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniques like LoRA and QLoRA. Use when this capability is needed.
- tomevault-io Bundle Ml Experiment Tracker
Guides ML experiment logging, versioning, and reproducibility using tools like MLflow, Weights & Biases, and DVC for systematic model development. Use when this capability is needed.
- tomevault-io Bundle Overcut AI Overcut Playbooks Agent Tools Reference
Agent Tools Reference
- tomevault-io Bundle Agent Orchestration Planner
Designs multi-step agent workflows with tool usage, retry logic, state management, and budget controls. Provides orchestration diagrams, tool execution order, fallback strategies, and cost limits. Use for "AI agents", "agentic workflows", "multi-step AI", or "autonomous systems". Use when this capability is needed.
- tomevault-io Bundle Kani Verifier
Rust formal verification using Kani model checker. Use when verifying Rust code for memory safety, undefined behavior, panics, arithmetic overflows, or custom correctness properties. Triggers include "verify this Rust code", "prove this function is safe", "check for undefined behavior", "write a proof harness", "kani proof", "model check", or any request involving Rust formal verification, property-based proofs, or safety guarantees beyond testing. Use when this capability is needed.
- tomevault-io Bundle Pavel Molyanov Telegram AI Agent Telegram AI Agent
Project Knowledge
- tomevault-io Bundle Slide Excellence
Multi-agent slide review (visual, pedagogy, proofreading). Use for comprehensive quality check before milestones. Use when this capability is needed.
- tomevault-io Bundle Codex Readiness Unit Test
Run the Codex Readiness unit test report. Use when you need deterministic checks plus in-session LLM evals for AGENTS.md/PLANS.md. Use when this capability is needed.
- tomevault-io Bundle Init Project Guidance
Scaffolds AI-agent guidance files (GEMINI.md and AGENTS.md) for new or existing projects. Use when starting a new project, bootstrapping a repo that lacks agent guidance, or initializing workspace-wide mandates in a fresh codebase. Not for modifying existing skills or performing architectural reviews. Use when this capability is needed.
- tomevault-io Bundle Documentation Authoring
Create structured docs from scratch — PRDs, technical specs, design docs, decision records, knowledge bases. Use when drafting documentation, writing proposals, defining requirements, or planning features. Use when this capability is needed.
Audited - tomevault-io Bundle Datastore Redis
Designs Redis usage for caching, rate limiting, and distributed locks. Use when this capability is needed.
- tomevault-io Bundle Messaging Kafka
Designs Kafka topics, schemas, and consumer groups. Use when this capability is needed.
- tomevault-io Bundle Codex Integration
Use this skill when delegating complex coding tasks to OpenAI Codex CLI and coordinating work between Claude and Codex.
- tomevault-io Bundle Langchain Use
LangChain 1.0 使用指南。提供 Agent、Tool、Memory、Middleware 等核心概念的快速参考。当用户需要创建 AI Agent、集成 LangChain、或解决 LangChain 相关问题时激活。 Use when this capability is needed.
- tomevault-io Bundle Neo4j Aura Agent Skill
Manages Neo4j Aura Agents via the v2beta1 REST API — create, list, get, update, delete,
- tomevault-io Bundle Numerai Experiment Design
Design and manage Numerai experiments in this repo for any model idea. Use when this capability is needed.
- tomevault-io Bundle Omer Metin Skills For Antigravity Prompt Engineer
---
- tomevault-io Bundle Agent Context Init
저장소를 분석해 Codex용 instruction 구조를 초기화합니다. 루트 AGENTS.md, 필요 시 하위 AGENTS.md/AGENTS.override.md, 보조 CONTEXT.md를 생성·보강할 때 사용합니다. Use when this capability is needed.
- tomevault-io Bundle Planning With Teams
Manus-style context engineering for Agent Teams. Coordinate multiple Claude Code instances with shared planning files. Use when complex tasks need parallel work (code review, debugging, feature development). Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. Use when this capability is needed.
- tomevault-io Bundle Overcut AI Overcut Playbooks Agent Session Design
Agent Session Design
- tomevault-io Bundle News Crawler
Use when working on the mcp-java-news-crawler repository and needing the project-specific workflow, transport model, tool contract, local run commands, or smoke-test steps.
- tomevault-io Bundle Math Model Selector
Routes problems to appropriate mathematical frameworks using expert heuristics Use when this capability is needed.
- tomevault-io Bundle Creating New Agent
Creates new A2A-compliant agents in the QuAIA framework. Use when adding a new specialized agent with custom tools, prompts, and MCP server integrations.
- tomevault-io Bundle Devcontainer Setup
Templates and process for creating devcontainer configurations. Use this when setting up a new project, adding devcontainer support, or creating devcontainers for worktrees. Use when this capability is needed.
- tomevault-io Bundle Pre Implementation
Mandatory checklist before starting implementation. Use this before writing code for any non-trivial task. Use when this capability is needed.
- tomevault-io Bundle Project Prompt Creator
在项目 AGENTS.md 约束下生成可直接交给 Codex 或 Agent 执行的中文任务 prompt。用于开发、修复、文档、验证、审计、治理或交接任务的 prompt 化，但不承载 Plan mode 和 code review 的完整模式规则。 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 niloykumarbarman--everything-claude-code--agent-eval, categorize-transactions, agent-context-file-writer. 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.