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 Eugenepyvovarov Mcpbundler Agent Skills Marketplace Spec ToSpec-to-Plan Skill
- tomevault-io Bundle Aiken Dex Security Audit
Adversarial security audit playbook for Plutus V3 Aiken DEX contracts (threat model, invariants, findings, tests, tx repro shapes). Use when this capability is needed.
- tomevault-io Bundle Flux Point Studios Cardano Agent Skills Cardano CLI Transact
cardano-cli-transactions
- tomevault-io Bundle Orchestrating Workshop To Pm
Convert team workshop outputs to project management artifacts Use when this capability is needed.
- tomevault-io Bundle Google Antigravity Sdk
Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK. ACTIVATE this skill when the user wants to create, configure, or orchestrate Google Antigravity agents. Use when this capability is needed.
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Dataset Spli
Overview
- tomevault-io Bundle Jeremylongshore Claude Code Plugins Plus Skills Ml Model Tra
Overview
- tomevault-io Bundle Juandelossantos Another Agent Skills Git Workflow And Versio
Git Workflow and Versioning
- tomevault-io Bundle Kevintsengtw Dotnet Testing Agent Skills Dotnet Testing Adva
.NET 進階測試技能總覽
- tomevault-io Bundle Bilibili History MCP
Use when an AI client needs to read BilibiliHistoryFetcher data through its read-only LAN MCP server without loading the full project context.
- tomevault-io Bundle Cross Agent Skill Sync
Use when discovering, verifying, or sharing SKILL.md based skills across local Hermes, Codex, OpenClaw, Gemini, OpenCode, Claude-adjacent, and generic agent skill roots without overwriting existing skills or leaking private paths.
- tomevault-io Bundle Ncu Cuda Profiling
Automated NCU (Nsight Compute) profiling workflow with full metrics collection and persistent storage Use when this capability is needed.
- tomevault-io Bundle Gemini Exploration Patterns
Strategic patterns for codebase exploration using Gemini's large context window. Covers token thresholds, model routing, and exploration strategies. Use when deciding between Claude and Gemini for exploration, analyzing large codebases, or choosing between Flash and Pro models for context size. Use when this capability is needed.
- tomevault-io Bundle Exoskeletons AI Agent Identity Skill
You are about to mint an Exoskeleton — an onchain identity NFT Use when this capability is needed.
- tomevault-io Bundle Tax Planning Strategy AI Agent Skill
You are a tax planning strategist. When activated, walk the user Use when this capability is needed.
- tomevault-io Bundle Video Url Transcriber
Transcribe a video/audio URL into timestamped JSON using yt-dlp + ffmpeg + faster-whisper. Use when an agent needs platform-agnostic URL-to-transcript ingestion for downstream analysis. Use when this capability is needed.
- tomevault-io Bundle Cisco Network Diagram
Generate Draw.io network topology diagrams from Cisco router and switch configurations. Use when asked to visualize network topology, create network diagrams, map network infrastructure, or generate visual representations from Cisco device configs. Supports parsing show commands, configuration files, CDP/LLDP neighbor data, and routing protocol information to automatically create professional network diagrams. Use when this capability is needed.
- tomevault-io Bundle Ecc Claude Engineering MCP Server Builder
OpenClaw bridge skill for engineering mcp server builder. Use when tasks match this specialized claude-skills capability and need OpenClaw-native execution with explicit verification. Use when this capability is needed.
- tomevault-io Bundle AI Agent Multi Agent Coordination
Use when designing systems where multiple agents collaborate on one task — supervisor/worker, debate, plan-execute, peer handoff. Covers handoff message contracts, shared scratchpad, conflict resolution, deadlock detection, and the cost/SLA discipline that keeps multi-agent setups from spiralling.
Audited - tomevault-io Bundle Peterbamuhigire Skills Web Dev AI Agent Observability Evalua
AI Agent Observability Evaluation
- tomevault-io Bundle Policyengine Github Agent Skill
Guidance for working with the PolicyEngine GitHub agent bot Use when this capability is needed.
- tomevault-io Bundle Agents Md Guide
Guide for using and supporting the AGENTS.md standard in VS Code. Use this when asked about AGENTS.md, custom instructions, or repo-level AI agent configuration. Use when this capability is needed.
- tomevault-io Bundle UI Agent Patterns
Patterns for delegating UI work to specialized agents. Covers synthesis-master vs specialized agents, multi-agent UI generation workflows, and orchestration strategies for complex UI tasks. Use when this capability is needed.
- tomevault-io Bundle Higashi Kota LLM Internal RAG Chat Senior UI Designer
Senior UI Designer Skill
- tomevault-io Bundle Flutter Widgets
Build maintainable Flutter UI components with composition and theming. Use when building, refactoring, or reviewing widget implementations. Use when this capability is needed.
- tomevault-io Bundle Work Queue
Activate when user has a large task to break into smaller work items. Activate when user asks about work queue status or what remains to do. Activate when managing sequential or parallel execution. Creates and manages .agent/queue/ for cross-platform work tracking. Use when this capability is needed.
- tomevault-io Bundle AI Agent Isolation Testing
Implements isolated work tree testing for AI agents with strict error checking. Triggered when developing multi-agent systems or testing agent implementations. Use when agents have overlapping tasks but need independent validation before integration. Use when this capability is needed.
- tomevault-io Bundle Huginn Onboard
Bridge to Starknet from any EVM chain and register with Huginn agent registry. Enables cross-chain agent onboarding with AVNU bridge integration. Use when this capability is needed.
- tomevault-io Bundle Performance Load Testing
Performance load testing workflow for realistic workload simulation, bottleneck detection, and saturation behavior analysis. Use when systems need throughput/latency validation before rollout; do not use for non-performance functional acceptance decisions. Use when this capability is needed.
- tomevault-io Bundle Security Threat Modeling
Security workflow for threat modeling using assets, trust boundaries, attacker capabilities, and abuse paths. Use when systems or major features need explicit security design validation before implementation or major release; do not use for active incident containment. Use when this capability is needed.
- tomevault-io Bundle Langcare Langcare MCP Fhir Clinical Summary Generator
Clinical Summary Generator
- tomevault-io Bundle Langcare Langcare MCP Fhir Insurance Coverage Summary
Insurance Coverage Summary
- tomevault-io Bundle Langcare Langcare MCP Fhir Transition Of Care Summary
Transition of Care Summary
- tomevault-io Bundle Portable Skills
Cross-agent portable skill standard and toolkit. Write skills once, run on Claude Code, Cursor, Windsurf, GitHub Copilot, and any Agent Skills compatible tool. Includes format specification, conversion tools, and compatibility matrix. Use when this capability is needed.
- tomevault-io Bundle Materialtrace AI Automation
Coordinate MaterialTrace specialist subagents and maintain repository agent guidance. Use when Codex should delegate to role-specific agents, update AGENTS.md or project skills, design agent workflows, review subagent outputs, or keep automation aligned with the source of truth and GitHub Project process. Use when this capability is needed.
- tomevault-io Bundle Codex Project Agents Init
Initialize or revise project-level AGENTS.md files from an existing codebase, seed specs, or repo docs. Use when asked to create AGENTS.md, onboard Codex to a repo, turn seed artifacts into agent instructions, or audit project guidance. 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 eugenepyvovarov--mcpbundler-agent-skills-marketplace--spec-to-plan, aiken-dex-security-audit, flux-point-studios--cardano-agent-skills--cardano-cli-transactions. 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.