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 Hosungyou Diverga G5⛔ Prerequisites (v8.2 — MCP Enforcement)
- tomevault-io Bundle Hosungyou Diverga G6
⛔ Prerequisites (v8.2 — MCP Enforcement)
- tomevault-io Bundle Hosungyou Diverga I0
⛔ Prerequisites (v8.2 — MCP Enforcement)
- tomevault-io Bundle Hosungyou Diverga I2
⛔ Prerequisites (v8.2 — MCP Enforcement)
- tomevault-io Bundle Progress Dashboard
Show AI design patterns project health, track completion status, coordinate agent activities, and suggest intelligent next priority actions Use when this capability is needed.
- tomevault-io Bundle Sweepi
Required orchestrater for linting using a dedicated sub-agent. Trigger when asked to run sweepi/linting + fixes, and before proposing commits. Use when this capability is needed.
- tomevault-io Bundle Plano Routing Model Selection
Optimize Plano model routing and selection. Use for provider defaults, model aliases, passthrough auth, and routing preference quality. Use when this capability is needed.
- tomevault-io Bundle Keadex Mina
Create, edit, and manage C4 Model architecture diagrams in Keadex Mina projects using the Mina MCP server tools. Use when working with C4 diagrams, PlantUML-based architecture documentation, or Keadex Mina projects. Use when this capability is needed.
- tomevault-io Bundle Keenthemes Ktui Ktui
KTDataTable — AI Agent Reference
- tomevault-io Bundle Idx Md
AgentSkill for https://idx.md. Use the index to locate AI agent library topics and fetch HEAD/BODY markdown. Use when this capability is needed.
- tomevault-io Bundle Remix
Use this skill for end-to-end Remix app work. It should help the agent choose
- tomevault-io Bundle Kerlos Pordee Pordee
This skill is delivered by `hooks/pordee-stats.js` (read by `hooks/pordee-mode-tracker.js` on `/pordee-stats`). The model does not need to do anything when this skill fires — the hook returns `decision: "block"` with the formatted stats as the reason. The user sees the numbers immediately.
- tomevault-io Bundle Ntk
基于信息密度路由的多智能体框架，MCP 协议接入，自适应任务复杂度 Use when this capability is needed.
- tomevault-io Bundle Litllm
Generate a related-work section, find prior literature, or rank candidate citations for an academic paper. Uses LLM-driven debate ranking over Semantic Scholar / arXiv / OpenAlex search, with optional citation-graph BFS expansion (deep research). Use when the user provides a paper (PDF or markdown) and asks for related work, citations, prior art, or a literature review. Use when this capability is needed.
- tomevault-io Bundle Vx Usage
Teaches AI agents how to use vx, the universal dev tool manager. Use when the project has vx.toml or .vx/, or when the user mentions vx, tool version management, Git/GitHub operations, or cross-platform setup. vx auto-manages Node.js, Python, Go, Rust, and 142 providers via Starlark DSL provider.star files. Also covers MCP integration patterns and GitHub Actions. Use when this capability is needed.
- tomevault-io Bundle Ingest Codebase
Guide the creation of a high-quality mental model for a codebase. Use when starting a new mental model, when the model feels incomplete or unclear, or when onboarding to understand a system's architecture. Produces domains, capabilities, aspects, and architectural decisions. Use when this capability is needed.
- tomevault-io Bundle Eval
Plan and run conversational AI agent evaluations with test generation and analysis. Use when this capability is needed.
- tomevault-io Bundle LLM
Large Language Model development, training, fine-tuning, and deployment best practices. Use when this capability is needed.
- tomevault-io Bundle Pkfire
Author and maintain `Taskfile.pkl` files for the `pkf` task runner. Use when adding, editing, or troubleshooting tasks in a project that has `pkf` installed (or is choosing it over `just` / `Taskfile.yml`). Covers the Pkl schema, the typed `deps` model, cache semantics (action key, local CAS, remote HTTP backend, symlink support), watch mode, and the common pitfalls. Recipes under `assets/recipes/` are copy-paste starting points for the patterns this skill describes. Use when this capability is needed.
- tomevault-io Bundle Instrumenting With Mlflow Tracing
Instruments Python and TypeScript code with MLflow Tracing for observability. Must be loaded when setting up tracing as part of any workflow including agent evaluation. Triggers on adding tracing, instrumenting agents/LLM apps, getting started with MLflow tracing, tracing specific frameworks (LangGraph, LangChain, OpenAI, Gemini, DSPy, CrewAI, AutoGen), or when another skill references tracing setup. Examples - "How do I add tracing?", "Instrument my agent", "Trace my LangChain app", "Set up tracing for evaluation Use when this capability is needed.
- tomevault-io Bundle Actix Web Framework
High-performance Rust web framework with actor model foundation. Use when this capability is needed.
- tomevault-io Bundle AI Artist
Craft prompts for AI models (text, image, video). Use for Midjourney, DALL-E, Stable Diffusion, Flux, Veo, prompt engineering, style keywords, negative prompts, iterative refinement. Use when this capability is needed.
- tomevault-io Bundle Aictx
Use this skill when working in a repository that uses AICTX for repo-local operational continuity. Prefer AICTX MCP tools when available, fall back to CLI commands, resume before substantial work, and finalize factual continuity after work.
- tomevault-io Skill Bagman
Secure key management for AI agents. Use when handling private keys, API secrets, wallet credentials, or when building systems that need agent-controlled funds. Covers secure storage, session keys, leak prevention, prompt injection defense, and MetaMask Delegation Framework integration. Use when this capability is needed.
Audited - tomevault-io Bundle Karpathy Guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria. Use when this capability is needed.
- tomevault-io Bundle Patriksimek Vm2 Hacker
Hacker - vm2 Sandbox Red Team Agent
- tomevault-io Bundle Paulkinlan Co Do Co Do
Silent Failure Hunter Agent
- tomevault-io Bundle Gimp
Automate GIMP image editing via Python-Fu scripting, CLI batch processing, and MCP integration Use when this capability is needed.
- tomevault-io Bundle Talk
Start a voice conversation using the Pipecat MCP server Use when this capability is needed.
- tomevault-io Bundle Evla Vla
EdgeVLA - Open-source edge vision-language-action model for robotics. Standardizes Open-X Embodiment datasets for consistent VLA training and deployment. Use when this capability is needed.
- tomevault-io Bundle Flox MCP
MCP server wrapper for flox CLI operations - environment management via JSON-RPC Use when this capability is needed.
- tomevault-io Bundle Ruska AI Orchestra Rlm
Recursive Language Model (RLM)
- tomevault-io Bundle Text To Speech
Convert text to natural speech using Sarvam AI's Bulbul v3 model. Handles audio generation, voiceovers, and voice interfaces for 11 Indian languages with 30+ voices. Supports REST, HTTP streaming, WebSocket, and pronunciation dictionaries. Use when generating spoken audio from text. Use when this capability is needed.
- tomevault-io Bundle Erc8128
Sign and verify HTTP requests with Ethereum wallets using ERC-8128. Use when building authenticated APIs that need wallet-based auth, making signed requests to ERC-8128 endpoints, implementing request verification in servers, or working with agent-to-server authentication. Covers both the @slicekit/erc8128 JS library and the erc8128 CLI. Use when this capability is needed.
- tomevault-io Bundle Ghost
Create a language-agnostic ghost package (spec + portable tests) from an existing repo by extracting SPEC.md, exhaustive tests.yaml (operations and/or scenarios), INSTALL.md, README.md, VERIFY.md, and upstream LICENSE files with provenance and regeneration instructions. Use when prompts say "$ghost", "ghostify this repo", "spec-ify/spec-package this library", "ghost library", or ask to extract portable spec/tests for libraries or tool-using agent loops (scenario testing); do not use for implementation work or editing skills. Use when this capability is needed.
- tomevault-io Bundle Repoprompt Tool Guidance Refresh
Update RepoPrompt tool guidance based on MCP/CLI changes across versions. Two-phase workflow - invoke BEFORE upgrading (--pre), then AFTER upgrading (--post). Uses `~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh` to detect and diff changes (outputs to `~/.pi/agent/skills/repoprompt-tool-guidance-refresh/rp-tool-defs/`). 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 hosungyou--diverga--g5, hosungyou--diverga--g6, hosungyou--diverga--i0. 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.