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 Training OptimizationAdvanced techniques for optimizing LLM fine-tuning. Covers learning rates, LoRA configuration, batch sizes, gradient strategies, hyperparameter tuning, and monitoring. Use when fine-tuning models for best performance. Use when this capability is needed.
- tomevault-io Bundle Scraperapi Scraperapi Skills Scraperapi Agent Onboarding
ScraperAPI — Agent Onboarding
- tomevault-io Bundle Non Blocking Execution
Guidelines for running long-lived processes (servers, watchers) without blocking agent execution. Use when this capability is needed.
- tomevault-io Bundle M365 Agent Developer
Designs, implements, and deploys Microsoft 365 Copilot agents using TypeSpec and ATK CLI. Provides architectural guidance, capability configuration, security patterns, and lifecycle management. Use when developing M365 Copilot agents, working with TypeSpec, or managing agent deployments. For creating new projects, use the m365-agent-scaffolder skill. Use when this capability is needed.
- tomevault-io Bundle Commit Message Guide
编写清晰、规范的 Git 提交信息，遵循 Conventional Commits 规范 Use when this capability is needed.
- tomevault-io Bundle Futu Stock
Access Futu stock market data via MCP server - real-time quotes, K-lines, options, account info for HK/US/CN markets Use when this capability is needed.
- tomevault-io Bundle Slowmist Agent Security
Comprehensive security review framework for AI agents. Covers skill/MCP installation, GitHub repos, URLs/documents, on-chain addresses, products/services, and social shares. Built from real-world attack patterns and incident response experience. Use when this capability is needed.
- tomevault-io Bundle Cedar
Authors, validates, and tests Cedar authorization policies and schemas for Sondera AI agent governance. Use when writing .cedar or .cedarschema files, working with agent guardrails, YARA signatures, sensitivity labels, or information flow control policies. Use when this capability is needed.
- tomevault-io Bundle Building Streamlit Multipage Apps
Building multi-page Streamlit apps. Use when creating apps with multiple pages, setting up navigation, or managing state across pages. Use when this capability is needed.
- tomevault-io Bundle Connecting Streamlit To Snowflake
Connecting Streamlit apps to Snowflake. Use when setting up database connections, managing secrets, or querying Snowflake from a Streamlit app. Use when this capability is needed.
- tomevault-io Bundle Agent Repo Init
One-click initialization of a multi-agent repository from the Antigravity template. Use this skill when users want to scaffold a new project quickly (`quick` mode) or with runtime defaults (`full` mode) including LLM provider profile, MCP toggle, swarm preference context, sandbox type, and optional git init. Use when this capability is needed.
- tomevault-io Bundle Personal Writing Style
Personal writing style preferences. Reference this skill when writing, translating, or editing content to ensure consistent style, punctuation, and formatting. Use when this capability is needed.
- tomevault-io Bundle Sun Lab Nbb Ataraxis Communication MCP Environment Setup
MCP environment setup
- tomevault-io Bundle MCP Builder Compiler Debugger
Build, test, and debug MCP (Model Context Protocol) servers using FastMCP. Use when creating MCP servers, testing endpoints, debugging connection issues, integrating with Claude Desktop, or working with MCP Inspector. Covers project setup, tool implementation patterns, error handling, testing workflows, and debugging techniques. Use when this capability is needed.
- tomevault-io Bundle Syntaxasspiral Zk Context Vault Multi Agent Coordination
---
- tomevault-io Bundle Takemi Ohama AI Agent Marketplace Corder Test Generation
Corder Test Generation Skill
- tomevault-io Bundle Aider Cache Default On
Aider's --cache-prompts is off by default. Flip it on for supported models. Use when this capability is needed.
- tomevault-io Bundle Gabrielmoreira Agent Skills Mirror Debugging Local Replay
Debugging local session replay
- tomevault-io Bundle Gabrielmoreira Agent Skills Mirror Openapi Spec Generator
OpenAPI / Swagger Specification Generator
- tomevault-io Bundle Ingesting RAG Content
Specialized skill for ingesting rag content Use when this capability is needed.
- tomevault-io Bundle AI Agent Guardrails
Apply safety controls when an LLM agent has authority to act on real systems. Covers blast-radius classification, dry-run-first patterns, out-of-band approval gates, scope locking, idempotency, kill switches, and rollback strategies. Invoke when designing an autonomous agent, when granting an LLM write access to production, or after an agent makes an unexpected change. Use when this capability is needed.
- tomevault-io Bundle Grey Haven Ontological Documentation
Create comprehensive ontological documentation for Grey Haven systems - extract domain concepts from TanStack Start and FastAPI codebases, model semantic relationships, generate visual representations of system architecture, and document business domains. Use when onboarding, documenting architecture, or analyzing legacy systems. Use when this capability is needed.
- tomevault-io Bundle Flutter Template Agent Guide
Complete project-specific guide for developing the LanRhyme Flutter template. Use when adding or refactoring features, changing routing/navigation, improving desktop or mobile UX, updating theme/settings/data/cache/network layers, creating tests, building releases, merging branches, or reviewing implementation quality in this Flutter template repository. Use when this capability is needed.
- tomevault-io Bundle Value Design Drawio Generator
価値デザインモデルのDrawIO形式のファイルを作成する。 Use when this capability is needed.
- tomevault-io Bundle Hassanzohdy Agent Kit Mongez Agent Kit Agent Integrations
Agent integrations
- tomevault-io Bundle Premiere Pro MCP
Install, verify, troubleshoot, and operate the Adobe Premiere Pro MCP server. Use when a user wants an agent to set up Premiere MCP, connect Claude Code/Codex/Claude Desktop, control Premiere, import media, build sequences, edit timelines, apply effects, or diagnose bridge issues. Use when this capability is needed.
- tomevault-io Bundle Hoangnguyen0403 Agent Skills Standard Typescript Security
TypeScript Security
- tomevault-io Bundle I3ringit Antigravity Cortex Deployment Verification Agent
You are a Deployment Verification Agent. Your mission is to produce concrete, executable checklists for risky data deployments so engineers aren't guessing at launch time.
- tomevault-io Bundle Parallel Agent Dispatch
Use when facing 2+ independent tasks that can be worked on without shared state. Dispatch one agent per problem domain for concurrent investigation.
- tomevault-io Bundle Hierarchy Tree
Construct ASCII tree visualizations from parent/child work item data. Use when the user asks to "show hierarchy", "show tree", "display parent child", "visualize structure", "show feature tree", or wants to see work item relationships as a tree diagram. This skill teaches how to build trees from flat data WITHOUT code - use LLM reasoning only. Use when this capability is needed.
- tomevault-io Bundle Spark Optimization
Specialist in Apache Spark performance optimization—partitioning strategies, memory tuning, shuffle reduction, and job profiling for production systems. Use when optimizing Spark jobs, tuning performance, reducing costs, profiling applications, or scaling Spark workloads. Use when this capability is needed.
- tomevault-io Bundle Tsh Migrating Copilot To Cursor
Convert GitHub Copilot customization artifacts (agents, skills, prompts, instructions) to their Cursor AI IDE equivalents (SKILL.md files, .mdc rules). Use when porting a PR or branch from a Copilot-based repo to this Cursor setup, adding a new Copilot-originated agent or skill, or verifying that a converted artifact follows the correct Cursor structure. Use when this capability is needed.
- tomevault-io Bundle Langcare Langcare MCP Fhir Critical Value Alert Generator
Critical Value Alert Generator
- tomevault-io Bundle Langcare Langcare MCP Fhir History And Physical Generator
History and Physical Generator
- tomevault-io Bundle Context Initialization
Always Auto-invoked skill that creates/updates workspace AGENTS.md to instruct the agent to always search for existing skills before attempting any scientific task. Use when this capability is needed.
- tomevault-io Bundle Daily Blog Post Composer
Compose daily blog posts in a multi-post single-file format from multiple data sources including Mastodon and Linkding. Use this skill when the user requests to create, update, or revise daily blog posts throughout the day. 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 training-optimization, scraperapi--scraperapi-skills--scraperapi-agent-onboarding, non-blocking-execution. 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.