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 Ashendulsanka Agent Arche Coding Standards---
- tomevault-io Bundle Migrating Airflow 2 To 3
Guide for migrating Apache Airflow 2.x projects to Airflow 3.x. Use when the user mentions Airflow 3 migration, upgrade, compatibility issues, breaking changes, or wants to modernize their Airflow codebase. If you detect Airflow 2.x code that needs migration, prompt the user and ask if they want you to help upgrade. Always load this skill as the first step for any migration-related request. Use when this capability is needed.
- tomevault-io Bundle Security Design V1
Generate comprehensive security design documents from domain models and use case specifications with multi-language support (Japanese/English/Bilingual). Defines authentication, authorization, data protection, API security, OWASP Top 10 countermeasures, role-permission matrices, and audit logging. Produces structured security-config.json for downstream code generation. Inherits language settings for document generation. Use after model-validator-v1 and before usecase-to-code-v1. Use when this capability is needed.
- tomevault-io Bundle Promptstart
Démarre un développement avec un starter léger puis active le mode plan Use when this capability is needed.
- tomevault-io Bundle Mental Model
Maintains a living mental model of the codebase. Read mental-model.md before making changes, update it when discovering new patterns or behaviors. Use when this capability is needed.
- tomevault-io Bundle Documenting Architecture
Document project architecture, tech stack, and data flow. Use when setting up or updating architecture documentation. Use when this capability is needed.
- tomevault-io Bundle Pic Audit
View detailed audit log for workflow - shows agent executions, tool usage, and decision trail Use when this capability is needed.
- tomevault-io Bundle Bankr Agent Job Workflow
This skill should be used when executing Bankr requests, submitting prompts to Bankr API, polling for job status, checking job progress, using Bankr MCP tools, or understanding the submit-poll-complete workflow pattern. Provides the core asynchronous job pattern for all Bankr API operations. Use when this capability is needed.
- tomevault-io Bundle Teach Workflow
Run guided teach-mode scans, dives, and local insight logging. Use when this capability is needed.
- tomevault-io Bundle Rspec Rails
This skill should be used when the user asks about "request specs", "system specs", "model specs", "controller specs", "mailer specs", "feature specs", "Capybara", "rspec-rails", or needs guidance on testing Rails applications with RSpec. Use when this capability is needed.
- tomevault-io Bundle Playwright LLM
Browser automation using Playwright for web navigation, content extraction, and interaction. Use when you need to browse websites, scrape content, or interact with web pages. Use when this capability is needed.
- tomevault-io Bundle Padic Ultrametric Embedding
P-adic ultrametric distance for UMAP/itUMAP/HNSW with Snowflake Arctic Use when this capability is needed.
- tomevault-io Bundle Polynomial Social Cognition
Social cognition via polynomial functors - "Agent" IS a polynomial p(y) = Σᵢy^{Aᵢ} with positions (observations) and directions (actions). Integrates Spivak/Niu Poly, Feigenbaum bifurcation, Mode 1/Mode 2, and GF(3) grading. Use when this capability is needed.
- tomevault-io Bundle Model Debugging
Debug and diagnose model errors in Pollinations services. Analyze logs, find error patterns, identify affected users. For taking action on user tiers, see tier-management skill. Use when this capability is needed.
- tomevault-io Bundle Tier Management
Evaluate and update Pollinations user tiers. Check balances, upgrade devs, batch process users. For finding users with errors, see model-debugging skill first. Use when this capability is needed.
- tomevault-io Bundle Wrap Session
End-of-session documentation workflow that updates README, CHANGELOG, agent context files, and creates session logs. Use when wrapping up a working session, when asked to document session progress, when preparing handoff documentation, or when the user says "wrap up", "end session", "document progress", or "save session". Use when this capability is needed.
- tomevault-io Bundle Pulumi Automation API
Load this skill when a user asks how to run Pulumi programmatically, embed Pulumi in an application, orchestrate multiple stacks in code, build a self-service infrastructure portal, replace pulumi CLI shell scripts with code, or use the Pulumi Automation API (LocalWorkspace, createOrSelectStack, inline programs). Also load for questions about multi-stack sequencing, parallel deployments, or passing outputs between stacks via code. Use when this capability is needed.
- tomevault-io Bundle Pulumi Best Practices
Load when the user is writing, reviewing, or debugging Pulumi TypeScript/Python programs; asks about Output<T> or apply() usage; wants to create ComponentResource classes; needs to refactor resources without destroying them (aliases); is setting up secrets or config; or is configuring a pulumi preview/up CI workflow. Also load for questions about resource dependency order, parent/child resource relationships, or pulumi.interpolate. Use when this capability is needed.
- tomevault-io Bundle Tick Coordination
Coordinate multi-agent work using the Tick protocol via CLI commands or MCP tools. Use when managing tasks, coordinating with other agents, tracking project progress, or when the user mentions tasks, coordination, agents, or project management. Enables natural conversation about work while maintaining structured task tracking. Use when this capability is needed.
- tomevault-io Bundle Add Voice Transcription
Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them. Use when this capability is needed.
- tomevault-io Bundle Create MCP
Add a new MCP server to all AI tool configs. Use when user says "add MCP server", "new MCP server", "create MCP", "add tool to MCP", or wants to register a new MCP server across Claude Code, Codex, Cursor, and OpenCode. Use when this capability is needed.
- tomevault-io Bundle Building With Llms
Help users build effective AI applications. Use when someone is building with LLMs, writing prompts, designing AI features, implementing RAG, creating agents, running evals, or trying to improve AI output quality. Use when this capability is needed.
- tomevault-io Bundle Verify MCP
Verifies the MCP server functionality by running the integration test suite. Use when this capability is needed.
- tomevault-io Bundle Rituals Guide
Audit and scaffold sprint documentation rituals based on MANIFESTO.md. Use when the user wants to follow the research -> spec -> prompt -> implement -> document workflow, generate checklists/templates, or evaluate documentation quality for a sprint. Use when this capability is needed.
- tomevault-io Bundle Activerecord Patterns
ActiveRecord model patterns and best practices for kw-app - validations, associations, scopes, queries, and when to keep models thin. Use when this capability is needed.
- tomevault-io Bundle Boundary Validator
Validates code changes against safe-formdata's boundary-focused design principles. Detects violations of "keys are opaque", "no silent behavior", "no inference", and "explicit issue reporting". Use when reviewing PRs, implementing features, or checking adherence to design rules.
- tomevault-io Bundle Rubakas Agent Notes Rails View Components
ViewComponent
- tomevault-io Bundle Agent Agentic Payments
Agent skill for agentic-payments - invoke with $agent-agentic-payments Use when this capability is needed.
- tomevault-io Bundle Agent Docs API Openapi
Agent skill for docs-api-openapi - invoke with $agent-docs-api-openapi Use when this capability is needed.
- tomevault-io Bundle Agent Matrix Optimizer
Agent skill for matrix-optimizer - invoke with $agent-matrix-optimizer Use when this capability is needed.
- tomevault-io Bundle Agent Mesh Coordinator
Agent skill for mesh-coordinator - invoke with $agent-mesh-coordinator Use when this capability is needed.
- tomevault-io Bundle Agent Multi Repo Swarm
Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm Use when this capability is needed.
- tomevault-io Bundle Agent Security Manager
Agent skill for security-manager - invoke with $agent-security-manager Use when this capability is needed.
- tomevault-io Bundle Agent Sync Coordinator
Agent skill for sync-coordinator - invoke with $agent-sync-coordinator Use when this capability is needed.
- tomevault-io Bundle Agent Test Long Runner
Agent skill for test-long-runner - invoke with $agent-test-long-runner Use when this capability is needed.
- tomevault-io Bundle Apple Silicon
Apple Silicon optimization for VMs, ML inference, and compression. Covers Metal GPU acceleration, MLX model inference, CoreML conversion, M-series zstd compression, Apple Virtualization Framework, and performance tuning. 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 ashendulsanka--agent-arche--coding-standards, migrating-airflow-2-to-3, security-design-v1. 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.