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 Decay UpkeepBuilding decay and upkeep systems for survival games. Use when implementing timer-based decay, Tool Cupboard patterns (Rust-style protection radius), resource upkeep costs, or server performance management through automatic cleanup. Balances gameplay and server health. Use when this capability is needed.
- tomevault-io Bundle Glm Calibration
Calibrate GLM parameters for water temperature simulation. Use when you need to adjust model parameters to minimize RMSE between simulated and observed temperatures. Use when this capability is needed.
- tomevault-io Bundle Librarian Update
Run the librarian agent to update the codebase graph after recent changes. Reads git diff and updates .claude/scratchpad/librarian/codebase_graph.md. Use when this capability is needed.
- tomevault-io Bundle Zabal Games Context
ZAO ecosystem context skill for ZABAL Games participants. Drop into your vibe-coding agent (Claude Code, Cursor, Windsurf, Cline, etc) so it understands ZAO, ZABAL, WaveWarZ, the active tooling stack, brand voice, and what a "good submission" looks like. Use when building anything for the ZABAL Games June bootcamp / July build-a-thon / August Finals. Use when this capability is needed.
- tomevault-io Bundle Codex CLI Knowledge
OpenAI Codex CLI の仕様と使い方に関する知識を提供。モデル選択、推論レベル、承認モード、サンドボックス、組み込みツール、スラッシュコマンド、Plan モード、マルチエージェント協調、メモリ管理、Steer モード、パーソナリティ設定、プラグインシステム、MCP 連携、フックエンジン、カスタムエージェントについて回答。Use when user asks about Codex CLI, codex command, approval mode, sandbox, AGENTS.md, codex configuration, /model, /review, /compact, /plan, /personality, /collab, /agent, apply_patch, reasoning level, multi-agent, plugin system, MCP server, hook engine, or memory management. Also use when user says Codex CLI について, codex の使い方, 承認モード, 推論レベル. Use when this capability is needed.
- tomevault-io Bundle Kirby Content Migration
Plans and applies safe Kirby content migrations using runtime content tools, update schemas, and explicit confirmation. Use when users need to rename/move/transform fields, clean up content, or bulk-update pages/files across languages. Use when this capability is needed.
- tomevault-io Bundle Kirby Security And Auth
Secures Kirby sites with access restriction, user roles, permissions, and protected downloads. Use when implementing login/role-based access, permissions, or file protection. Use when this capability is needed.
- tomevault-io Bundle Bolta Review Digest
V2 - Generate a human-readable review summary (daily/weekly digest) of inbox activity, agent performance, and pending actions. Use when this capability is needed.
- tomevault-io Bundle Golang Testcontainers
Write Go integration tests with testcontainers-go Use when this capability is needed.
- tomevault-io Bundle Analyze MCP
Analyze MCP server structure and create wrapping strategy when user needs to understand an MCP server or create a CLI wrapper Use when this capability is needed.
- tomevault-io Bundle Smart Money Tracker
聪明钱追踪师 - 综合北向资金、龙虎榜、大宗交易、资金流向，追踪主力资金动向 Use when this capability is needed.
- tomevault-io Bundle Setup Multi Repo
Set up a multi-clone repo folder structure with a primary clone and 5 slot clones for parallel Claude Code agent work. Use when the user says "set up multi-repo", "setup slots", "create repo slots", or wants to create the same folder pattern used for towles-tool-repos. Use when this capability is needed.
- tomevault-io Bundle Aliyun Solution Article Illustrator Test
Smoke test for aliyun-solution-article-illustrator. Validate solution-skill structure, compatibility-oriented documentation, prompt-before-image workflow, backend recommendation policy, and final Markdown output artifacts. Use when this capability is needed.
- tomevault-io Bundle Coreml Optimizer
Optimize CoreML models for iOS and macOS deployment. Covers quantization, palettization, pruning, Neural Engine targeting, compute unit selection, and performance profiling. Use when converting ML models to CoreML, optimizing model size/latency, debugging Neural Engine issues, or benchmarking on-device inference. Use when this capability is needed.
- tomevault-io Bundle Clearfunction Cf Devtools MCP Management
MCP Management
- tomevault-io Bundle LLM Service Integration
Guide for integrating with LLM providers in the DEVS platform. Use this when asked to add LLM functionality, create AI-powered features, or work with the LLM service. Use when this capability is needed.
- tomevault-io Bundle Parity Safety Net Rules
View, set, and verify the custom guard rules enforced by Lisa's safety-net PreToolUse Bash hook (parity-safety-net.sh). The consolidated cross-agent equivalent of the upstream safety-net plugin's set-custom-rules + verify-custom-rules skills — manages a project-local list of extended-regex patterns that block destructive shell commands, on Codex, agy, Copilot, Cursor, and Claude. Use when this capability is needed.
- tomevault-io Bundle Confluentinc MCP Confluent MCP Confluent
PR Review Skill
- tomevault-io Bundle Nushell Tooling
This skill should be used when the user asks to "lint Nushell code", "use nu-lint", "set up Nushell LSP", "configure nu --lsp", "use nu --mcp", "test Nushell scripts", "generate documentation", "format Nushell code", "debug Nushell", or mentions LSP, MCP server, linting, testing, debugging, or IDE integration for Nushell. Use when this capability is needed.
- tomevault-io Bundle Davepoon Buildwithclaude Coda Automation
Coda Automation via Rube MCP
- tomevault-io Bundle Zoom Automation
Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas. Use when this capability is needed.
- tomevault-io Bundle Qdrant Vector Search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance. Use when this capability is needed.
- tomevault-io Bundle Information Security Strategy
AI-enabled security excellence through transparent ISMS implementation, defense-in-depth, and strategic planning aligned with Hack23 business model Use when this capability is needed.
- tomevault-io Bundle Agentworkos Inventory
Scan and package-manage a local AgentWorkOS environment, including Codex skills, agent role cards, TERMS.md, AGENTS.md rules, local repositories, lockfiles, and sync drift. Use when the user asks to migrate machines, restore AI workspace context, package skills, or verify three-end sync. Use when this capability is needed.
- tomevault-io Bundle Helloworldsungin Ark AI MCP MCP Context7
<objective>
- tomevault-io Bundle Helloworldsungin Ark AI MCP MCP Deepwiki
<objective>
- tomevault-io Bundle Inspector
PDCO 全局监管系统 - Codex 版本。评估和管理所有 Agent（编程/分析/设计等）的质量、效率和成长。 Use when this capability is needed.
- tomevault-io Bundle Chrome Devtools Debugger
chrome-devtools-mcp を使ってWebサイトの問題を体系的にデバッグします。ネットワークエラー、コンソールエラー、パフォーマンス問題、UI/UXの問題を調査する際に使用します。 Use when this capability is needed.
- tomevault-io Bundle Playwright Cross Browser
Playwright MCPを使用してFirefox/WebKitなどChrome以外のブラウザでの動作確認を行います。クロスブラウザ互換性の問題を調査する際に使用します。 Use when this capability is needed.
- tomevault-io Bundle Skill Personalizer
Use when auditing or adapting newly created, downloaded, forked, installed, or community Agent Skills to the user's tools, habits, directories, session history, and preferred workflows, especially when triggers feel wrong, noisy, or too generic.
- tomevault-io Bundle Agent Configuration
Configure agent specs, inheritance, skills, and tools in .parac/ workspace. Use when setting up or customizing agents. Use when this capability is needed.
- tomevault-io Bundle Daily Papers X
Automatically fetch and summarize trending AI papers from arXiv and Hugging Face with x.com-style hot topic detection. Focuses on 4 research directions - AI/LLM, Embodied AI, AI+Finance, AI+Biomedical. Use when this capability is needed.
- tomevault-io Bundle Igorbeethetech Skills Knowledge Base RAG
Knowledge Base RAG System Generator
- tomevault-io Bundle Injective CLI
Use the Injective `injectived` CLI against a chain with consistent wallet, endpoint, and gas handling. Use the CLI map and reference docs to find commands and build transactions safely. Use when this capability is needed.
- tomevault-io Bundle Lorem Ipsum
Generate lorem ipsum placeholder text. This skill should be used when users ask to generate lorem ipsum content, placeholder text, dummy text, or filler text. Supports various structures including plain paragraphs, headings with sections, lists, and continuous text. Output can be saved to a file or used directly as requested by the user. Use when this capability is needed.
- tomevault-io Bundle Compare Versions
Compare different states of a threat model to identify architectural and security changes. Use when reviewing pull requests for security impacts, detecting drift from approved baselines, or auditing historical changes. Returns structured diff for interpretation. 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 decay-upkeep, glm-calibration, librarian-update. 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.