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 CuboxCubox CLI is a callable personal reading memory system that enables you to search, read, and use saved content, perform semantic (RAG-based) queries, access articles, highlights, and metadata, save URLs, update content states, and retrieve annotations and structure such as folders and tags. Use this tool when a task depends on the user’s reading history or requires context from their Cubox library. Use when this capability is needed.
-
tomevault-io Bundle BlintThis file defines practical skills an AI agent should apply when working on `blint`. Use when this capability is needed.
-
tomevault-io Bundle Sync Skills SpecSync the agentpool skills implementation with the official Agent Skills Spec by comparing against the reference repository. Use when this capability is needed.
-
tomevault-io Bundle Phntm7 Skills Prompt CraftPrompt Craft
-
tomevault-io Bundle Pinchtab ColdstartRun the PinchTab cold-start test. Spawns a subagent that follows tests/coldstart/subagent-context.md to validate the documented first-install user journey. Use when asked to 'run cold start', 'cold-start test', or 'test the agent onboarding flow'. Use when this capability is needed.
-
tomevault-io Bundle Agent O RamaLayer 4 Learning and Pattern Extraction for Cognitive Surrogate Systems Use when this capability is needed.
-
tomevault-io Bundle Deepwiki MCPDeepWiki MCP server for AI-powered GitHub repository documentation and Use when this capability is needed.
-
tomevault-io Bundle Koho SheafnnRust sheaf neural networks on k-cells. Candle-based diffusion over cellular Use when this capability is needed.
-
tomevault-io Bundle MCP FastpathDirect FastMCP tool registration bypassing workflow wrappers. Addresses Use when this capability is needed.
-
tomevault-io Bundle Ngrok TunnelSecure tunnel for exposing local MCP servers to Claude, remote agents, and external clients. Supports custom domains, IP whitelisting, and traffic policies. Use when this capability is needed.
-
tomevault-io Bundle Otel TracingOpenTelemetry tracing for agent observations and SPI verification Use when this capability is needed.
-
tomevault-io Bundle Ruizrica Agent Pi Agent Piqa-state-persistence
-
tomevault-io Bundle ManusDelegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing. Use when this capability is needed.
-
tomevault-io Bundle Tot SpecLanguage-agnostic model definition and RPC code generator from YAML specifications. Use for generating type-safe data (Rust, Python, TypeScript, Java, Swift) from a single source of truth, defining RPC service interfaces with request/response types, creating cross-language type definitions for microservices, working with existing .yaml spec files in the project, or creating new model definitions, enum types, or service methods. Use when this capability is needed.
-
tomevault-io Bundle AetherFull-stack AITuber (AI VTuber) orchestrator covering planning, implementation, and operation. Designs and builds real-time streaming pipelines (Chat → LLM → TTS → Avatar → OBS), live chat integration, TTS voice synthesis, Live2D/VRM avatar control, lip-sync and expression mapping, and OBS WebSocket streaming automation. Use when this capability is needed.
-
tomevault-io Bundle ApacheApache HTTP Server web server. Use for traditional web hosting. Use when this capability is needed.
-
tomevault-io Bundle AppiumAppium mobile app automation. Use for mobile testing. Use when this capability is needed.
-
tomevault-io Bundle CursorCursor AI-powered code editor with chat. Use for AI-assisted coding. Use when this capability is needed.
-
tomevault-io Bundle Fly IoFly.io edge platform with global distribution. Use for edge deployment. Use when this capability is needed.
-
tomevault-io Bundle GolandGoLand Go IDE with debugging and testing. Use for Go development. Use when this capability is needed.
-
tomevault-io Bundle HerokuHeroku platform-as-a-service with buildpacks. Use for easy deployment. Use when this capability is needed.
-
tomevault-io Bundle HttpieHTTPie human-friendly HTTP client. Use for API testing. Use when this capability is needed.
-
tomevault-io Bundle LocustLocust load testing in Python. Use for load testing. Use when this capability is needed.
-
tomevault-io Bundle OllamaOllama local LLM deployment and management. Use for running LLMs locally. Use when this capability is needed.
-
tomevault-io Bundle PulumiPulumi infrastructure as code with programming languages. Use for IaC. Use when this capability is needed.
-
tomevault-io Bundle StrapiStrapi headless CMS with REST and GraphQL. Use for content APIs. Use when this capability is needed.
-
tomevault-io Bundle Gastownhall Gastown GastownGas Town + Cursor Agent CLI
-
tomevault-io Bundle Add ModelAdd a new language model to the Giselle codebase. Use when the user wants to add, register, or integrate a new LLM model (OpenAI, Anthropic, Google) into the system. Use when this capability is needed.
-
tomevault-io Bundle Sync DocsThis skill should be used when the user asks to "sync docs", "update guides", "check docs against official", "refresh documentation", "compare guides to official docs", "update docs from upstream", or mentions syncing the SDK documentation guides with the official Claude Agent SDK documentation. Use when this capability is needed.
-
tomevault-io Bundle Analystanalyst agent Use when this capability is needed.
-
tomevault-io Bundle Hkd987 Remix Browser BrowseUse the remix-browser MCP tools (prefixed `mcp__remix-browser__`) for all browser tasks.
-
tomevault-io Bundle Add Model DescriptionsAdd descriptions for new models from the HuggingFace router to chat-ui configuration, flag reasoning-capable ones, and enable artifacts for models with 32B+ parameters. Use when new models are released on the router and need descriptions added to prod.yaml and dev.yaml. Triggers on requests like "add new model descriptions", "update models from router", "sync models", or when explicitly invoking /add-model-descriptions. Use when this capability is needed.
-
tomevault-io Bundle Huggingface Kernels KernelsROCm Triton Kernels for Diffusers & Transformers
-
tomevault-io Bundle Generate Openenv EnvGenerate OpenEnv environments from a concrete use case (for example, "generate an env for the library textarena"). Use when asked to design or implement a new environment under envs/ by researching a target library/API, selecting matching OpenEnv examples, asking key implementation questions, and building models/client/server/openenv.yaml. Do not use for model training or evaluation tasks. Use when this capability is needed.
-
tomevault-io Bundle Example SkillExample fixture skill for action smoke tests Use when this capability is needed.
-
tomevault-io Bundle Rust GpuGPU 内存与计算专家。处理 CUDA, OpenCL, GPU memory, compute shader, memory coalescing, zero-copy, 显存管理, 异构计算---
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 cubox, blint, sync-skills-spec. 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.