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 Digital Stoic Org Agent Skills Openspec TestOpenSpec Test
- tomevault-io Bundle Clockify API
Clockify API integration patterns and key endpoints Use when this capability is needed.
- tomevault-io Bundle Organic Search Features
This agent helps optimize for organic search features like featured snippets, rich snippets, and local packs to improve search engine visibility. Use this skill to improve your website's performance in Google search results. Use when this capability is needed.
- tomevault-io Bundle Managing Databases
AI agent performs database administration tasks including backup/restore, monitoring, replication, security hardening, and maintenance operations. Use when managing production databases, troubleshooting performance, or implementing high availability. Use when this capability is needed.
- tomevault-io Bundle Thinking Sequentially
AI agent structures complex reasoning through numbered thought sequences with explicit dependencies. Use when facing multi-step problems, complex debugging, or architectural decisions. Use when this capability is needed.
- tomevault-io Bundle Architect System
Triggered when user asks to design architecture, plan system structure, or make architectural decisions. Automatically delegates to the architect agent. Use when this capability is needed.
- tomevault-io Bundle Auto Optimize Prompt
Iteratively auto-optimize a prompt until no issues remain. Uses prompt-reviewer in a loop, asks user for ambiguities, applies fixes via prompt-engineering skill. Runs until converged. Use when this capability is needed.
- tomevault-io Bundle Agent Figure Gallery
Query visual scientific figure references, show candidates for human preference selection, export selected reference bundles, and guide plotting agents from human-selected visual examples to code action. Use when this capability is needed.
- tomevault-io Bundle Ark Dashboard Test
Test the Ark Dashboard UI with Playwright Use when this capability is needed.
- tomevault-io Bundle Anthropic Evaluations
This skill should be used when the user asks to "create evals", "evaluate an agent", "build evaluation suite", or mentions agent testing, graders, or benchmarks. Also suggest when building coding agents, conversational agents, or research agents that need quality assurance. Use when this capability is needed.
- tomevault-io Bundle Web Search Advanced Personal Site
Search personal websites and blogs using Exa advanced search. Full filter support for finding individual perspectives, portfolios, and personal blogs. Use when searching for personal sites, blog posts, or portfolio websites. Use when this capability is needed.
- tomevault-io Bundle Executioner1939 Claude Code Skills MCP Fleet
Executioner1939 Claude Code Skills Mcp Fleet
- tomevault-io Bundle Pydantic AI Testing
Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions. Use when this capability is needed.
- tomevault-io Bundle Claude RAG Skills
Analyze your documents and recommend optimal chunking strategies based on content type, use case, and embedding model. Use when this capability is needed.
- tomevault-io Bundle Flutter Embedding Native Views
Embeds native Android, iOS, or macOS views into a Flutter app. Use when integrating complex native components like maps or web views. Use when this capability is needed.
- tomevault-io Bundle MCP Crafting
Building MCP (Model Context Protocol) servers using official SDKs. Covers protocol concepts (tools, resources, prompts), transports (stdio, streamable HTTP), bundles (.mcpb), testing with MCP Inspector, client integration with Claude Desktop and Claude Code, logging, error handling, and security principles. Language modules available for Python (with FastMCP) and TypeScript (with @modelcontextprotocol/sdk). Use when creating MCP servers, defining MCP tools or MCP resources, configuring transports, packaging bundles, testing MCP servers, or integrating with Claude. Also relevant for MCP tool definition, MCP resource exposure, and FastMCP server patterns. Use when this capability is needed.
- tomevault-io Bundle Project Initialization
使用 agent-workflows 的项目初始化工作流来启动新项目和绿地仓库；当 Codex 被要求创建新项目、初始化仓库、搭建绿地代码库、选择初始工具链、配置包管理、创建基础 README/.gitignore/配置文件或验证初始脚手架时使用。 Use when this capability is needed.
- tomevault-io Bundle Future3ooo Agentic Cockpit Cockpit Exec Agent
Cockpit Exec Agent
- tomevault-io Bundle Github Pr Creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing PRs, use github-pr-merge instead.
- tomevault-io Bundle Kata Review Pull Requests
Run a comprehensive pull request review using multiple specialized agents. Each agent focuses on a different aspect of code quality, such as comments, tests, error handling, type design, and general code review. The skill aggregates results and provides a clear action plan for improvements. Triggers include "review PR", "analyze pull request", "code review", and "PR quality check". Use when this capability is needed.
- tomevault-io Bundle Gitstq Awesome AI Agent Skills Super Reviewer
Super Reviewer - AI Senior Code Review Engine
- tomevault-io Bundle Gologo13 Agent Skills Generate Pr Description
Generate PR Description
- tomevault-io Bundle Hainamchung Agent Assistant Lint And Validate
Lint and Validate Skill
- tomevault-io Bundle Security Prompts Threat Modeling
Security analysis and threat modeling prompt templates for STRIDE analysis, code review, OWASP compliance, and vulnerability assessment. Use for security planning, pre-deployment reviews, and ongoing threat assessment. Triggers include "STRIDE", "threat model", "security review", "code review", "OWASP", "payment security", "security analysis", "vulnerability assessment". Use when this capability is needed.
- tomevault-io Bundle Desc Value Design
価値デザインモデルを作る時の観点を説明する Use when this capability is needed.
- tomevault-io Bundle Helixdevelopment Helixagent Adk Agent Builder
ADK Agent Builder
- tomevault-io Bundle Tokrepo Search
Search and install AI assets from TokRepo when a user asks to find, discover, or install Codex skills, MCP servers, prompts, cursor rules, or workflows. Use when this capability is needed.
- tomevault-io Bundle Quick Fix
Fast workflow for small changes, bug fixes, and UI tweaks that don't require full feature development. Uses sub-agent orchestration with model selection (Sonnet 4.5 orchestrator, Haiku 4.5 workers) for efficient context management. Handles styling adjustments, minor functionality fixes, and quick improvements while maintaining project quality standards. Use when this capability is needed.
- tomevault-io Bundle Sync Upstream Features
Investigate whether the latest hook events and features from Claude Code / Codex CLI are covered by tmux-agent-sidebar's current implementation, and report gaps. Use on requests like "check diff with upstream", "look for new hooks", "check changelog for unsupported features". Does not implement anything. Use when this capability is needed.
- tomevault-io Bundle Javascript Tooling
Development tools, linting, and testing for JavaScript projects. Use when this capability is needed.
- tomevault-io Bundle Harness Tester
Testing orchestrator for autonomous harness. Runs comprehensive tests (unit, integration, E2E), coordinates with validation systems, and reports results to Archon. Supports browser automation via Playwright MCP. Use when verifying features, running test suites, or validating code changes. Use when this capability is needed.
- tomevault-io Bundle Context7 Lookup
Fetch up-to-date library documentation using Context7 MCP. Avoid hallucinated APIs and outdated code examples. Use when this capability is needed.
- tomevault-io Bundle Iamcaominhtien Kanban Board MCP Setup Copilot
Setup Copilot Instructions
- tomevault-io Bundle Ignaciosua Copilot Skills Repo Whatsapp Agent
WhatsApp Agent
- tomevault-io Bundle Agent Support Matrix
Maintain Agent Sessions agent support matrix and JSON/JSONL parsing compatibility. Use when checking upstream agent releases for session format changes, updating max verified versions in docs/agent-support/agent-support-matrix.yml, or updating docs/agent-json-tracking.md and fixtures/tests. Use when this capability is needed.
- tomevault-io Bundle Golang Ddd Refactor
Refactor existing Go code toward a behavior-first, invariant-protecting domain model. Use when business rules live in handlers or repositories, shared structs couple DB and API models, entities expose setters or mutable public fields, or a service needs domain methods, constructors, private state, repository update closures, and focused domain tests. 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 digital-stoic-org--agent-skills--openspec-test, clockify-api, organic-search-features. 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.