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 Building AI Agent On CloudflareGenerates production-ready agent code deployed to Workers.
- tomevault-io Bundle Maximus Review
This skill should be used when the user wants to review Maximus Loop results, analyze run performance, or check execution status. Triggers on "review the run", "analyze maximus results", "check status", "how is the run going", "show me the summary", "what's the progress", "/maximus-review", or when the user wants post-execution analysis with cost/performance insights. Use when this capability is needed.
- tomevault-io Bundle Video Analysis
Use when user wants to analyze video files for quality, UI/UX, aesthetics, or technical execution feedback using FFmpeg frame extraction and Claude vision
- tomevault-io Bundle Pict Test Designer
Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code. Analyzes inputs, generates PICT models with parameters, values, and constraints for valid scenarios using pairwise testing. Outputs the PICT model, markdown table of test cases, and expected results. Use when this capability is needed.
- tomevault-io Bundle Agent Zero Research
Deep research, analysis, and comparison tasks using Agent Zero Use when this capability is needed.
- tomevault-io Bundle LLM Vulnerabilities
OWASP Top 10 for LLM Applications (2025) vulnerability knowledge base for identifying, assessing, and remediating security risks in large language model systems. Use when this capability is needed.
- tomevault-io Bundle Nostrstack Dev Workflow
Local development workflow for nostrstack, including running API/gallery with logs, regtest stack usage, MCP Chrome DevTools verification, QA fallback, and environment/setup troubleshooting. Use when starting dev, debugging, reproducing issues, or validating UI/console/network behavior in the nostrstack repo. Use when this capability is needed.
- tomevault-io Bundle Install Chrome Devtools MCP
Install Chrome DevTools MCP server for debugging and network inspection in Claude Code Use when this capability is needed.
- tomevault-io Bundle AI Agent Skills Assistant
Expert assistant for the AI Agent Skills repository. Helps install skills, agents, and extensions; provides guidance on available capabilities by gathering information from installed directories. Use when this capability is needed.
- tomevault-io Bundle Ms Playwright MCP
Apply when automating browser interactions, web scraping, or UI testing with AI agents Use when this capability is needed.
- tomevault-io Bundle Kart Rc Dataobservability Agents Rca Copilot Agent
RCA Copilot Agent
- tomevault-io Bundle Neo4j Support DB
知的障害・精神障害のある方の支援情報を包括的に管理するNeo4jグラフデータベース。汎用neo4j MCPツールを通じてCypherクエリを実行し、計画相談支援業務を支援する。 Use when this capability is needed.
- tomevault-io Bundle Architecture Monolith
Modular monolith architecture workflow for strong domain boundaries, transactional consistency, and operational simplicity in a single deployable. Use when teams need fast delivery and coherent data consistency with controlled complexity; do not use when independent runtime scaling boundaries are mandatory. Use when this capability is needed.
- tomevault-io Bundle DB Migration Strategy
Schema migration strategy workflow for sequencing changes, compatibility windows, and rollback-safe rollout in live systems. Use when schema evolution impacts running services; do not use for static greenfield schemas without deployment constraints. Use when this capability is needed.
- tomevault-io Bundle DB Query Optimization
Query optimization workflow for reducing latency and resource cost through plan-aware rewrites and access-path improvements. Use when hot-path query behavior is the bottleneck; do not use for conceptual schema redesign without workload evidence. Use when this capability is needed.
- tomevault-io Bundle Jest Testing Workflow
Jest verification workflow for JavaScript/TypeScript codebases with deterministic tests, explicit mock boundaries, and actionable CI evidence. Use when JS/TS changes need executable Jest evidence before merge; do not use for browser-level E2E or language-agnostic policy design. Use when this capability is needed.
- tomevault-io Bundle Ml Data Preprocessing
ML data preprocessing workflow for cleaning, normalization, and leakage-safe dataset preparation. Use when training/inference data pipelines need explicit preprocessing decisions; do not use for generic API-layer or infrastructure-only changes. Use when this capability is needed.
- tomevault-io Bundle Stock Analysis Agent
This skill owns the yfinance CLI contract even when Standard Mode is executed by Use when this capability is needed.
- tomevault-io Bundle Langcare Langcare MCP Fhir Mental Health Screening
Mental Health Screening
- tomevault-io Bundle Langcare Langcare MCP Fhir Prenatal Visit Workflow
Prenatal Visit Workflow
- tomevault-io Bundle Openclaw Agent Builder
Build specialized openclaw agents with proper workspace structure, identity, and skills Use when this capability is needed.
- tomevault-io Bundle Itallstartedwithaidea Google Ads Skills Google Ads MCP
Google Ads MCP Server
- tomevault-io Bundle Agentic Vulnerabilities
OWASP Agentic Security Top 10 vulnerability knowledge base for identifying, assessing, and remediating security risks in AI agent systems. Use when this capability is needed.
- tomevault-io Bundle Claude Code Lifecycle Hooks
Configure shell command hooks with exit codes to control Claude Code agent behavior at specific lifecycle points (session start, pre/post tool use). Trigger when you need to prevent agents from modifying protected files like tests or enforce workflow constraints. Use exit code 2 for blocking errors, 0 for success. Use when this capability is needed.
- tomevault-io Bundle Josiahsiegel Claude Plugin Marketplace Fal Model Guide
Quick Reference
- tomevault-io Bundle Jscraik Agent Skills Talk Roberts AI Native Brownfield
Stop Maintaining, Start Evolving: Applying AI-Native Practices to Brownfield Codebases — Katie Roberts
- tomevault-io Bundle Kangarooking System Prompt Skills System Prompt Skills
语音场景优化
- tomevault-io Bundle Git History Investigation
Reconstruct change history using log/show/diff/blame evidence to explain when and why behavior changed. Use when teams need evidence-based history analysis for regressions or ownership questions; do not use for CI workflow design or application behavior implementation. Use when this capability is needed.
- tomevault-io Bundle Kumaran Is Claude Code Onboarding Multi Agent Patterns
Iron Law
- tomevault-io Bundle Commit With Agent
Create a Git commit with agent attribution for ADW workflows. Use after implementing changes to create semantically formatted commits. Use when this capability is needed.
- tomevault-io Bundle Improve Expertise
Run self-improve on an expert's mental model to sync with codebase. Use periodically to keep expertise files accurate. Use when this capability is needed.
- tomevault-io Bundle Mitch Avis Agent Skills Generating Custom Instructions
Generating Custom Instructions
- tomevault-io Bundle Call Academic Search Agent
This skill provides specialized capabilities for call academic search agent. Use when this capability is needed.
- tomevault-io Bundle Call Claude Sonnet 4 Agent
This skill provides specialized capabilities for call claude sonnet 4 agent. Use when this capability is needed.
- tomevault-io Bundle Openclaw Skill Lazy Loader
This skill pairs directly with [OpenClaw Token Optimizer](https://clawhub.ai/Asif2BD/openclaw-token-optimizer). Lazy loading handles **context loading costs**; Token Optimizer handles **model routing, heartbeat budgeting, and runtime costs**. Together they cover the full token lifecycle. Use when this capability is needed.
- tomevault-io Bundle Modbender Skill Library MCP Sovereign Security Auditor
---
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 building-ai-agent-on-cloudflare, maximus-review, video-analysis. 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.