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 Riligar Dev Databasedatabase patterns for RiLiGar using Drizzle ORM + bun:sqlite. Use when setting up database connections, defining schemas, creating migrations, or writing queries. Covers SQLite on Fly.io volumes with the drizzle-kit workflow. Use when this capability is needed.
- tomevault-io Bundle Security Detection
Detect infrastructure and security-critical file changes to trigger security agent review recommendations ensuring proper security oversight for sensitive modifications. Use when this capability is needed.
- tomevault-io Bundle Rspack Debugging
Helps Rspack users and developers debug crashes or deadlocks/hangs in the Rspack build process using LLDB. Use this Skill when users encounter "Segmentation fault" errors during Rspack builds or when the build progress gets stuck. Use when this capability is needed.
- tomevault-io Bundle Agent Code Analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer Use when this capability is needed.
- tomevault-io Bundle Agent Data Ml Model
Agent skill for data-ml-model - invoke with $agent-data-ml-model Use when this capability is needed.
- tomevault-io Bundle Agent Issue Tracker
Agent skill for issue-tracker - invoke with $agent-issue-tracker Use when this capability is needed.
- tomevault-io Bundle Agent Load Balancer
Agent skill for load-balancer - invoke with $agent-load-balancer Use when this capability is needed.
- tomevault-io Bundle Agent Release Swarm
Agent skill for release-swarm - invoke with $agent-release-swarm Use when this capability is needed.
- tomevault-io Bundle Agent Specification
Agent skill for specification - invoke with $agent-specification Use when this capability is needed.
- tomevault-io Bundle Swarm Orchestration
Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems. Use when this capability is needed.
- tomevault-io Bundle Git Atomic Commits
Organize uncommitted changes into atomic Git commits using Conventional Commits. Use before opening a PR or merging to produce a clean, reviewable history where each commit represents one logical change. Use when this capability is needed.
- tomevault-io Bundle Typescript MCP
MCP servers with TypeScript on Cloudflare Workers using @modelcontextprotocol/sdk. Use for API integrations, stateless tools, edge deployments, or encountering export syntax, schema validation, memory leak, CORS, auth errors. Use when this capability is needed.
- tomevault-io Bundle Class
Use this skill when creating a new class or asking how to model a new class in ShapeCrawler.
- tomevault-io Bundle Debugging And Error Recovery
Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing. Use when this capability is needed.
- tomevault-io Bundle Code Review Agent
Reviews code for bugs, security issues, and breaking changes. Produces prioritized findings on quality, vulnerabilities, and regressions. Use when asked to review code or check a PR diff. Use when this capability is needed.
- tomevault-io Bundle Generating Agents
Scaffolds a complete Claude Code agent. Generates frontmatter, system prompt, and file structure for a new agent. Use when the user asks to create, scaffold, or generate an agent. Use when this capability is needed.
- tomevault-io Bundle Gem LLM Debug MCP
Diagnose Model Context Protocol (MCP) server issues for the GEM-LLM Claude Code setup — connection failures, missing tools, permission prompts, env var/token problems, npx package resolution, log inspection. Use when the user says "MCP 안 떠", "MCP 디버깅", "MCP 서버 연결 실패", "github mcp 토큰 에러", "filesystem mcp 권한", "firecrawl mcp 안됨", "mermaid mcp 동작 안함", "mcp 도구 안 보여", "mcp 로그 어디". Inspects ~/.claude/settings.json mcpServers config, runs npx <pkg> --help to check resolution, validates env vars, and tails Claude Code MCP stderr. Use when this capability is needed.
- tomevault-io Bundle Agentica Prompts
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity Use when this capability is needed.
- tomevault-io Bundle Openai Responses
OpenAI Responses API for stateful agentic applications with reasoning preservation. Use for MCP integration, built-in tools, background processing, or migrating from Chat Completions. Use when this capability is needed.
- tomevault-io Bundle Team Shinchanverify Agents
Use when you need to validate agent schema compliance and reference integrity.
- tomevault-io Bundle Analyze Coverage
Analyze test coverage and identify gaps with actionable recommendations Use when this capability is needed.
- tomevault-io Bundle Changelog Format
Keep a Changelog format guidelines and entry writing best practices. Use when writing changelog entries, updating CHANGELOG.md, or following Keep a Changelog specification. Use when this capability is needed.
- tomevault-io Bundle Validate Adapter
Validates adapter files against live platform documentation to detect stale mappings,missing features, and outdated version information
- tomevault-io Bundle MCP Graveyard
Audit which MCP server tools your Claude Code sessions actually invoke. Use when the user wants to find dead MCP servers (configured but never called), hallucinated MCP tool calls, or per-project MCP usage. Triggers on "which MCP servers don't I use?", "clean up MCP config", "remove unused MCP servers", "audit MCP tools". Runs locally; reads ~/.claude session JSONL logs and ~/.claude.json. No network calls. Use when this capability is needed.
- tomevault-io Bundle Idumb Stress Test
META package for stress-testing the iDumb framework itself - validates agent coordination, integration completeness, and regression prevention Use when this capability is needed.
- tomevault-io Bundle Sleek Design Mobile Apps
Use when the user wants to design a mobile app, create screens, build UI, or interact with their Sleek projects. Covers high-level requests ("design an app that does X") and specific ones ("list my projects", "create a new project", "screenshot that screen").
Audited - tomevault-io Bundle Request Codex Review
Use after Claude opens a PR to have Codex review the diff and post findings back to the PR. Verifies the Codex CLI is current before delegating; briefs the codex:codex-rescue agent so Codex itself never tries to access GitHub from inside its sandbox; posts a single structured comment with the standard AI-disclaimer prefix; verifies the comment landed before reporting success. Auto-trigger when Claude has just pushed a branch and run `gh pr create` (or after Spencer / a teammate has opened a PR you're about to review). Use when this capability is needed.
- tomevault-io Bundle Softaworks Agent Toolkit Web To Markdown
web-to-markdown
- tomevault-io Bundle Dipeo Package Maintainer
Router skill for DiPeO runtime Python code (execution handlers, service architecture, domain models, LLM infrastructure). Use when task mentions node handlers, EventBus, ServiceRegistry, Envelope pattern, or domain logic. For simple tasks, handle directly; for complex work, escalate to dipeo-package-maintainer agent. Use when this capability is needed.
- tomevault-io Bundle Generate MCP Server
Use when generating an MCP server from an OpenAPI spec with Speakeasy. Triggers on "generate MCP server", "MCP server", "Model Context Protocol", "AI assistant tools", "Claude tools", "speakeasy MCP", "mcp-typescript
- tomevault-io Bundle AI Agent Defi Guide
Guide for teaching AI agents DeFi fundamentals — key concepts, protocol categories, transaction patterns, and common user requests. Essential for any OpenClaw agent that helps users with DeFi tasks including swapping, lending, yield farming, and portfolio management. Use when this capability is needed.
- tomevault-io Bundle Validate Run
Validate all checkpoints from an agent run directory in parallel. Spawns test-validator agents for each checkpoint and summarizes results. Invoke with /validate-run <run_path> [problem]. Use when this capability is needed.
- tomevault-io Bundle Minimal Example
Use when working with a minimal example skill demonstrating the required structure
- tomevault-io Bundle Langchain Prompting
Prompt Engineering with Langchain. prompt templates. Use when this capability is needed.
- tomevault-io Bundle Agentscope
AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or Java agent development. Specializes in non-blocking code, tool integration, hooks, pipelines, and production-ready agent applications. Use when this capability is needed.
- tomevault-io Bundle Sisyphus
Multi-agent orchestration system that persists until all tasks are complete. Delegates to specialized subagents and coordinates parallel execution. 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 riligar-dev-database, security-detection, rspack-debugging. 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.