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

Doc Toc

Generate or update table of contents for a documentation file. Creates markdown TOC from headers. Use after adding sections or to standardize existing docs. Use when this capability is needed.

Sep 17
tomevault-io Bundle

LLM Judge

Compare code implementations across 2+ repos using LLM-as-judge methodology with weighted scoring Use when this capability is needed.

Sep 17
tomevault-io Bundle

Startup Context

Validate and diagnose startup context files — CLAUDE.md, AGENTS.md, rules, and .cursorrules — that inject instructions into the model context at session start across Claude Code, Cursor, and Codex. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Firebase Security Rules Auditor

Use when working with a skill to evaluate how secure Firestore security rules are. Use this when Firestore security rules are updated to ensure that the generated rules are extremely secure and robust.

Sep 17
tomevault-io Bundle

Reply Comments

Reply to PR review comments after addressing them. Resolves conversations where changes were made. Uses polite tone for humans, terse factual responses for AI bots. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Fpt Go Dev MCP Add Doc Integration

Add a New Documentation Site Integration

Sep 17
tomevault-io Bundle

Agent Implementer

Implementation guidance for creating individual agents in the Arcanea system with proper structure, capabilities, and integration. Use when this capability is needed.

Sep 17
tomevault-io Bundle

OAUTH Ops

Use when diagnosing, operating, or standardizing Hub LLM OAuth refresh/reimport incidents for Claude Code OAuth, OpenAI Codex OAuth, Gemini OAuth, Gemini CLI OAuth, Gemini Code Assist service, and Groq pool readiness.

Sep 17
tomevault-io Bundle

Agent Bootstrap

Use when setting up or repairing repo agent instructions for Claude Code, Codex, or both. Proposes durable AGENTS.md, CLAUDE.md, and project memory changes before writing unless setup was explicitly requested.

Sep 17
tomevault-io Bundle

Do Fixes

Apply fixes from a review. Detects the most recent review artifact and applies checked findings — currently supports code-review output. Verifies, commits, pushes, and posts the PR summary comment. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Appwrite Dart

Appwrite Dart SDK skill. Use when building Flutter apps (mobile, web, desktop) or server-side Dart applications with Appwrite. Covers client-side auth (email, OAuth), database queries, file uploads with native file handling, real-time subscriptions, and server-side admin via API keys for user management, database administration, storage, and functions. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Appwrite Ruby

Appwrite Ruby SDK skill. Use when building server-side Ruby applications with Appwrite, including Rails and Sinatra integrations. Covers user management, database/table CRUD, file storage, and functions via API keys. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Openclaw Native

Build and operate OpenClaw Native decision tracking in this ClawCommit repository. Use when implementing or running OpenClaw-specific SDK/MCP/schema APIs, PR+merge onchain automation, redacted PR link posting, or artifact-based reveal/replay workflows. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Deliverable Review

Review AIKnowSys deliverables (skills, stack templates, documentation) using Context7 MCP for current framework documentation. Use for monthly quality reviews, pre-release validation, or when frameworks release major versions. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Qwen Image Edit

Build Qwen Image Edit workflows — model loading, conditioning, LoRAs, prompt patterns, and XY plot testing Use when this capability is needed.

Sep 17
tomevault-io Bundle

Watcher Creator

Guide for creating agent-deck watchers conversationally. This skill should be used when users want to set up a new watcher (webhook, ntfy, github, slack, gmail) to route events to a conductor. It walks the user through selecting an adapter type, gathering required settings, generating watcher.toml and clients.json entries, and emits the exact `agent-deck watcher create` command to run. Use when this capability is needed.

Sep 17
tomevault-io Bundle

War Room

Convene a multi-LLM expert panel to pressure-test high-stakes decisions and build consensus through structured deliberation. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Generating Skills

Create new agent skills following SKILL.md best practices. Use when creating, validating, or improving skill files for AI agent consumption. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Beirux Agent Skills Code Simplifier

Code Simplifier

Sep 17
tomevault-io Bundle

Glm Basics

Basic usage of the General Lake Model (GLM) for lake temperature simulation. Use when you need to run GLM, understand input files, or modify configuration parameters. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Agent Access

Retrieve login credentials, API keys, and secrets (username, password, TOTP) from the user's Bitwarden vault via aac. Use when you need credentials to sign into a website or service, or need an API key. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Kirby Headless API

Exposes Kirby content to headless clients using the API, KQL, and JSON representations. Use when building API endpoints, KQL queries, or headless frontends. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Bntvllnt Agent Skills Skill Builder

Skill Builder

Sep 17
tomevault-io Bundle

Update Mr Desc

Updates merge request descriptions in GitLab by summarizing MR changes into a bulleted list, excluding changes under docs/. Use when updating an MR description via glab MCP or glab CLI, or when the user asks to summarize MR changes for the description. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Home Assistant Integrations Addons

Home Assistant integrations, add-ons, updates, and system operations. Use when the user asks about config entries, add-ons, updates, reloads/restarts, or system health, and when mapping those needs to ha-mcp tools. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Brokermr810 Quantdinger Quantdinger

QuantDinger agent workflow

Sep 17
tomevault-io Bundle

Feature MCP Server

Designs or implements MCP-facing work for bb-cli by exposing the existing grounded tool layer safely. Use when moving into the Day 12 MCP milestone or evaluating how current repo capabilities should be exposed to Claude Desktop or other MCP clients. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Deepseek Integration

当用户要求"DeepSeek API 集成"、"AI 服务"、"生成回复建议"、"调用 LLM"、"HTTP 请求"、"流式响应"、"连接池优化"、"重试策略"，或者提到"DeepSeek"、"API 调用"、"reqwest"、"streaming"时使用此技能。用于 DeepSeek API 集成、HTTP 客户端配置、错误处理、流式响应、连接池优化和 API 密钥管理。 Use when this capability is needed.

Sep 17
tomevault-io Bundle

Celina Create X Studio AI Agent Sdd

AI Agent SDD — Software Design Document for AI Agents

Sep 17
tomevault-io Bundle

Cheneeheng Agent Skills Code Review

Code Review

Sep 17
tomevault-io Bundle

LLM Sdk Guide

U-llm-sdk and claude-only-sdk patterns. Use when working on projects with LLM service, designing LLM integrations, or implementing AI-powered features. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Config Management

When agent config parameters need querying or modification → read/write YAML configuration files. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Council Advice

Multi-model AI council for actionable project advice. Leverages Gemini 3 Flash and GPT-5.2 skills in parallel, then synthesizes through an Opus Judge for stage-appropriate, non-overkill recommendations. Use when seeking architectural guidance, code review synthesis, or implementation planning. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Error Recovery

Provides structured error handling protocol for all agent operations. Ensures users receive clear error reports, troubleshooting guidance, and actionable next steps. Use when any tool operation fails, encounters an error, or produces unexpected results.

Sep 17
tomevault-io Bundle

Multi Pr Review

Run a consensus-style multi-agent review of a PR with severity-based findings. Use when this capability is needed.

Sep 17
tomevault-io Bundle

Typefully Agent Skills Agent Skills

Typefully Skill

Sep 17

Frequently asked questions

What are AI & ML agent skills?

Which AI & ML skills are most installed?

Popular AI & ML skills on SkillMD right now include doc-toc, llm-judge, startup-context. 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.