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 CodesessionTrack AI agent session costs, tokens, file changes, and git commits. Use when starting tasks, logging AI usage, checking budgets, or ending sessions. The MCP server handles all operations automatically. Use when this capability is needed.
- tomevault-io Bundle Project Careti
Guidelines for testing LLM API providers when adding or modifying support in Caret. Use when this capability is needed.
- tomevault-io Bundle Claude Md Init
Generate a CLAUDE.md project file that orients Claude Code to the repo's structure, commands, and constraints. Use when this capability is needed.
- tomevault-io Bundle Cds Yiwei Agent Skills JS To TS Migration
JavaScript to TypeScript Migration
- tomevault-io Bundle Local LLM Deployment
Ollama, llama.cpp, and local LLM deployment for privacy and cost optimization. Use when this capability is needed.
- tomevault-io Bundle Parallel Subagents
Coordinate independent teammates concurrently in Agent Teams for 50-70% speedup. Launch multiple teammates simultaneously. Use when this capability is needed.
- tomevault-io Bundle Modify Stations
Guide for finding and modifying stations in The Years Between the Stars — docking rules, station placement, station rendering, and station interaction flow (landing, docked UI, undocking). Use this skill whenever the user wants to change docking radius/speed, docking behavior, where stations appear, station visuals, or station interaction flow. Trigger on "station", "dock", "docking", "undock", "dock radius", "landing at station", "station placement", "station model". Use when this capability is needed.
- tomevault-io Bundle Screenshot Testing
This skill should be used when the user asks to "test UI with screenshots", "screenshot testing", "visual testing", "compare UI screenshots", "verify UI layout", "take screenshot for testing", or when using screenshot MCP tools (list_windows, list_displays, screenshot_window, screenshot_screen, screenshot_region) for testing purposes. Provides guidance on effective screenshot-based UI testing workflows. Use when this capability is needed.
- tomevault-io Bundle Problem Definition
Guide RCCA/8D problem definition using 5W2H and IS/IS NOT analysis. Transforms scattered failure data into precise, measurable problem statements that bound investigation scope without embedding cause or solution. Use when defining problems for root cause analysis, writing D2 sections of 8D reports, analyzing nonconformances, investigating failures, or when user mentions problem definition, problem statement, RCCA, 8D, failure analysis, or corrective action. Use when this capability is needed.
- tomevault-io Bundle God Mode
Developer oversight and AI agent coaching. Use when viewing project status across repos, syncing GitHub data, or analyzing agents.md against commit patterns. Use when this capability is needed.
- tomevault-io Bundle Uid Life
Interact with the UID.LIFE agent-to-agent marketplace - register agents, discover workers, send proposals, manage contracts, and transact in $SOUL currency. Use when this capability is needed.
- tomevault-io Bundle Descoped LLM Skills Github Issues Workflow
GitHub Issues Workflow
- tomevault-io Bundle Dice Group Dice Embeddings Dice Embeddings
Use a Pre-Trained KGE Model for Inference
- tomevault-io Bundle Youtube Rl Tracker
Track YouTube video performance for "poor man's reinforcement learning" - learn what thumbnails, titles, and hooks work Use when this capability is needed.
- tomevault-io Bundle Edit Claude
Creates, updates, or optimizes CLAUDE.md files following Anthropic best practices. Use when user requests creating, updating, improving, or optimizing CLAUDE.md files for project context, coding standards, or persistent memory.
- tomevault-io Bundle Digital Stoic Org Agent Skills Edit Plugin
Edit Plugin
- tomevault-io Bundle Digital Stoic Org Agent Skills Investigate
Investigate
- tomevault-io Bundle Cc Devflow Orchestrator
CC-DevFlow workflow router and agent recommender. Use when starting requirements, running flow commands, or asking about devflow processes. Use when this capability is needed.
- tomevault-io Bundle Dmitriyyukhanov Claude Plugins Agent Teams
Agent Teams
- tomevault-io Bundle Ralph Multimodel
Ralph Wiggum persistence loop with intelligent multi-model routing (Gemini, Codex, Claude, Council) Use when this capability is needed.
- tomevault-io Bundle Chaos Engineering And Resilience Testing
Use when working with the agent implements chaos engineering practices for building resilient systems. Use when testing fault tolerance, designing game days, or validating system recovery.
- tomevault-io Bundle Add Validation
Triggered when user asks to implement data validation, create validation schemas, add input validation, or ensure type-safe validation. Automatically delegates to the validation-specialist agent. Use when this capability is needed.
- tomevault-io Bundle Cursor Genius
Answers questions about the Cursor product using official Cursor documentation first. Covers Agent, modes, rules, skills, subagents, MCP, CLI, models, pricing, account, billing, enterprise, integrations, and troubleshooting. Use when the user asks how Cursor works, how to configure a Cursor feature, where Cursor documents something, or how two Cursor features differ. Avoid for generic code references to "cursor" that are unrelated to the Cursor product. Use when this capability is needed.
- tomevault-io Bundle Droodotfoo Agent Skills MCP Server Builder
MCP Server Builder
- tomevault-io Bundle Shap Explainer
Explain machine learning model predictions using SHAP (SHapley Additive exPlanations). Use when this capability is needed.
- tomevault-io Bundle Dungle Scrubs Agent Config Image As Design
Image-as-Design: UI Implementation from Images
- tomevault-io Bundle Dungle Scrubs Agent Config Swift Standards
Swift Best Practices
- tomevault-io Bundle Eduardo Sl Go Agent Skills Go Agent Skills
Go Architecture Review
- tomevault-io Bundle Migrate From Openai App
This skill should be used when the user asks to "migrate from OpenAI Apps SDK", "convert OpenAI App to MCP", "port from window.openai", "migrate from skybridge", "convert openai/outputTemplate", or needs guidance on converting OpenAI Apps SDK applications to MCP Apps SDK. Provides step-by-step migration guidance with API mapping tables. Use when this capability is needed.
- tomevault-io Bundle Elliotjlt Claude Skill Potions Agent Audit
Agent Audit
- tomevault-io Bundle Software Tool Research
Expert system for analyzing software tools and repositories (especially GitHub). Understands architecture, generates architectural models, produces detailed reports, and measures quality metrics. Use when investigating code structure, dependencies, design patterns, testing strategies, or generating comprehensive tool documentation. Use when this capability is needed.
- tomevault-io Bundle Doc Frontmatter
Add or fix YAML frontmatter for documentation files. Adds missing required fields or fixes invalid frontmatter. Use for bulk fixing or when validation fails. Use when this capability is needed.
- tomevault-io Bundle Fabioc Aloha Windowswidget AI Agent Design
AI Agent Design Skill
- tomevault-io Bundle Fabioc Aloha Windowswidget MCP Development
MCP Development Skill
- tomevault-io Bundle Compaction Strategies
Implement hook-based history compaction in fast-agent (rolling window, context threshold truncation, tool-result clearing, summary prompt compaction). Use when adding or extending compaction hooks and wiring them into agent cards. Use when this capability is needed.
- tomevault-io Bundle Shared Worktree
Git worktree setup and management for parallel agent development. Use when working in isolated git worktrees to avoid merge conflicts between Developer and Tech Artist agents. 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 codesession, project-careti, claude-md-init. 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.