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 Agent RolesCollaboration protocol for autonomous agents working on shared repositories. Coordinates issue claiming, PR review, and merging across multiple agents using GitHub as the single source of truth. Use when this capability is needed.
- tomevault-io Bundle Huggingface
Sync Janitr experiment artifacts from remote to local and publish to Hugging Face experiments repo with single-index and manifest validation. Use when this capability is needed.
- tomevault-io Bundle Snip
You are an expert at writing declarative YAML filters for **snip**, a CLI proxy that reduces LLM token consumption by filtering shell output. Use when this capability is needed.
- tomevault-io Bundle Route
Analyze project state and route user to the appropriate agent based on current context. Use when this capability is needed.
- tomevault-io Bundle Flurdy Agent Skills Next
Next - Pick Your Next Bead
- tomevault-io Bundle Agent Eval
Head-to-head comparison of coding agents (Gemini Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics Use when this capability is needed.
- tomevault-io Bundle JWT
JSON Web Tokens for secure transmission. Use for authentication. Use when this capability is needed.
- tomevault-io Bundle Nim
Nim systems programming with Python-like syntax. Use for .nim files. Use when this capability is needed.
- tomevault-io Bundle PHP
PHP 8+ web development with Composer, attributes, and modern frameworks. Use for .php files. Use when this capability is needed.
- tomevault-io Bundle Pip
pip Python package manager. Use for Python packages. Use when this capability is needed.
- tomevault-io Bundle Swc
SWC Rust-based JS/TS compiler. Use for fast compilation. Use when this capability is needed.
- tomevault-io Bundle Tig
tig text-mode git interface. Use for git browsing. Use when this capability is needed.
- tomevault-io Bundle Graft Boot
Repository-specific startup workflow for Graft. Use when the task starts from a short prompt such as "boot", "continue", "read AGENTS", or "next step", and Codex should first ground itself in AGENTS.md, the ai-plan/ documents, the current repo state, assess whether multi-agent work is justified, and then enter implementation with the repository's closeout and commit workflow in place. Use when this capability is needed.
- tomevault-io Bundle Fuzzing Memory Unsafe Expert
This skill provides the agent with the necessary knowledge and tools to fuzz open source software projects, particularly those that are part of the OSS-Fuzz program. The agent can use this skill to build fuzzers, run fuzzing campaigns, analyze results, and improve the fuzzing posture of projects. Use when this capability is needed.
- tomevault-io Bundle Guoqingbao Xinfer Xinfer
Check Model — Pre-Load Compatibility Audit for xinfer
- tomevault-io Bundle Emoji
Generate emoji packs using AI-powered prompt generation and image creation Use when this capability is needed.
- tomevault-io Bundle Hegelion
Dialectical reasoning and autocoding via Hegelion MCP tools. Use when this capability is needed.
- tomevault-io Bundle Dgame Dev
DGame Unity 项目开发指导。触发词：DGame, GameModule, UIWindow, UIWidget, UIModule, AddUIEvent, GameEvent, GameEventDriver, EEventGroup, LoadAssetAsync, LoadGameObjectAsync, SetSprite, ConfigSystem, HybridCLR, YooAsset, Luban, RedDotModule, CoplayDev unity-mcp, MCP, 热更, 资源加载, UI开发, 事件系统, 模块架构 Use when this capability is needed.
- tomevault-io Bundle Nelson
Orchestrates multi-agent task execution using a Royal Navy squadron metaphor — from mission planning through parallel work coordination to stand-down. Use when work needs parallel agent orchestration, tight task coordination with quality gates, structured delegation with progress checkpoints, or a documented decision log. Use when this capability is needed.
- tomevault-io Bundle Agnix
Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 385 rules.
- tomevault-io Bundle Desktop App Flows
Understand and explore the Omi desktop macOS app's UI flows, navigation patterns, and SwiftUI architecture. Use when developing features, fixing bugs, or verifying changes in desktop/ Swift files. Provides agent-swift commands to explore the live app, understand how screens connect, and verify your work. Use when this capability is needed.
- tomevault-io Bundle Jlens MCP
专业级 Java 代码库分析与 Maven 依赖管理技能。当需要进行以下操作时触发：(1) 在多模块项目中使用多版本隔离技术分析 Java 类结构，(2) 深度解析 Maven 依赖树及排查版本冲突，(3) 利用游标分页在海量 Jar 包中搜索类，(4) 自动化执行 Maven 构建任务，(5) 智能识别本地源码与第三方库。本技能指导 Agent 优先使用已注册的 MCP 服务，并提供命令行模式的 Fallback 机制。 Use when this capability is needed.
- tomevault-io Bundle Officecli Financial Model
Use this skill when the user wants to build a financial model,
- tomevault-io Bundle Ralph
Autonomous agent for tackling big projects. Create PRDs with user stories, then run them via the CLI. Sessions persist across restarts with pause/resume and real-time monitoring. Use when this capability is needed.
- tomevault-io Bundle Ue MCP Native Cpp
Use when writing or modifying native C++ UCLASSes in an Unreal project via ue-mcp. Covers create_cpp_class → write_cpp_file → live_coding_compile loop, when to use build vs Live Coding, and the add_module_dependency workflow. Pulls in any time the user asks to write a new native class, add a UPROPERTY, or implement a UFUNCTION.
- tomevault-io Bundle Clify
Generate a self-updating CLI repo from an API documentation URL. Use when the user says "/clify <url>", "generate a CLI for this API", or wants to create agent-friendly API wrappers. Use when this capability is needed.
- tomevault-io Bundle Beads Orchestration
Multi-agent orchestration for GitHub Issues using BEADS task tracking Use when this capability is needed.
- tomevault-io Bundle Dust LLM
Step-by-step guide for adding support for a new LLM in Dust. Use when adding a new model, or updating a previous one. Use when this capability is needed.
- tomevault-io Bundle Prime
New agent startup checklist for Agent Mail and Beads. Use when starting a new agent session, when the user says "prime" or "startup", or when beginning work on a multi-agent project. Use when this capability is needed.
- tomevault-io Bundle Clawhub
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI. Use when this capability is needed.
- tomevault-io Bundle Query
Query Ethereum network data via ethpandaops CLI or MCP server. Use when analyzing blockchain data, block timing, attestations, validator performance, network health, or infrastructure metrics. Provides access to ClickHouse (blockchain data), Prometheus (metrics), Loki (logs), and Dora (explorer APIs). Use when this capability is needed.
- tomevault-io Bundle Link Retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP. Use when this capability is needed.
- tomevault-io Bundle Papi
This skill should be used when the user wants to interact with their paper database — listing papers, searching content, showing paper details, adding papers, or exporting context. Matches queries like "search papers for X", "add this arXiv paper", "show equations from paper Y", "what papers do I have". Prefer CLI over MCP RAG tools for direct lookups. Use when this capability is needed.
- tomevault-io Bundle Config Schema Sync
Use when reviewing, writing, or committing changes that touch model/config.go or any TOML config struct in this repo. Verifies that every added, renamed, or removed TOML field has a matching update in sesh.schema.json so the JSON schema used by TOML editors (via `#:schema` directive) stays in sync with the Go config model. Trigger whenever a diff touches files under model/, configurator/, or any struct tagged with `toml:"..."`.
- tomevault-io Bundle Gnhf
Use when the user asks to run GNHF, says they are going to sleep or leaving and wants an agent-managed coding run, asks to supervise, steer, or review an active GNHF run, or gives feedback on GNHF results.
- tomevault-io Bundle Toolfs RAG
Semantic search over vector databases for document retrieval. Use this skill when the user requests searching documents, finding relevant content, or performing semantic queries such as "Search for information about X", "Find documents related to Y", or "Query the knowledge base". 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 agent-roles, huggingface, snip. 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.