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 Claude ConfigThis skill should be used when configuring Claude, setting up MCP servers, or when "settings.json", "claude_desktop_config", "MCP server", or "Claude config" are mentioned. Use when this capability is needed.
- tomevault-io Bundle Claude Skills
This skill should be used when creating Claude Code skills with Claude-specific features like allowed-tools, context modes (fork/inherit), argument-hint, or model overrides. Triggers on "Claude skill", "allowed-tools", "context fork", "skill arguments". Use when this capability is needed.
- tomevault-io Bundle Task Use Creator Decomposition Strategy
Use to draft decomposition for one feature/epic with dependencies and risks; final scope and priorities stay with main agent Use when this capability is needed.
- tomevault-io Bundle Paddlepaddle Fastdeploy Fastdeploy
FastDeploy LLM Integration Skill
- tomevault-io Bundle Pbans Agent Skillpack Git Workflow
Git Workflow
- tomevault-io Bundle Boros Portfolio Account
View Boros positions, open orders, PnL, settlements, transaction and transfer history, on-chain and liquidation events, assets, collateral, and entered markets. Manage deposits and withdrawals, set up or revoke the delegated agent key, transfer cash between cross and isolated buckets, and read vault and incentive info. Activate when the user asks "how am I doing", wants to deposit, withdraw, set up Boros for the first time, move margin between markets, claim incentives, or audit their trade history. Use when this capability is needed.
- tomevault-io Bundle Docs Prep
Use when preparing documentation for large implementations (Size >= M) following the _docs/ hierarchy and lifecycle rules.
- tomevault-io Bundle Codex Self Rewriting
Lisp machine self-modification patterns via MCP Tasks and Narya bridge types Use when this capability is needed.
- tomevault-io Bundle Commit Security Scan
Analyze code changes for security vulnerabilities using LLM reasoning and threat model patterns. Use for PR reviews, pre-commit checks, or branch comparisons. Use when this capability is needed.
- tomevault-io Bundle Signal Isolated Auth
Maximally isolated Signal authentication via colored operad security boundaries. VM→Container→Process enclosure with GF(3) conservation for Agent-O-Rama pathways. Use when this capability is needed.
- tomevault-io Bundle Aidev Add AI Runner
Add a new AI runner (e.g. another CLI agent) to the aidev project. Use when implementing a new AIRunner, adding a new agent to AGENTS, or extending which AI tools aidev can invoke. Use when this capability is needed.
- tomevault-io Bundle Fleet Agent
Context-aware development assistant for AgenticFleet with auto-learning and dual memory (NeonDB + ChromaDB). Handles development workflows with intelligent context management. Use when this capability is needed.
- tomevault-io Bundle AI Switch Stop
Save the current project progress into PROGRESS.md and commit all changes so that a different AI agent can continue the work in a later session. Use this whenever the user runs out of usage/quota, wants to switch AI agents (Claude Code ↔ Codex ↔ Gemini CLI ↔ Cursor), or stops work to resume later. Trigger on phrases like "ai-switch stop", "/ai-switch-stop", "save progress and commit", "out of quota switch agent", "hand off to another AI". Use when this capability is needed.
- tomevault-io Bundle Openrouter
Use this skill when the user wants to call different LLM models through OpenRouter's unified API, compare model responses, track costs and response times, or find the best model for a task. Triggers include requests to test models, benchmark performance, use specific providers (OpenAI, Anthropic, Google, etc.), or optimize for speed/cost.
- tomevault-io Bundle Writing Agents Md
Teach an agent how to create a high-quality AGENTS.md file for a code project, including structure, rules, conventions, and examples. Use when the user requests guidance or generation of an AGENTS.md file. Use when this capability is needed.
- tomevault-io Bundle Ue Test Patterns
Patterns for writing and running UE 5.7 automation tests Use when this capability is needed.
- tomevault-io Bundle Rshade Agent Skills Security Audit
<!-- Copyright 2025-2026 Richard Shade. Licensed under Apache-2.0. -->
- tomevault-io Bundle Rubakas Agent Notes Rails Concerns
Concerns
- tomevault-io Bundle Threejs Builder
Build and validate simple, performant Three.js web apps using modern ES module patterns. Use this when you need a minimal Three.js scene, interaction, or animation for a web UI or demo. Use when this capability is needed.
- tomevault-io Bundle Jsonlee12138 Agent Team Rules Writer
rules-writer
- tomevault-io Bundle Jwilger Agent Skills Domain Modeling
Domain Modeling
- tomevault-io Bundle Jwilger Agent Skills Task Management
Task Management
- tomevault-io Bundle Stacks Agent
AI-powered intelligence for building Stacks blockchain applications with 40 production code examples Use when this capability is needed.
- tomevault-io Bundle Zk
Intelligent router — analyzes your request and auto-routes to the best execution mode (cyberconan, spectre, siege, legion, hydra, pcc-opus, or pcc). Use instead of choosing manually. Use when this capability is needed.
- tomevault-io Bundle Receipts Guard
Capture and verify all agreements before your agent accepts them. Local risk analysis and evidence capture for autonomous transactions. Use when this capability is needed.
- tomevault-io Bundle Python Pre Commit Validation
Execute mandatory pre-commit validation workflow for Python projects using uv, ruff, and pytest Use when this capability is needed.
- tomevault-io Bundle Kensaurus Cursor Kenji Test Emulator
test-emulator — Native build QA on Android emulator + MCP loop
- tomevault-io Bundle File Organizer Dev
Development guide for the File Organizer MCP server codebase. Use when (1) adding new MCP tools, (2) adding new services, (3) modifying existing tools or services, (4) writing tests, (5) fixing security issues, (6) refactoring code, or (7) understanding the architecture. Provides patterns for Zod schemas, path validation, error handling, and security-hardened file operations. Use when this capability is needed.
- tomevault-io Bundle Lambdatest Agent Skills Agent Skills
Postman Collection Generator
- tomevault-io Bundle Git Workflow Guard
Use when creating branches or commits in this repository and you must enforce MailBot git-flow, commit format, and agent co-author footer rules.
- tomevault-io Bundle Messaging Agents
Send messages to other agents on your server. Use when you need to communicate with, query, or delegate tasks to another agent. Use when this capability is needed.
- tomevault-io Bundle Migrating Memory
Migrate memory blocks from an existing agent to the current agent. Use when the user wants to copy or share memory from another agent, or during /init when setting up a new agent that should inherit memory from an existing one. Use when this capability is needed.
- tomevault-io Bundle Libtv Skill
agent-im 会话技能 - 通过 liblib.tv 的 AI 能力生成和编辑图片/视频。覆盖场景包括：生成（文生图、文生视频、图生视频、做动画、画一个xxx、来段xxx）、编辑修改（把xxx换成yyy、去掉xxx、加上xxx、改成xxx、调整xxx、局部修改、改镜头）、风格转换（风格迁移、转绘、换风格）、视频续写延长、复刻视频/TVC/宣传片、短剧/短漫剧生成、音乐MV生成、产品广告/展示片制作、分镜/故事板设计、教育视频/短视频制作。当用户提到 liblib、libtv、上传参考图/视频、查看生成进度时也应触发。关键判断：只要用户的请求涉及 AI 图片或视频的创作、生成、编辑、修改，无论措辞如何（如"画只猫"、"做个海报"、"把纸船换成爱心"、"这个视频帮我改一下"、"帮我复刻这段视频"、"用这首歌做个MV"、"一句话生成短剧"），都必须触发此技能。 Use when this capability is needed.
- tomevault-io Bundle Transformers
Work with state-of-the-art machine learning models for NLP, computer vision, audio, and multimodal tasks using HuggingFace Transformers. This skill should be used when fine-tuning pre-trained models, performing inference with pipelines, generating text, training sequence models, or working with BERT, GPT, T5, ViT, and other transformer architectures. Covers model loading, tokenization, training with Trainer API, text generation strategies, and task-specific patterns for classification, NER, QA, summarization, translation, and image tasks. (plugin:scientific-packages@claude-scientific-skills) Use when this capability is needed.
- tomevault-io Bundle Lllooollpp Clawdbot Cn Mijia Control
Mijia Control Skill (Universal AI Agent Skill)
- tomevault-io Bundle Jira Orchestration Workflow
This skill should be used when the user asks to "orchestrate jira", "work on issue", "complete jira ticket", "development workflow", "jira automation", "issue lifecycle", "work on story", "fix bug ticket", or needs guidance on coordinating development work through Jira with multi-agent orchestration patterns. 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 claude-config, claude-skills, task-use-creator-decomposition-strategy. 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.