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 Databricks DocsDatabricks documentation reference. Use as a lookup resource alongside other skills and MCP tools for comprehensive guidance. Use when this capability is needed.
- tomevault-io Bundle Nanogpt
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU). Use when this capability is needed.
- tomevault-io Bundle Gemini CLI Extension Porting
Use when porting beads or superpowers workflows into Gemini CLI extensions or designing Gemini CLI command prompts that emulate multi-step agent workflows - covers extension layout, GEMINI.md context, command TOML patterns, and enforceable guardrails (tests/CI/pre-commit)
- tomevault-io Bundle AI Agent Card Payments
Virtual card payments for AI agents. Create intents, issue cards within policy, and make autonomous purchases with approvals for high-value spend. Use when this capability is needed.
- tomevault-io Bundle Didit Protocol Didit Agent Skills Didit Proof Of Address
Didit Proof of Address API
- tomevault-io Bundle AI Agent Development V2
AI Agent Development Workflow workflow skill. Use this skill when the user needs AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off. Use when this capability is needed.
- tomevault-io Bundle Backend Ralph Plan
Create a structured plan directory with Ralph Wiggum Loop integration for backend Django projects (PLAN.md, task files, and RALPH-PROMPT.md). Use when this capability is needed.
- tomevault-io Bundle Docs Workflow Create Mr
Create or find an existing merge request (GitLab) or pull request (GitHub) for the published documentation branch. Skipped in draft mode or when the branch was not pushed. Use when this capability is needed.
- tomevault-io Bundle MCP Management Workflow
Complete development workflow for MCP Management System v2.1 including Phase 0 cognitive analysis, MCP service selection and testing, template modification procedures, and deployment protocols. Use when working on MCP Management System development tasks. Use when this capability is needed.
- tomevault-io Bundle Ecos Performance Tracking
Use when tracking team performance, analyzing agent strengths and weaknesses, collecting metrics, and generating performance reports. Trigger with performance review or metrics requests.
- tomevault-io Bundle Eoa Kanban Management
GitHub Projects V2 kanban board management. Use when creating boards, adding columns, moving items. Trigger with kanban or column requests. Use when this capability is needed.
- tomevault-io Bundle Eoa Task Distribution
Task distribution based on skills and availability. Use when assigning work to agents, balancing load, or resolving dependencies. Trigger with assignment requests. Use when this capability is needed.
- tomevault-io Bundle Deepagents Skills
在 Deep Agents 中创建和使用自定义技能，实现渐进式披露、SKILL.md 格式和 Agent Skills 协议。 Use when this capability is needed.
- tomevault-io Bundle Pm Improvement Skill Research
MCP-based skill improvement during retrospective - research and update agent skills Use when this capability is needed.
Audited - tomevault-io Bundle Frankx Daily Execution System
Helps execute Frank's daily workflow using the FRANKX-SUPERINTELLIGENT-AGENT-SYSTEM, Starlight Intelligence, and productivity methodologies for conscious creation Use when this capability is needed.
- tomevault-io Bundle Gabrielmoreira Agent Skills Mirror Flutter Testing Skill
Flutter Testing Skill
- tomevault-io Bundle Multi Agent Red Team Planning
Plan the next steps for the repository, then run a structured multi-agent red-team on the plan, refine twice, and produce a final implementation plan. Use when this capability is needed.
- tomevault-io Bundle Acreadiness Generate Instructions
Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar. Use when this capability is needed.
- tomevault-io Bundle Developing AI Agents
AI Agent Development with LangChain and LangGraph Use when this capability is needed.
- tomevault-io Bundle Dialectic Review
Dialectic process for reviewing, brainstorming, comparing tradeoffs, or stress-testing plans. Configurable modes, agent counts, and expert lenses. Use when this capability is needed.
- tomevault-io Bundle Disabled Skill
Use when working with a skill with model invocation disabled
- tomevault-io Bundle Gxinlong Cuda Optimization Skill Cuda Optimization Skill
Kernel Benchmark
- tomevault-io Bundle Browser Devtools MCP
Integrating Chrome DevTools and browser automation via MCP for live UI inspection, screenshot-to-code workflows, and visual debugging. Bridges the gap between design and implementation. Use when this capability is needed.
- tomevault-io Bundle Hoangnguyen0403 Agent Skills Standard Android Navigation
Android Navigation (Jetpack Compose)
- tomevault-io Bundle Hoangnguyen0403 Agent Skills Standard Typescript Tooling
TypeScript Tooling
- tomevault-io Bundle Notebooklm Infographic
Use when creating professional infographics automatically using NotebookLM MCP, generating visual content from research topics with automated web search, data structuring, and browser automation for visualization
- tomevault-io Bundle Gemini Runner Audit
Use isolated Gemini CLI audit via local MCP tool (`gemini_audit`) for context-safe code/security/doc analysis with optional session resume. Use when this capability is needed.
- tomevault-io Bundle Quotation Generator
Auto-generate professional PDF proforma invoices with company letterhead, multi-language support, and post-quote tracking. Use when this capability is needed.
- tomevault-io Bundle Note To Video Transcript
Transform study notes (Markdown or PDF) into a ready-to-record video transcript (5-8 minutes) with spoken language, natural pacing, and structured sections. Use when this capability is needed.
- tomevault-io Bundle Chrome Devtools MCP Singleton
Run and manage a single-instance Chrome DevTools MCP server on this machine, including start/stop/status/dedupe workflows and safe cleanup to prevent multiple chrome-devtools-mcp processes from running concurrently. Use when you need a singleton MCP server for Chrome DevTools or when EMFILE/process-spawn issues require enforcing exactly one chrome-devtools-mcp instance. Use when this capability is needed.
- tomevault-io Bundle Advanced Skill Builder
Guides users through creating production-ready Claude skills via interactive dialogue. Use when user wants to build a new skill, needs help structuring a skill, or asks "how do I create a skill?" Covers requirements gathering, planning, YAML frontmatter generation, instruction writing, testing, and iterative refinement. Works with or without MCP integration. Use when this capability is needed.
- tomevault-io Bundle Josiahsiegel Claude Plugin Marketplace Agent Development
Agent Development for Claude Code Plugins
- tomevault-io Bundle Starknet Identity
Register AI agents on-chain using the ERC-8004 Trustless Agents standard. Manage agent identity as NFTs, build reputation through feedback, and request third-party validation. Use when this capability is needed.
- tomevault-io Bundle Documentation API Reference
Author API reference documentation that is accurate, complete, and implementation-aligned for client developers. Use when API docs are primary deliverables or must be updated for contract changes; do not use for implementing new product behavior. Use when this capability is needed.
- tomevault-io Bundle Fastapi Service Development
FastAPI service development workflow for production-grade Python APIs. Use when FastAPI service behavior (path operations, dependency injection, request/response models, validation, async execution, OpenAPI exposure) must be implemented or revised; do not use for repository-wide architecture governance or release management policy. Use when this capability is needed.
- tomevault-io Bundle Security Secrets Management
Security workflow for secret inventory, storage, distribution, rotation, and auditability controls. Use when API keys, credentials, certificates, or signing secrets lifecycle decisions are required; do not use for generic config management that excludes sensitive material. 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 databricks-docs, nanogpt, gemini-cli-extension-porting. 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.