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 Saeed Vayghan Gemini Agent Skills Cpp ProYou are a senior C++ developer with deep expertise in modern C++20/23 and systems programming, specializing in high-performance applications, template metaprogramming, and low-level optimization. Your focus emphasizes zero-overhead abstractions, memory safety, and leveraging cutting-edge C++ features while maintaining code clarity and maintainability.
- tomevault-io Bundle Saeed Vayghan Gemini Agent Skills PHP Pro
You are a senior PHP developer with deep expertise in PHP 8.3+ and modern PHP ecosystem, specializing in enterprise applications using Laravel and Symfony frameworks. Your focus emphasizes strict typing, PSR standards compliance, async programming patterns, and building scalable, maintainable PHP applications.
- tomevault-io Bundle Cloudflare Agents
Build AI agents on Cloudflare Workers with MCP integration, tool use, and LLM providers. Use when this capability is needed.
- tomevault-io Bundle Firecrawl Scraper
Firecrawl v2.5 API for web scraping/crawling to LLM-ready markdown. Use for site extraction, dynamic content, or encountering JavaScript rendering, bot detection, content loading errors. Use when this capability is needed.
- tomevault-io Bundle Openai Assistants
OpenAI Assistants API v2 for stateful chatbots with Code Interpreter, File Search, RAG. Use for threads, vector stores, or encountering active run errors, indexing delays. ⚠️ Sunset August 26, 2026. Use when this capability is needed.
- tomevault-io Bundle Add API Endpoint
Add a new API endpoint following project conventions (Zod, route registration, client, tests). Use when creating or extending backend API routes. Use when this capability is needed.
- tomevault-io Bundle Claude Code Teams
Reference for Claude Code Agent Teams — lifecycle, messaging, spawning, orchestration, and hooks Use when this capability is needed.
- tomevault-io Bundle Shareai Lab Shareai Skills Shareai Skills
Agent Builder
- tomevault-io Bundle Text To Image Generation
Generate stunning images from text descriptions using state-of-the-art AI models Use when this capability is needed.
- tomevault-io Bundle Shunk031 Dotfiles Convert To Transformers
Hugging Face Transformers Model Conversion
- tomevault-io Bundle Hm L3 Opencode Non Interactive Shell
This skill should be used when the user asks to "write shell commands", "run non-interactive shell", "CI=true safety", "banned shell commands", "shell environment variables", "headless agent execution", "shell command safety", "avoid interactive prompts", or "non-interactive flags". Use when this capability is needed.
- tomevault-io Bundle Convert Miniapp
Converts a standalone browser-based JavaScript app into an OpenYoghurt mini-app with manifest, tool handlers, and Claude agent integration. Use when the user asks to convert, adapt, or integrate a JS app with the OpenYoghurt platform.
- tomevault-io Bundle Chartjs Chart Types
This skill should be used when the user asks "how to create a line chart", "Chart.js bar chart", "pie chart Chart.js", "doughnut chart", "radar chart", "polar area chart", "bubble chart", "scatter chart", "mixed chart", "combo chart", "area chart", "stacked chart", "horizontal bar chart", "Chart.js chart types", "dataset properties", "chart data structure", or needs help implementing specific Chart.js v4.5.1 chart types. Use when this capability is needed.
- tomevault-io Bundle Self Evaluation
End-of-session self-evaluation for continuous improvement. Run before finalizing any session to capture lessons learned, identify skill updates, and improve agent effectiveness. Use when completing a task, reviewing work quality, or improving project skills. Use when this capability is needed.
- tomevault-io Bundle Chunking Strategies
Document chunking strategies for RAG systems. Use when implementing document processing pipelines to determine optimal chunking approaches based on document type and retrieval requirements. Use when this capability is needed.
- tomevault-io Bundle Python Imports
Python import style guidelines for absolute and relative imports Use when this capability is needed.
- tomevault-io Bundle Python Pathlib
Python pathlib usage guidelines for file and directory operations Use when this capability is needed.
- tomevault-io Bundle MCP Server Patterns
Build and consume MCP servers — TypeScript SDK, tools, resources, prompts, stdio vs HTTP transport, Zod validation, health monitoring. Use this skill whenever configuring MCP servers in claude.json, building a custom MCP server, debugging MCP connection issues, or working with the GitHub/Supabase/Context7 MCPs. Also use when the user mentions "MCP", "tool server", "model context protocol", or when mcp-health-check hook reports failures. Use when this capability is needed.
- tomevault-io Bundle Genaisemantic Conventions
OpenTelemetry GenAI semantic conventions for agent instrumentation - the standard attributes for LLM observability Use when this capability is needed.
- tomevault-io Bundle Systemcc
Intelligent workflow router with Lyra AI optimization, build config detection, and triple code review. Auto-analyzes complexity, risk, and scope to execute the optimal workflow automatically. Use when this capability is needed.
- tomevault-io Bundle Agent Step Sequencer
Multi-step scheduler for in-depth agent requests. Detects when user needs multiple steps, suggests plan and waits for confirmation, persists state, and runs heartbeat-aware flow. Use when requests have 3+ actions, sequential dependencies, output dependencies, or high scope/risk. Use when this capability is needed.
- tomevault-io Bundle Behavioral Guardrails
Core behavioral corrections for LLM coding. Reduces over-engineering, surfaces assumptions, enforces surgical changes, and defines verifiable success criteria. Use when writing code, reviewing code, fixing bugs, or implementing features. Use when this capability is needed.
- tomevault-io Bundle Github Fix CI
Respond to GitHub Actions failures with evidence-based triage, root-cause isolation, and minimal-risk fixes. Use when GitHub-hosted checks fail and teams need a repair plan tied to failed jobs; do not use for non-GitHub runtime architecture or data-layer design. Use when this capability is needed.
- tomevault-io Bundle Rust Neckbeard
Dedalus Rust correctness and style rules. Use when writing, reviewing, or refactoring any Rust code in the host-agent, enclave, or packages/rust workspaces. Covers return-value naming, error design, must_use, visibility, RAII, fail-closed, and all hard limits from style.md and rust.mdx. Use when this capability is needed.
- tomevault-io Bundle Fastapi Sse MCP Protocol
Host a hosted MCP (Model Context Protocol) server over FastAPI's StreamingResponse using API-key auth, a session dict, and a tool registry surfaced via the 2025-03-26 Streamable HTTP spec. Use when this capability is needed.
- tomevault-io Bundle Koshkinvv IOS Agent Skills IOS Concurrency
iOS Concurrency Skill
- tomevault-io Bundle Libgdx 3d Rendering
Use when writing libGDX Java/Kotlin code involving 3D rendering — ModelBatch, ModelInstance, Model loading (G3DJ/G3DB/OBJ), ModelBuilder procedural meshes, Environment and lighting (DirectionalLight/PointLight), PerspectiveCamera, Materials and Attributes (ColorAttribute/TextureAttribute/BlendingAttribute), AnimationController, or camera controllers (CameraInputController/FirstPersonCameraController). Use when debugging black 3D models, missing lighting, wrong camera setup, animation not playing, or model disposal issues.
- tomevault-io Bundle AI Sdk 6
Vercel AI SDK v6 development. Use when building AI agents, chatbots, tool integrations, streaming apps, or structured output with the ai package. Covers ToolLoopAgent, useChat, generateText, streamText, tool approval, smoothStream, provider tools, MCP integration, and Output patterns. Use when this capability is needed.
- tomevault-io Bundle Lambdatest Agent Skills Hyperexecute Skill
HyperExecute Skill
- tomevault-io Bundle Lambdatest Agent Skills Laravel Dusk Skill
Laravel Dusk Skill
- tomevault-io Bundle Lwy Knowledge Consolidation
Use when the user wants to persist a single insight from the current chat as a structured, project-local doc — debugging breakthroughs, hard-won config, workflow steps, or post-mortem lessons. Triggers: 'save this', 'document this', 'we figured it out', '记录下来', '总结一下'. Writes to <project>/.{trae,claude,cursor,windsurf}/knowledges/. For global compounding knowledge (architecture, patterns, APIs), use llm-wiki instead.
- tomevault-io Bundle Nest Server Updating
Provides migration guides, release notes, and error solutions for updating @lenne.tech/nest-server to a newer version. Covers version-specific breaking changes, stepwise upgrade strategies, and starter project comparisons. Activates for nest-server version updates, upgrades, migrations, breaking changes between versions, "pnpm run update", TypeScript errors after upgrading, or stepwise migration planning. Delegates execution to the lt-dev:nest-server-updater agent. NOT for writing NestJS code or building features (use generating-nest-servers). NOT for general npm package updates (use maintaining-npm-packages).
- tomevault-io Bundle Wc REST API V4
Use the WooCommerce REST API v4 (namespace wc/v4, since WC 10.2) Use when this capability is needed.
- tomevault-io Bundle Skill Md Validator
Validates SKILL.md files for format, completeness, and best practices
- tomevault-io Bundle Ltczding Gif Ref Downloader Ref Downloader
Ref Downloader — Agent Runbook
- tomevault-io Bundle Agent Template
Create new GitHub Copilot agents with proper structure and frontmatter. Use when asked to create a skill, make a new agent, or scaffold agent files. 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 saeed-vayghan--gemini-agent-skills--cpp-pro, saeed-vayghan--gemini-agent-skills--php-pro, cloudflare-agents. 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.