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 Prompt RefinerRefine rough prompts into structured, high-quality prompts. Use this skill when the user has a vague request and wants to turn it into a well-structured prompt with clear objectives, constraints, and acceptance criteria. Triggers include "refine this prompt", "make this prompt better", "structure this request", or "help me write a better prompt". Use when this capability is needed.
- tomevault-io Bundle Babegeman MCP Diagnostic MCP Diagnostic
MCP Diagnostic Skill
- tomevault-io Bundle Hello Auditkit
Use this skill to audit, review, validate, or check the quality of AI assistant configurations including prompt text, prompt files, skills (SKILL.md), plugins, MCP servers, agents, hooks, memory files (AGENTS.md, CLAUDE.md, GEMINI.md), and composite configurations. Evaluates against GPT Prompting Guide best practices.
- tomevault-io Bundle Fuzzing Python
Creating fuzz driver for Python libraries using LibFuzzer. This skill is useful when agent needs to work with creating fuzz drivers / fuzz targets for Python project and libraries. Use when this capability is needed.
- tomevault-io Bundle Lean4 Memories
This skill should be used when working on Lean 4 formalization projects to maintain persistent memory of successful proof patterns, failed approaches, project conventions, and user preferences across sessions using MCP memory server integration Use when this capability is needed.
- tomevault-io Bundle Search Flights
Search flights by origin, destination, and departure date using the bundled flights dataset. Use this skill when proposing flight options or checking whether a route/date combination exists. Use when this capability is needed.
- tomevault-io Bundle Storage
Storage management for Zephyr RTOS. Covers Non-Volatile Storage (NVS) for persistent settings, flash partition management in Devicetree, and runtime flash layout access. Trigger when implementing persistent data storage, managing flash wear leveling, or configuring device partitions. Use when this capability is needed.
- tomevault-io Bundle Memory Bank Protocol
Hybrid memory system combining OpenMemory MCP (semantic persistence) with .agent/memory-bank/ static files (structural context). OpenMemory is the primary dynamic memory; memory-bank files are the structural foundation. Use when this capability is needed.
- tomevault-io Bundle Blazemeter Recorders
Comprehensive guide for BlazeMeter Recorders, including Chrome Extension and Proxy Recorder. Use when working with recorders for (1) Recording tests with Chrome Extension, (2) Creating and using Proxy Recorder, (3) Configuring browsers and devices for proxy recording, (4) Setting port ranges for proxy recorder, or any other recording tasks. Use when this capability is needed.
- tomevault-io Bundle Blazemeter Scripting
Comprehensive guide for BlazeMeter Scripting, including Groovy/Beanshell, JMeter plugins, JMeter DSL, and API Monitoring scripting. Use when working with scripting for (1) Writing files in Groovy/Beanshell scripts, (2) Using non-standard JMeter plugins, (3) Creating JMeter tests with JMeter DSL, (4) Writing custom scripts for API Monitoring (custom libraries, included libraries, initial script, reusable snippets), or any other scripting tasks. Use when this capability is needed.
- tomevault-io Bundle Bmob Database Android
Use when implementing Bmob NoSQL database CRUD in an Android Native project (Java or Kotlin). Triggers: io.github.bmob:android-sdk, Bmob.initialize(this, ...), BmobObject, BmobQuery, BmobUser, BmobInstallation, BmobFile, BmobRelation, BmobGeoPoint, BmobDate, SaveListener, UpdateListener, FindListener, QueryListener, BmobException, BmobContentProvider, AndroidManifest Bmob 配置. NOT for cross-platform JavaScript / WeChat Mini Program / Cocos Creator JS (use bmob-database-javascript), iOS / Swift (use bmob-database-ios), Flutter / Dart (use bmob-database-flutter), or raw HTTP from any other language (use bmob-database-restful). If Bmob MCP is configured, call get_project_tables via bmob-mcp before writing code.
- tomevault-io Bundle Security Vulnerability Testing
Production-grade security testing with agentic vulnerability detection, SAST/DAST tools, OWASP Top 10 coverage, threat modeling, and AI-powered security analysis achieving 92% detection accuracy (OpenAI Aardvark benchmark 2024) Use when this capability is needed.
- tomevault-io Bundle Git Commit Bullets
Perform git commit with the message body written as a bullet list. Use when committing with git and the user wants bullet-list commit bodies. Use when this capability is needed.
- tomevault-io Bundle Cursor Specialist
Expert on Cursor IDE — rules format, agent modes, composer, MCP, tab completion, configuration. Always validates against official docs before acting. Use when this capability is needed.
- tomevault-io Bundle Bsamiee Parametric Portal Agent Builder
[H1][AGENT-BUILDER]
- tomevault-io Bundle Python Agent Development
Python Agent 开发规范（Windows wxauto v4），包括项目结构、模块化、wxauto 使用、IPC 集成、错误处理、测试和部署。 Use when this capability is needed.
- tomevault-io Bundle Gemini Audit
Run audit workflow via Gemini CLI to validate task and plan alignment Use when this capability is needed.
- tomevault-io Bundle Creating Financial Models
This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions Use when this capability is needed.
- tomevault-io Bundle Ssh MCP Helper
Use when 用户希望安装、配置或新增 ssh-mcp-server 的 MCP 连接（如「帮我装一下 ssh-mcp-server」「给 Cursor/Claude Code 配置 SSH MCP」「在已有 MCP 里加一台远程主机」「ssh-mcp-server 的 mcp.json 怎么写」）。技能通过逐步问答收集主机、认证、传输模式、命令限制等参数，并把生成的 mcpServers JSON 片段写入对应客户端的配置文件。
- tomevault-io Bundle Orchestration Workflow
Guide for working with the multi-agent orchestration system in DEVS. Use this when asked to modify task orchestration, agent coordination, or workflow execution. Use when this capability is needed.
- tomevault-io Bundle Commandcodeai Agent Skills Agent Skills
Building MCP Servers on Cloudflare
- tomevault-io Bundle Repo Researcher
Research GitHub repositories to find trending tools, MCP servers, and CLI utilities that could expand AI assistant capabilities. Use when the user wants to discover new repos, research a specific repo, or find trending tools for their stack (LibreChat, OpenClaw, MCP servers, CLI tools, etc.). Triggers on phrases like "find repos", "research repo", "what's trending", "suggest tools", or when asked about GitHub repositories. Use when this capability is needed.
- tomevault-io Bundle Readable Cpp
Readable C/C++/Rust/CUDA code rules inspired by The Art of Readable Code. Use when writing, reviewing, or refactoring C, C++, Rust, or CUDA code. Enforces short functions, flat control flow, clear naming, readable structure, and idiomatic patterns. Use when this capability is needed.
- tomevault-io Bundle Pynchy Plugin Authoring
Use when creating, scaffolding, or updating a pynchy plugin, including channels, MCP servers, skills, agent cores, workspace specs, and container runtime plugins. Also use when users ask how to register plugins via config.toml, add entry points, or validate plugin hook wiring.
- tomevault-io Bundle Cyanheads Git MCP Server Git MCP Server
Preconditions
- tomevault-io Bundle Bat Story Eval
Compare MCP tool behavior between target and baseline versions using pre-built and custom stories with diff-based triage. Use when this capability is needed.
- tomevault-io Bundle Hosungyou Diverga Research Coordinator
MANDATORY: Checkpoint Enforcement Rules (v8.2 — MCP-First)
- tomevault-io Bundle Litellm
Unified LLM API with LiteLLM. Call 100+ LLM providers with one interface. Use for multi-provider AI, cost optimization, fallbacks, and LLM gateway deployment. Use when this capability is needed.
- tomevault-io Bundle Meta Capabilities
Advanced AI capabilities for paracle_meta including web search, code execution, MCP integration, and autonomous agent spawning. Use when you need enhanced AI functionality beyond basic generation. Use when this capability is needed.
- tomevault-io Bundle Idusortus CLI Five Agent Customization
Agent Customization
- tomevault-io Bundle Igmarin Rails Agent Skills Code Review
Code Review
- tomevault-io Bundle J4flmao Agent Skills Rust Architecture
Rust Architecture
- tomevault-io Bundle Publish Code
Prepare and publish an open-source project. Use when user wants to open-source a repo, make a project public, or prepare code for release. Use when this capability is needed.
- tomevault-io Bundle Codex Docs
Local Codex CLI documentation reference. Use when asked about Codex features, configuration, skills, rules, custom prompts, MCP, or AGENTS.md setup. Use when this capability is needed.
- tomevault-io Bundle Story Explanation
Create compelling story-format summaries using UltraThink to find the best narrative framing. Support multiple formats - 3-part narrative, n-length with inline links, abridged 5-line, or comprehensive via Foundry MCP. USE WHEN user says 'create story explanation', 'narrative summary', 'explain as a story', or wants content in Daniel's conversational first-person voice. Use when this capability is needed.
- tomevault-io Bundle Creating Plugins
Guide for creating Claude Code plugins with commands, agents, skills, hooks, and MCP servers. Use when the user wants to create a new plugin, add plugin components (commands, agents, hooks), set up a plugin marketplace, or needs help with plugin.json configuration. 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 prompt-refiner, babegeman--mcp-diagnostic--mcp-diagnostic, hello-auditkit. 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.