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.
-
mlitech-dev01 Bundle Docutect AI MCPConnect to DocuTect AI's MCP server to scan GitHub repositories and documentation URLs for API endpoints, run LLM hallucination audits, validate Markdown documentation, generate OpenAPI specs, and retrieve remediation suggestions. Use when the user asks to audit an API, detect hallucinations in docs, scan a repo for endpoints, validate documentation accuracy, generate an OpenAPI spec from source code, or fix inaccurate API documentation. Requires a DocuTect AI account (free, pro, or enterprise) and an API key starting with dtai_.
-
sol1986 Bundle Mindstudio Generate Text Block Prompting SkillWrite, review, or improve prompts for MindStudio Generate Text blocks — whether the output is plain text or structured JSON. Use this skill whenever someone asks to write a MindStudio prompt, configure a Generate Text block, set up JSON output schema, use variables in a prompt, add conditional logic to a prompt, or access JSON data with dot notation inside a MindStudio workflow. Always use this skill for any MindStudio prompt-writing task, even if the request seems simple.
-
kaojunn Bundle Unity MCP BridgeInstall, configure, and verify CoderGamester/mcp-unity for Unity Editor projects so AI clients can control and query Unity through MCP. Use when asked to add MCP Unity to a Unity project, connect Claude/Cursor/Windsurf/Codex/GitHub Copilot to Unity, start or troubleshoot the Unity MCP bridge, verify get_scene_info/get_console_logs, or generate MCP client configuration for Unity.
-
mangiapanejohn-dev Skill OracleBest practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
-
mangiapanejohn-dev Skill ClawhubUse the ResonixHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.
-
ekajto Skill PushCommit & Push Agent
-
ekajto Skill TestTest Agent — Active Validator
-
mangiapanejohn-dev Skill McporterUse the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
-
mangiapanejohn-dev Skill Gh IssuesFetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]
-
mangiapanejohn-dev Bundle Model UsageUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
-
mangiapanejohn-dev Skill Coding AgentDelegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), or any work in ~/clawd workspace (never spawn agents here). Requires a bash tool that supports pty:true.
-
kylin-feng Bundle MCP MasterUse when user asks about MCP, needs to create/configure/debug MCP servers, or explore the MCP ecosystem. Comprehensive MCP knowledge including protocol, development, deployment, and troubleshooting.
-
kylin-feng Bundle MCP QuickstartUse when user wants to quickly set up MCP servers with Hermes Agent. One-command quickstart guide for getting MCP up and running in under 5 minutes.
-
woaillr-crypto Bundle Code2wiki为大型后端项目生成和维护面向业务的 Business Context Layer(业务语义层 / 项目知识地图)。当需要总结、梳理、文档化、wiki 化、构建上下文、创建领域 skill、提升 LLM 对既有后端代码库的理解时使用——尤其适用于 10w+ 行、50w+ 行这类需求主要由业务驱动而不是技术模块驱动的系统。支持 Java/Spring、Kotlin(Spring/Ktor)、Python(Django/FastAPI/Flask)、Go(Gin/Echo/gRPC)、TypeScript/JavaScript(NestJS/Express)等多种后端栈;扫描器自动识别项目语言,混合语言 Monorepo 会并行扫描所有命中插件。也适用于多级业务域目录、项目知识地图、API/Database/Code Entrypoint 映射、风险清单、分层上下文(L0/L1/L2/Source)建设等任务。
-
douglac Skill Banco MCPSkill abrangente pra trabalhar com dados financeiros via Banco MCP — analisar gastos, gerar extratos, fluxo de caixa, fatura de cartão, carteira de investimentos. Use sempre que o usuário perguntar sobre dinheiro, gastos, banco, cartão, investimentos, fatura, saldo, extrato, transações, ou variantes. Orquestra as 13 ferramentas openfinance_* (read-only) do servidor MCP remoto em https://api.mcp.ai/banco.
-
hzq510473048 Bundle Xianxia Pinball GameplayDesign, prototype, tune, and polish the specific xianxia dark-fantasy arcane pinball mobile game concept. Use when Codex works on this game's dual-hand energy-control pinball mechanics, arcane orb states, overload/harvest/deep-abyss rules, dark stone and gold rune board art, teal/gold/purple lightning effects, Cocos implementation plans, MCP automation, generated material assets, or future iterations of this game's reusable art/gameplay rules.
-
hzq510473048 Bundle Cocos AI Automation DevelopmentAutomate Cocos Creator projects with AI agents, MCP tools, and local editor control. Use when Codex needs to install or connect cocos-mcp, inspect or modify a Cocos Creator project, create or tune 3D/2D scenes, add nodes/components/materials/scripts/assets, interact with Cocos Creator UI, preview behavior, debug physics/rendering issues, or document repeatable Cocos AI automation workflows.
-
easyp-tech Bundle Protoc Gen MCP SkillBuild MCP servers from protobuf definitions using protoc-gen-mcp and easyp. Use when: creating an MCP server, generating MCP tools from proto files, building a proto-first MCP server in Go, Python, Java, Kotlin, TypeScript, or JavaScript, configuring easyp for MCP generation, adding MCP tool annotations to protobuf services, implementing MCP tool handlers, setting up ProtoJSON-based MCP tools, or any task involving protobuf-to-MCP code generation. Also use when the user mentions protoc-gen-mcp, mcp proto, proto mcp server, easyp mcp, or wants type-safe MCP bindings from .proto files.
-
carolina1-po Skill Aio Jira Aio Test CreationEnd-to-end workflow: read Jira tickets (Atlassian MCP), generate BDD/Gherkin test cases, create them in AIO Tests via API (Draft), link to Jira requirements, pick folders/cycles, naming conventions, QA lead review handoff. Use when the user provides a Jira URL and wants cases in AIO. Use proactively with the manual QA / AIO persona for ticket-driven test creation.
-
mekko-digital Bundle Elementor MCPBuild and manage Elementor pages on any WordPress site via MCP. Use when user asks to create pages, add widgets, update designs, manage templates, or modify any Elementor content. Reads connection from the project's .mcp.json automatically.
-
nicolasestrem Skill MCP Expertan MCP (Model Context Protocol) expert specializing in creating, configuring, and optimizing MCP int
-
gil-kapel Bundle Debug Fix AgentDebug a failing feature from evidence, isolate the cause, propose the smallest safe fix, and verify the result. Use when the user shares an error, stack trace, failing behavior, terminal output, logs, or asks for root-cause analysis and a targeted fix.
-
gil-kapel Bundle UX User Flow AgentDesign user journeys, flows, screen logic, and state handoffs before visual UI work starts. Use when the user asks for UX flows, journeys, screen logic, onboarding steps, empty or error states, or a UX handoff for UI and development.
-
gil-kapel Bundle Security Review AgentReview a feature, architecture, or code path for practical security risks including auth, permissions, secrets, data exposure, abuse cases, and release blockers. Use when the user asks for a security review, threat model, permissions check, data-handling sanity check, or pre-release risk scan.
-
gil-kapel Bundle Dev Composer AgentImplement a feature in small, testable slices using Composer-style multi-file work. Use when the user asks to build, implement, wire up, or ship a feature across files, especially when code must connect data shape, services, UI, validation, and tests.
-
gil-kapel Bundle Quality Gate AgentRun a merge-ready quality gate by combining code review and QA in one flow. Use when the user asks for code review, QA checks, release readiness, test planning, or "what must be fixed before merge". Produces severity-ranked findings, a targeted test plan, and one high-value automated test.
-
gil-kapel Bundle Cursor Skill FoundationCreate or improve Cursor-ready skills, rules, and expertises for a project. Use when a user wants to author a new SKILL.md, merge several overlapping skills into one stronger workflow, migrate lesson guidance into a reusable agent skill, or decide whether something should be a skill, a Cursor rule, or an ASM expertise.
-
martin-pv Bundle Agent TeamsInteract with Microsoft Teams - send messages, read channels, manage reactions
-
nicolasestrem Skill Agent Organizera senior agent organizer with expertise in assembling and coordinating multi-agent teams
-
nicolasestrem Skill Prompt Engineera senior prompt engineer with expertise in crafting and optimizing prompts for maximum effectiveness
-
zazencodes Skill Agent Skills Setup ManagerSet up, repair, re-run, or inspect the agent-skills monorepo. Use when the user wants to install the monorepo for the first time, add a new agent (codex/copilot/cursor/gemini) to an existing setup, check the status of their symlinks, repair drift, or ask any "set up my agent skills" / "configure agent-skills-monorepo" question. Operates on the repo whose root contains `setup_symlinks.py` and `AGENTS.md` describing the agent-skills monorepo. Do NOT use for unrelated skill authoring or other repos.
-
inhyeoklee Bundle Paper2slidesGenerate a show-ready journal club presentation from a scientific paper PDF using the paper2slides library and agent-driven scientific comprehension.
-
yht0827 Bundle Tdd TeamTDD를 수행하는 agent team을 구성할 때 쓰는 스킬. Team Lead가 개발 요구사항을 받아 task로 나누고, Red agent는 실패 테스트 작성과 실패 확인, Green agent는 테스트 통과를 위한 최소 구현, Refactor agent는 통과 상태를 유지하며 리팩터링을 담당한다. tmux 4분할 agent team이 필요할 때 사용한다.
-
martin-pv Skill Create SkillCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
-
martin-pv Skill CLI Hub Meta SkillDiscover agent-native CLIs for professional software. Access the live catalog to find tools for creative workflows, productivity, AI, and more.
-
nicolasestrem Skill Multi Agent Coordinatora senior multi-agent coordinator with expertise in orchestrating complex distributed workflows
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 docutect-ai-mcp, mindstudio-generate-text-block-prompting-skill, unity-mcp-bridge. 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.