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 Uisato Ableton MCP Extended Ableton MCP ExtendedAbleton Songwriter
- tomevault-io Bundle Usernametron Claude Code Kickstart Agent Factory
Agent Factory — Development Team Agent Generator
- tomevault-io Bundle Deep Gemini
Deep technical documentation generation workflow using zen mcp's clink and docgen tools. First uses clink to launch gemini CLI in WSL for code analysis, then uses docgen for structured document generation with complexity analysis. Specializes in documents requiring deep understanding of code logic, model architecture, or performance bottleneck analysis. Use when user requests "use gemini for deep analysis", "generate architecture analysis document", "analyze performance bottlenecks", "deeply understand code logic", or similar deep analysis tasks. Default output is .md format. Use when this capability is needed.
- tomevault-io Bundle Main Router
Intelligent skill router that analyzes user requests and automatically dispatches to the most appropriate skill(s) or zen-mcp tools. Routes to zen-chat for Q&A, zen-thinkdeep for deep problem investigation, codex-code-reviewer for code quality, simple-gemini for standard docs/tests, deep-gemini for deep analysis, or plan-down for planning. Use this skill proactively to interpret all user requests and determine the optimal execution path. Use when this capability is needed.
- tomevault-io Bundle Senior Developer
Senior developer agent for the Pulse JS framework. Use this skill to implement features, fix bugs, write production code, and refactor modules. Strictly follows the software architect's decisions (ADRs, design principles, API conventions). Handles runtime modules, compiler code, CLI commands, and build tool integrations with emphasis on code quality, performance, and framework consistency. Use when this capability is needed.
- tomevault-io Bundle Analyzing Crypto Weakness
Identifies weak cryptographic algorithms, hardcoded keys, and insecure key management practices in binary code. Use when analyzing encryption/decryption, authentication mechanisms, or reviewing cryptographic implementations. Use when this capability is needed.
- tomevault-io Bundle Detecting Arbitrary Write
Detects arbitrary write vulnerabilities by identifying unchecked array indexing and out-of-bounds memory writes. Use when analyzing memory write operations, pointer arithmetic, or investigating code execution vulnerabilities. Use when this capability is needed.
- tomevault-io Bundle Writing Skill
Write or refactor an Agent Skill / SKILL.md (agentskills.io spec; portable across Cursor, Claude Code, etc.). Use when user asks to 写/create/refactor/audit/优化 a skill or SKILL.md, or asks why a skill 没触发/太长. Do NOT use for Cursor Rules, CLAUDE.md, AGENTS.md, MCP server. Use when this capability is needed.
- tomevault-io Bundle Golang Aip Pr Review
Use this skill when asked to review a GitHub Pull Request for compliance with Google AIP (API Improvement Proposals) standards in Go code. Triggers include "review this PR for AIP compliance", "check if this PR follows AIP standards", "AIP review", or any request to audit Go API code against Google's API design guidelines. Requires the GitHub MCP connector to be active.
- tomevault-io Bundle Whatifwedigdeeper MCP Deep Learning Course Learn
Learn from Conversation
- tomevault-io Bundle Lmstudio Orchestrator
Deterministic multi-agent orchestration system for LMStudio enabling constraint-driven agent composition, semantic field navigation, and thermodynamic resource allocation. Use when orchestrating local LLM swarms, building multi-agent systems with validation, implementing constraint-based configurations, or requiring deterministic agent composition from discovered model states. Use when this capability is needed.
- tomevault-io Bundle Winbda Claude Skills Collection AI Agent Builder
ai-agent-builder
- tomevault-io Bundle Markdown Segment Translator
长文档Markdown分段翻译技能（Agent自己翻译） Use when this capability is needed.
- tomevault-io Bundle Hanx Youtube Researcher
Specialized YouTube video analysis with domain-specific templates (general, trading strategy, framework/tool). Extends youtube-video-analysis with structured analysis prompts from hanx YouTube Researcher Agent. Use when this capability is needed.
- tomevault-io Bundle Creating Inline Actions
Interactive button-based UI for XMTP agents following XIP-67. Use when creating menus, confirmation dialogs, selection options, or any button-based interaction. Triggers on inline actions, buttons, menus, or ActionBuilder. Use when this capability is needed.
- tomevault-io Bundle Auto Evolution
Memory-driven self-evolution layer for Agent Skills. Captures usage patterns, learns from errors, and automatically generates reusable knowledge. Use when you want your agent to learn from experience, track skill effectiveness, or generate improvement suggestions. Use when this capability is needed.
- tomevault-io Bundle Zhanlincui Auto Evolution Agent Skills Templates
[Skill Name]
- tomevault-io Bundle Networking Management
Use when designing OCI networks, troubleshooting connectivity, optimizing egress costs, or configuring VCN security. Covers Service Gateway cost savings, VCN CIDR immutability, Security List vs NSG tradeoffs, VCN peering limitations, and Load Balancer subnet requirements.
- tomevault-io Bundle Skill Practicing
Create or update agent instructions and local skills for this repository. Use when asked to modify AGENTS.md, add or refine skills under skills/, audit README/CHANGELOG/SECURITY/CONTRIBUTING/pyproject.toml for stale guidance, or perform no-secrets documentation hygiene checks. Use when this capability is needed.
- tomevault-io Bundle Aedev Tools Adobe Agent Skills Adobe Agent Skills
Overview
- tomevault-io Bundle Creating Claude Agents
Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and validation against schema.
- tomevault-io Bundle Agent Self Correction
AI agent self-correction mechanisms enable agents to detect errors, validate Use when this capability is needed.
- tomevault-io Bundle LLM Cost Optimization
This is an **alias skill** so docs can reference `81-saas-finops-pricing/llm-cost-optimization`. Use when this capability is needed.
- tomevault-io Bundle Amnadtaowsoam Cerebraskills Tool Permission Model
Tool Permission Model
- tomevault-io Bundle AI Agent Super Skill
Comprehensive AI agent building skill merging Perplexity Computer's skill creation, webserver, and automation capabilities with Claude Code's agent orchestration, MCP server building, RAG system construction, subagent coordination, parallel agent dispatching, prompt optimization, and execution planning. Covers designing AI agents, building MCP servers, creating RAG pipelines, orchestrating multi-agent systems, optimizing prompts, and deploying AI-powered workflows. Use when building AI agents, creating MCP servers, designing RAG systems, coordinating subagents, optimizing prompts, or architecting any AI-powered automation. Use when this capability is needed.
- tomevault-io Bundle Effect AI
This skill should be used when the user asks about "Effect AI", "@effect/ai", "LLM integration", "AI tool use", "AI execution planning", "building AI agents", "AI providers", "structured AI output", "AI completions", "Effect OpenAI", "Effect Anthropic", or needs to understand how Effect integrates with AI/LLM services. Use when this capability is needed.
- tomevault-io Bundle Research Before Coding
Use when writing ANY implementation code, fixing bugs, or modifying existing code. Delegates research to a fast subagent that distills WebSearch results into compact RAG-efficient summaries. Main context never sees raw output.
- tomevault-io Bundle Git Wizard Agent
Git power user specializing in complex operations like interactive rebase, bisect, cherry-pick, worktrees, and history rewriting. Expert in branching strategies and merge conflict resolution. Use for advanced git operations or untangling complex git situations. Use when this capability is needed.
- tomevault-io Bundle Hoyvoh Project Based Agent Kit Project Skeleton
See `.claude/commands/project-skeleton.md` for the full workflow.
- tomevault-io Bundle Vllm Omni Diffusion Benchmark Profile
Benchmark, profile, and tune vLLM-Omni diffusion models, especially Wan/Qwen/Helios style pipelines on GPU or NPU. Use this when measuring denoise latency, collecting torch or torch_npu profiler traces, reading ASCEND_PROFILER_OUTPUT artifacts, comparing before/after performance, or diagnosing bottlenecks such as SP communication, VAE convs, data transforms, offload overlap, and RoPE overhead. Use when this capability is needed.
- tomevault-io Bundle Flutter Riverpod Arch
Implement Feature-First architecture with Riverpod state management and Flutter Hooks in Flutter applications Use when this capability is needed.
- tomevault-io Bundle Iml1s Flutter Claude Skills Flutter MCP Testing
核心定位
- tomevault-io Bundle Integrum Global Kailash Vibe Cc Setup 04 Kaizen
Kailash Kaizen - AI Agent Framework
- tomevault-io Bundle Analyze Source Material
Analyze mixed repositories (application code + infrastructure + policies + docs) to extract ALL components for ONE unified threat model. Use when analyzing codebases with multiple source types for threat modeling. Architecture modeling only - do NOT identify vulnerabilities. Use when this capability is needed.
- tomevault-io Bundle API Doc Generator
Generate API documentation from source code, supporting REST APIs, GraphQL, and various documentation formats. Use when this capability is needed.
- tomevault-io Bundle Roi Calculator
Build ROI analyses, TCO comparisons, and value calculators for prospects. Use this skill when a rep needs to justify the investment to a prospect, build a business case with numbers, create an ROI model, compare total cost of ownership, says "build me an ROI calculator", "what's the payback period", "help me show the value", "TCO comparison", or when a prospect asks "what's the return on this?". Also trigger when building value engineering tools, cost-benefit analyses, or investment justification documents. 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 uisato--ableton-mcp-extended--ableton-mcp-extended, usernametron--claude-code-kickstart--agent-factory, deep-gemini. 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.