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 Coding Backend OrchestrationUse when the user explicitly asks Guardian to launch or check an external coding assistant such as Codex, Claude Code, Gemini CLI, or Aider.
- tomevault-io Bundle Tool Guide
Use this skill to determine which MCP tool or service to use for a specific task (search, documentation, browser automation).
- tomevault-io Bundle Tryboy869 Dojutsu For AI Nextjs Typescript Cursorrules Promp
nextjs-typescript-cursorrules-prompt-file
- tomevault-io Bundle Migrating Agents Md To Control Flow
Audits repositories that rely heavily on AGENTS.md, CLAUDE.md, copilot instructions, or similar agent instruction files, then migrates repeatable workflows into skills, mandatory checks into scripts/hooks/CI, and leaves only stable repo context, policy, and workflow entrypoints in repo instructions. Use when Codex is asked to reduce long natural-language agent instructions, create agent skills from repo workflows, codify mandatory checks, or produce an instruction migration report. Use when this capability is needed.
- tomevault-io Bundle Goose Extensible AI Coding Agent By Block
Use when working with an open-source, extensible AI agent from Block (formerly Square) that goes beyond code suggestions to install packages, execute commands, edit files, and run tests. Supports any LLM and extends via MCP servers for tool integration.
- tomevault-io Bundle GRAPHQL Schema Stitching Federation Agent
Manages Apollo Federation v2 supergraph composition from subgraph schemas, validating composition rules and generating rover CLI deployment manifests. Handles @key, @shareable, and @override directives.
- tomevault-io Bundle Braintrustdata Braintrust Claude Plugin Troubleshoot Braintr
This Claude plugin automatically sets up a Braintrust MCP connection. The connection reads the `BRAINTRUST_API_KEY` environment variable to establish the MCP connection.
- tomevault-io Bundle Building MCP Servers
Expert at integrating MCP servers into Claude Code plugins. Auto-invokes when configuring MCP servers (stdio/SSE/HTTP/WebSocket), writing .mcp.json files, or adding external tool integrations. Use when this capability is needed.
- tomevault-io Bundle Langchain Agents Deepagents Code
Use when editing a DeepAgents project — adding tools, sub-agents, modifying the system prompt, choosing a filesystem backend, or composing extra middlewares (retries, fallbacks, HITL) on top.
- tomevault-io Bundle Langchain Agents Langsmith Evals
Use when authoring eval datasets, writing evaluators, running evals against a LangChain / LangGraph / DeepAgents project, comparing eval results between runs, or writing unit/integration tests for an agent.
- tomevault-io Bundle Openclaw AI Agent Verification
Use this skill when you need to audit OpenClaw AI agent configurations for security risks. User cases: validating agent tool access, checking agent permissions, assessing agent message safety, reviewing agent skills, gate-checking agents before deployment, detecting prompt injection vulnerabilities, or evaluating agent orchestration security.
- tomevault-io Bundle Conversation History
Use when the user asks what was said earlier in a chat, wants an old decision, exact wording, prior links, or suspects the agent forgot conversation context across Telegram, BlueBubbles, Feishu, ChatGPT, Claude, or other archived chat sources. Search memory_search first, then search the local conversation archive for exact recall.
- tomevault-io Bundle Evaluating Code Models
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards. Use when this capability is needed.
- tomevault-io Bundle Code Complete Issue Pr Handling
Use when all work from ACE_TASK.md is finished to create a PR via GitHub MCP, move the issue to In review with proper issue comments via Appforge MCP, assign to repo-owner, and write ACE_TASK_DONE.json. Also defer to blocked-task-handling when developer input is required.
- tomevault-io Bundle Langchain4j MCP Server Patterns
Provides LangChain4j patterns for implementing MCP (Model Context Protocol) servers, creating Java AI tools, exposing tool calling capabilities, and integrating MCP clients with AI services. Use when building a Java MCP server, implementing tool calling in Java, connecting LangChain4j to external MCP servers, or securing tool exposure for agent workflows.
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Dbt Model Ge
Dbt Model Generator
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Openrouter M
OpenRouter Model Routing
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Tensorflow M
Tensorflow Model Trainer
- tomevault-io Bundle Agent Claude Code Extension Builder
Construction d'extensions et skills pour Claude Code — slash commands, hooks, intégration MCP et commandes personnalisées. Se déclenche avec "extension Claude Code", "skill Claude", "slash command", "Claude Code plugin", "custom command Claude". Use when this capability is needed.
- tomevault-io Bundle Modbender Skill Library MCP Butler AI Agent Treasury Orchest
Butler - AI Agent Treasury & Orchestration Skill
- tomevault-io Bundle Clawskill Mine Rtc Tokens With Your AI Agent
Mine RTC (RustChain Tokens) by proving your agent runs on real Use when this capability is needed.
- tomevault-io Bundle Laravel Extended Relationships Development
Use this skill when working with MrPunyapal Laravel Extended Relationships package. Activate when adding or fixing `belongsToManyKeys`, `hasManyKeys`, `hasManyArrayColumn`, or `belongsToArrayColumn` relationships, or when a Laravel model stores multiple related keys in columns or JSON array columns. Covers trait setup, relationship definitions, eager and lazy loading, inverse relationship patterns, and array-string matching. Do not use for standard Eloquent relationships that Laravel already supports directly.
- tomevault-io Bundle Brainstorming Coach
brainstorming-coach agent Use when this capability is needed.
- tomevault-io Bundle Presentation Master
presentation-master agent Use when this capability is needed.
- tomevault-io Bundle Configure Git CLI
Configure Git CLI with GitHub authentication using environment variables (GITHUB_EMAIL, GITHUB_NAME, GITHUB_PAT) Use when this capability is needed.
- tomevault-io Bundle Tryboy869 Dojutsu For AI Android Jetpack Compose Cursorrules
android-jetpack-compose-cursorrules-prompt-file
- tomevault-io Bundle Kotlin Ktor Development Cursorrules Prompt File
Apply for kotlin-ktor-development-cursorrules-prompt-file. - Follow **SOLID**, **DRY**, **KISS**, and **YAGNI** principles - Adhere to **OWASP** security best practices - Break tasks into smallest units and solve problems step-by-step Use when this capability is needed.
- tomevault-io Bundle Tryboy869 Dojutsu For AI Nodejs Mongodb Cursorrules Prompt F
nodejs-mongodb-cursorrules-prompt-file-tutorial
- tomevault-io Bundle Translation Harness Assistant
Helps volunteers set up, update, and troubleshoot the Translation Harness MCP server for Claude Desktop. Use when someone asks how to get started with the translation harness, install or configure it, connect it to Claude Desktop, update it after changes, or fix a problem with it not working. Use when this capability is needed.
- tomevault-io Bundle Enterprise AI Agent Deployment Framework
Use when working with a structured framework for planning and rolling out agentic AI across an enterprise, emphasizing workforce enablement, process redesign with human oversight, and scaling into durable product capabilities.
- tomevault-io Bundle Fastapi App Architecture Review
Use when reviewing FastAPI application architecture, route design, dependency injection, Pydantic schemas, async boundaries, and background tasks.
- tomevault-io Bundle Instructor Structured Data Extraction From Llms
Instructor is a multi-language library for extracting structured, validated data from LLM outputs. It patches LLM client libraries to return Pydantic models (Python) or Zod schemas (TypeScript) instead of raw text, supporting 15+ providers including OpenAI, Anthropic, and Google. Use when this capability is needed.
- tomevault-io Bundle Stripe Agent Toolkit For AI Payment Integration
Use when working with the official Stripe Agent Toolkit provides Python and TypeScript libraries plus a hosted MCP server for integrating Stripe payment APIs with AI agent frameworks. Supports OpenAI, LangChain, CrewAI, and Vercel AI SDK through function calling with granular API key permissions.
- tomevault-io Bundle Use Sim For Orchestrated AI Agent Workflow Runs
Build and run repeatable AI agent workflows in Sim by composing agents, tools, triggers, and integrations on a visual canvas. Use when this capability is needed.
- tomevault-io Bundle Langchain Middleware Skill
LangChain uses Middleware as a way to more tightly control what happens inside the agent. There are many built-in middleware components supplied by LangChain for common needs, and custom middleware can be created. Use when this capability is needed.
- tomevault-io Bundle Eugenepyvovarov Mcpbundler Agent Skills Marketplace Wordpres
WordPress Plugin Development (Core)
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 coding-backend-orchestration, tool-guide, tryboy869--dojutsu-for-ai--nextjs-typescript-cursorrules-prompt-file. 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.