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 Doc TemplateGenerate documentation templates for common document types. Outputs a ready-to-fill template with proper frontmatter and structure. Use when starting a new document. Use when this capability is needed.
- tomevault-io Bundle Copilot Config
Tune the GitHub Copilot AI — `copilot-instructions.md`, PR-review patterns, suggestion behavior, output verbosity. NOT for dev-environment setup (use `devcontainer`). Use when this capability is needed.
- tomevault-io Bundle Evilfreelancer Rpa Skills Rpa Gen Rules
RPA generate project rules (layered + BDD, multi-agent)
- tomevault-io Bundle Cost Auditor
Audit LLM usage, API costs, and resource optimization Use when this capability is needed.
- tomevault-io Bundle Finalrun Generate Test
Generate test and suite specifications in the strict FinalRun YAML format. Handles automated test planning, folder grouping by feature, repo app configuration, environment-specific overrides in .finalrun/env/*.yaml, and validation via finalrun check. Use when this capability is needed.
- tomevault-io Bundle Dude Specifications
Document specifications using the dude MCP server. List, create, update specifications. Record requirements, architecture decisions, API contracts, design patterns. Search for specs. Use when documenting requirements, recording architecture decisions, writing API specs, capturing design patterns, or managing technical documentation. Use when this capability is needed.
- tomevault-io Bundle Rust Gpu Discipline
Use this skill aggressively any time the work involves Rust code that touches GPU compute — including ferrotorch (and ferrotorch-* crates), burn, candle, wgpu-rs, cubecl, cudarc, or any project involving CUDA, ROCm, Metal, Vulkan, WGPU, cuBLAS, PTX, WGSL, or kernel dispatch. Trigger on any mention of `.cuda()`, `Device::Cuda(_)`, `.to_device()`, kernel launches, tensor ops, autograd backward passes, JIT codegen, or "GPU acceleration" in a Rust context. Also trigger when the user names a Rust GPU/ML project (ferrotorch, ferray, burn, candle) or asks to implement, port, optimize, or debug compute kernels. This skill exists because the model otherwise systematically defaults to CPU implementations, stubs out GPU code paths, and reports "done" while the work secretly executes on CPU. Use this skill to enforce pre-flight planning, the forbidden-pattern checklist, mechanical verification, and honest reporting so that GPU work actually lands on the GPU.
- tomevault-io Bundle Using Weaviate
Weaviate vector database for semantic search, hybrid queries, and AI-native applications. Use for embeddings storage, similarity search, RAG pipelines, and multi-modal retrieval. Use when this capability is needed.
- tomevault-io Bundle Persona Creation
Master the art of creating effective AI agent personas for Jules. Learn how to design role-specific prompts that guide Jules to execute tasks with precision, following best practices, and maintaining project standards. Use when creating new Jules personas or improving existing ones. Use when this capability is needed.
- tomevault-io Bundle Frootai Frootai Evaluate Voice AI Agent
Evaluate Voice AI Agent
- tomevault-io Bundle Manager Handoff
Standardizes the creation of "Source of Truth" Markdown briefs in .agent/temp for assigning tasks to Developer Agents. Use when this capability is needed.
- tomevault-io Bundle Visccyberacct N8n MCP Server N8n Setup
n8n Setup Skill
- tomevault-io Bundle Racecar LLM Summary
Generate a single-file Markdown knowledge package (`docs/$repo/$REPO.md`, ~400-800 lines) designed to be shared as one drag-and-drop file into Claude / Gemini / ChatGPT (mobile or desktop). A recipient using their own LLM can interview the system — ask what it is, how it works conceptually, what entities exist at the class level, what relationships connect them, what endpoints it exposes, why design choices were made, what's working, what's open — without needing source access or repo installation. YAML frontmatter carries the queryable spine (class-level entities, relationships DAG, endpoints by surface kind). Markdown body carries narrative (purpose, design decisions, intentional weirdness, flows, operational, configuration as bullets). Not a reconstruction-grade spec; not a CLAUDE.md replacement. Use when asked to "share a brief of this repo," "produce a knowledge package," "summarize for another LLM," or to noodle on refactors from mobile. Use when this capability is needed.
- tomevault-io Bundle Claude Oracle
Use when user asks "what exists for X?", before implementing custom MCP servers or plugins from scratch, or when browsing available tools — searches 19 sources and 15,000+ skills, plugins, and MCP servers in one query.
- tomevault-io Bundle Localize Strings
Run the build-add-in localization workflow when UI strings are added or changed, including extracting strings, generating translation prompts, updating TSV language files, embedding localized output, and validating results. Use when this capability is needed.
- tomevault-io Bundle Wgj Agent Plugins Codex Best Practices
Codex Best Practices
- tomevault-io Bundle Flutter Debug Cycle
Complete Flutter debugging toolkit combining PDCA methodology, Dart logging patterns, and MCP tools. Use when debugging Flutter apps - visual issues, runtime behavior, widget problems, or verifying fixes through device testing. Use when this capability is needed.
- tomevault-io Bundle Agents Guidelines
Defines the operational guidelines for the agent during this session. Use when this capability is needed.
- tomevault-io Bundle Salesforce Expert
Provides Salesforce platform expertise for Apex, LWC, Flow, and declarative development. The agent invokes this skill when working on Salesforce code, discussing platform constraints, or troubleshooting Salesforce-specific issues.
- tomevault-io Bundle Excalidraw Skill
Programmatic canvas toolkit for creating, editing, and refining Excalidraw diagrams via MCP tools with real-time canvas sync. Use when an agent needs to (1) draw or lay out diagrams on a live canvas, (2) iteratively refine diagrams using describe_scene and get_canvas_screenshot to see its own work, (3) export/import .excalidraw files or PNG/SVG images, (4) save/restore canvas snapshots, (5) convert Mermaid to Excalidraw, or (6) perform element-level CRUD, alignment, distribution, grouping, duplication, and locking. Requires a running canvas server (EXPRESS_SERVER_URL, default http://127.0.0.1:3000). Use when this capability is needed.
- tomevault-io Bundle Aptos MCP
Official Aptos MCP server for AI-assisted development on the Aptos blockchain. Provides tools for vibe coding with Aptos via Cursor and Claude Code, powered by Geomi. Use when this capability is needed.
- tomevault-io Bundle Maiat MCP
Maiat Trust Score MCP Server — query agent trust scores, token safety verdicts, and reputation data from Claude, GPT, Cursor, Codex, or any MCP-compatible AI tool. Use when this capability is needed.
- tomevault-io Bundle Sdd Requirements
Generate EARS-formatted requirements for SDD workflow. Use when starting a new feature specification, creating requirements documents, or defining acceptance criteria. Invoked via /sdd-requirements <feature-name>. Use when this capability is needed.
- tomevault-io Bundle Golden Dataset
Golden dataset lifecycle patterns for curation, versioning, quality validation, and CI integration. Use when building evaluation datasets, managing dataset versions, validating quality scores, or integrating golden tests into pipelines. Use when this capability is needed.
- tomevault-io Bundle Multimodal LLM
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling, Sora, Veo, Runway), or building multimodal AI pipelines. Use when this capability is needed.
- tomevault-io Bundle Clean Link Titles
Removes extraneous information (source, author, etc.) from link titles using LLM intelligence. Use when this capability is needed.
- tomevault-io Bundle Github Pr Workflow
Working with GitHub Pull Requests using the gh CLI. Use for fetching PR details, review comments, CI status, and understanding the difference between PR-level comments vs inline code review comments. Use when this capability is needed.
- tomevault-io Bundle Nature Paper To Patent
Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts. Use when an AI agent must extract patentable technical contributions, map every claimed feature to source evidence, preserve core formulas as editable Office Math, generate claim-aligned flowcharts and methodology figures, compare a paper with an existing patent, audit support and consistency, or deliver separate Chinese DOCX files for claims, specification, abstract, and abstract figure. Use when this capability is needed.
- tomevault-io Bundle Yysun Awesome Agent World AI Workspace
AI Workspace
- tomevault-io Bundle Zelk Oss Template Beginner Train Model
What this skill does
- tomevault-io Bundle Flutter Fix Layout Issues
Fixes Flutter layout errors (overflows, unbounded constraints) using Dart and Flutter MCP tools. Use when addressing "RenderFlex overflowed", "Vertical viewport was given unbounded height", or similar layout issues. Use when this capability is needed.
- tomevault-io Bundle Generate Agents
Generate agent definitions native to the target tool's runtime — Claude Code .claude/agents/*.md, Antigravity/Gemini agents with kind field, Hermes plugin-provided agents via register(ctx), Codex agent definitions, or Pi agent configs. Detects the active tool and emits the correct format. Invoked by scaffold or standalone via /generate-agents. Use when this capability is needed.
- tomevault-io Bundle Zrozoom Agent Skills Core Review Agent
Review Agent Skill
- tomevault-io Bundle Zycaskevin Vault For LLM Vault For LLM
Vault-for-LLM Project Memory
- tomevault-io Bundle 00bx 00bx Photoshop MCP Ps Tool Catalog
§3 COMPLETE TOOL CATALOG (323 Tools)
- tomevault-io Bundle Self Improving Agent
Use when working with a universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
Audited
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 doc-template, copilot-config, evilfreelancer--rpa-skills--rpa-gen-rules. 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.