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 Paiml Paiml MCP Agent Toolkit Pmat RefactorPMAT Automated Refactoring Skill
- tomevault-io Bundle Ast Grep Find
AST-based code search and refactoring via ast-grep MCP Use when this capability is needed.
- tomevault-io Bundle Email Management Expert
Expert email management assistant for Apple Mail. Use this when the user mentions inbox management, email organization, email triage, inbox zero, organizing emails, managing mail folders, email productivity, checking emails, or email workflow optimization. Provides intelligent workflows and best practices for efficient email handling. Use when this capability is needed.
- tomevault-io Bundle Adr Creation
Template and process for creating Architecture Decision Records (ADRs). Use this when making significant technical decisions that affect system design. Use when this capability is needed.
- tomevault-io Bundle Codex Context Budget Audit
Audit Codex initial-context budget and token overhead from a specific workdir or Codex home. Use when the user asks to inspect, compare, reduce, or visualize initial prompt/token usage from skills, plugins, MCP servers, memories, AGENTS.md, or runtime configuration. Includes a CLI that reports phase-separated estimates and an ASCII prompt-composition chart. Use when this capability is needed.
- tomevault-io Bundle Claude Code Plugin Builder
Creates Claude Code plugins with proper manifest structure, directory layout, and components (commands, agents, skills, hooks, MCP servers). Use when user requests creating plugins, adding slash commands, integrating MCP servers, setting up hooks, migrating Gemini extensions, or mentions "plugin.json", ".claude-plugin", or "marketplace.json". Handles plugin testing, debugging, and marketplace distribution.
- tomevault-io Bundle Create Commit Instructions
Generate or update `.github/instructions/commit.instructions.md` for the current workspace from bundled `assets/commit.instructions.d` fragments. Use when the user asks to create commit instructions, Conventional Commit guidance, repository-specific commit message rules, or GitHub Copilot/agent commit instructions, especially when the SCOPE GUIDANCE and GOOD EXAMPLES sections must be adapted to the project being edited. Use when this capability is needed.
- tomevault-io Bundle Podo Design Agent Skills Google Fonts Skill
google-fonts-skill
- tomevault-io Bundle Draft Plan Review
复审 plan-agent 生成的"预定清单（草案）"。触发：用户让你复审/分析/补全 plan-agent 的项目规划草案时使用；读取 draft-plan.md 并回写分析结果。 Use when this capability is needed.
- tomevault-io Bundle Vasallo94 Obsidian MCP Server Git Workflow
Git Workflow Skill
- tomevault-io Bundle Governancedefine Roc
Defines a Rule of Constraints policy bundle for agent autonomy. Use when this capability is needed.
- tomevault-io Bundle Glab MCP
Work with Model Context Protocol (MCP) server for AI assistant integration. Exposes GitLab features as tools for AI assistants (like Claude Code) to interact with projects, issues, merge requests, and pipelines. Use when integrating AI assistants with GitLab or working with MCP servers. Triggers on MCP, Model Context Protocol, AI assistant integration, glab mcp serve. Use when this capability is needed.
- tomevault-io Bundle Detecting Dead Code
Identifies unreachable functions, unused variables, and abandoned code in binary programs. Use when optimizing binary size, analyzing code coverage, or investigating abandoned functionality. Use when this capability is needed.
- tomevault-io Bundle J Skills
CLI tool for managing Agent Skills - link, install, and manage skills across 35+ coding agent environments Use when this capability is needed.
- tomevault-io Bundle Web Performance Audit
Audit web performance using Chrome DevTools MCP. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Use when this capability is needed.
- tomevault-io Bundle Webdevcody Go Mailing List Commit And Push
> **User-question protocol:** Whenever this skill needs the user to pick between options, confirm an action, or answer a multiple-choice prompt, you MUST call the `AskUserQuestion` tool to render a proper interactive picker. Do NOT print numbered options as plain text and wait for the user to type a number — that produces a degraded UX. Free-form questions (open-ended typing) may be asked in prose, but any time you would write "1) … 2) … 3) …", use `AskUserQuestion` instead.
- tomevault-io Bundle Willyu1007 AI First Template Runtime Model
Runtime Model
- tomevault-io Bundle Bug Fix Agent
Bug Fix Agent - Automated bug fixing with review loopback and auto-commit to main branch. Fixes bugs, tests them, reviews quality, and commits when quality gates pass. Use when this capability is needed.
- tomevault-io Bundle Grepai Chunking
Configure code chunking in GrepAI. Use this skill to optimize how code is split for embedding. Use when this capability is needed.
- tomevault-io Bundle Nushell Plugin Builder
Guide for creating Nushell plugins in Rust using nu_plugin and nu_protocol crates. Use when users want to build custom Nushell commands, extend Nushell with new functionality, create data transformations, or integrate external tools/APIs into Nushell. Covers project setup, command implementation, streaming data, custom values, and testing. Use when this capability is needed.
- tomevault-io Bundle Implement Agent Skills
Comprehensive workflow for creating, implementing, and validating Agent Skills. Use when asked to "create a new skill", "author a skill", "add a capability", or when standardizing project-specific workflows. Support for platform detection (Cursor, Claude Code, Gemini CLI, Codex) and template selection. Use when this capability is needed.
- tomevault-io Bundle Fastgpt Workflow Generator
Generates production-ready FastGPT workflow JSON from natural language requirements. Uses AI-powered semantic template matching from built-in workflows (document translation, sales training, resume screening, financial news). Performs three-layer validation (format, connections, logic completeness). Supports incremental modifications to add/remove/modify nodes. Activates when user asks to "create FastGPT workflow", "generate workflow JSON", "design FastGPT application", or mentions workflow automation, multi-agent systems, or FastGPT templates.
- tomevault-io Bundle Go Navigator Read
Use Go Navigator MCP to explore Go code semantically (packages, symbols, definitions/references, context, metrics, deps) and return file/line/snippets; do not modify code. Use when this capability is needed.
- tomevault-io Bundle Text Summary Guide
Guide for AI agent to perform text summary task. Use when this capability is needed.
- tomevault-io Bundle Guided Dev Team
Guided full-lifecycle development orchestration via agent team. Use when the user asks to "start a new task from scratch", "walk me through the full workflow", "guide me through development", or wants structured define, plan, implement, review, and commit phases with decision points. Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS enabled. Use when this capability is needed.
- tomevault-io Bundle Dispatch Watcher
Optional agent dispatch watcher — Phase 1 walking skeleton, Codex-flavored. Use on agent session start when a Slack-style dispatch channel assigns GitHub issues to a model handle such as @codex. For Claude use `.agent/skills/dispatch-watcher-claude/SKILL.md`, for Gemini use `.agent/skills/dispatch-watcher-gemini/SKILL.md`, for the full multi-agent contract see `.agent/skills/agent-presence/SKILL.md`. Use when this capability is needed.
- tomevault-io Bundle Playlist Variety Auditor
Audit DJ lighting playlists for effect-family diversity, strobe density, phase coverage, and role balance. Use when validating that playlists are not repetitive and comply with guide constraints before showtime. Use when this capability is needed.
- tomevault-io Bundle Tool Image Prompt
Generate Adobe Firefly image prompts for AEM tools website (tools.aem.live) tool card thumbnails. Use when creating or updating thumbnail images for tools, or when a new tool needs a card image. Triggers on requests like "create an image for the X tool", "generate a tool thumbnail", "make a Firefly prompt for this tool". Use when this capability is needed.
- tomevault-io Bundle Agent Symlink Init
Initialize or migrate agent-skill symlinks in any repository. Use when a project needs `.claude/skills` linked to `.agents/skills`, `AGENTS.md` linked to `CLAUDE.md`, migration away from `.ruler`-based AI rules, or removal of legacy `sync-llm-skills` copy/sync setups. Trigger on requests about Claude/Codex skill symlinks, AGENTS/CLAUDE symlinks, `.claude/skills` setup, replacing copied skill folders with symlinks, or cleaning old ruler/sync automation. Use when this capability is needed.
- tomevault-io Bundle Argocd MCP Server
ArgoCD MCP Server
- tomevault-io Bundle Cre Document Ingestion
CRE Document Ingestion suite — 4 specialist skills for classifying and extracting structured data from deal documents including rent rolls, T-12 financials, and offering memoranda. Use when this capability is needed.
- tomevault-io Bundle Tutorial Engineer
Creates step-by-step tutorials and educational content from code. Transforms complex concepts into progressive learning experiences with hands-on examples.
- tomevault-io Bundle Techwavedev Agi Agent Kit Vercel Automation
Vercel Automation via Rube MCP
- tomevault-io Bundle Techwavedev Agi Agent Kit Vercel Deployment
Vercel Deployment
- tomevault-io Bundle Theagenticguy Erpaval Meta Prompt Optimizer
Contents
- tomevault-io Bundle Archi MCP Modeling
Model and evolve ArchiMate architectures through the local Archi MCP server with semantically correct element and relationship choices. Use when asked to create/update Archi models, generate views, map capabilities to applications/technology, or apply migration roadmaps using safe async operations. 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 paiml--paiml-mcp-agent-toolkit--pmat-refactor, ast-grep-find, email-management-expert. 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.