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.
-
majiayu000 Bundle Add Telegram Swarm 4Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
567 - majiayu000 Bundle Moai Tool Ast Grep 3
AST-based structural code search, security scanning, and refactoring using ast-grep (sg CLI) with pattern matching and code transformation across 40+ languages. Use when performing structural code search, AST-based refactoring, codemod operations, security pattern scanning, or syntax-aware code transformations across files. Do NOT use for simple text search (use Grep tool instead) or full codebase exploration (use Explore agent instead).
567 - majiayu000 Bundle Nanobanana Prompt 2
Image generation prompts
567 - majiayu000 Bundle Obsidian Writer 2
Obsidian Vault에 문서를 업로드하는 스킬. 현재 프로젝트의 컨텍스트 문서를 workspace/{프로젝트명}/context/ 경로에 저장합니다. 'obsidian 업로드', 'obsidian에 저장', '옵시디언 문서', 'vault에 업로드' 요청 시 활성화됩니다.
567 - majiayu000 Bundle Rdra Notion 2
RDRA operations (draft creation / consistency check / reporting) on Notion via MCP. PoC-0: only loading check.
567 - majiayu000 Bundle Slashcommandcreator 2
Autonomous meta-skill for creating high-quality custom slash commands using 5-phase workflow with multi-agent validation and quality gates. Use when user requests new slash command, reusable prompt automation, or wants to convert repetitive workflows into documented commands.
567 - majiayu000 Bundle Spellbook Auditing 2
Meta-audit skill for spellbook development. Spawns parallel subagents to factcheck docs, optimize instructions, find token savings, and identify MCP candidates. Produces actionable report.
567 - majiayu000 Bundle Monitoring Logging 3
Implement CloudWatch monitoring, error tracking with Sentry, structured logging, and alert configuration. Apply when setting up monitoring, tracking errors, debugging production issues, or configuring dashboards.
567 - majiayu000 Bundle Context Restore 2
Use when you need to fully restore working context from a previous session - loads STATUS.json, reads key files, rebuilds mental model of current work state. Do NOT use for quick questions or when starting fresh unrelated work - the full context restoration adds overhead that isn't needed for standalone tasks.
567 - majiayu000 Bundle Deepagents CLI 3
Deep Agents CLI reference and usage guide. Use when the user wants to: (1) Launch or configure the deepagents terminal coding assistant, (2) Set up interactive or non-interactive (automation/CI) agent sessions, (3) Manage agent memory, skills, or AGENTS.md context files, (4) Configure LLM providers, models, or sandbox execution environments, (5) Build scripted workflows or subagent patterns with deepagents.
567 - majiayu000 Bundle AI Context Optimizer 2
AIコーディング支援ツールのコンテキストファイル（CLAUDE.md等）を最適化するスキル。 以下の状況で使用: (1) ユーザーが「CLAUDE.mdを改善して」「コンテキストファイルを最適化して」と依頼した時 (2) ユーザーが明示的に「/ai-context」を実行した時-optimizer (3) AI向けドキュメントの品質改善を求められた時
567 - majiayu000 Bundle Omnihuman1 Video 2
OmniHuman1によるAIアバター・リップシンク動画生成ガイド。 Use when: (1) user says「AIアバター」「リップシンク」「OmniHuman」, (2) user wants talking head videos from images, (3) user mentions「アバター動画」「1枚の画像から動画」. Do NOT use for: 実写動画編集（video-agentを使用）、 アニメ制作（anime-productionを使用）。
567 - majiayu000 Bundle Research 60
Web research skill for augmenting agent context with current information. Used when outdated information could lead to broken implementations or wasted effort.
567 - majiayu000 Bundle LLM Wiki 6
Karpathy 风格 LLM Wiki / markdown knowledge base 工作流。用于 ingest、query、lint 持久化知识库；先做 orientation，再按 analysis -> generation 维护 wiki。
567 - majiayu000 Bundle Readme I18N 3
維護 README 的多語言版本，確保中文與英文內容對照同步。
567 - majiayu000 Bundle Recall 10
Query memory system for relevant learnings from past sessions
567 - majiayu000 Bundle Motherduck Connect 2
Connect to MotherDuck from any application. Use when setting up database connectivity via the Postgres endpoint (recommended), pg_duckdb, native DuckDB API, or JDBC. Covers connection strings, authentication, SSL, and environment variable configuration.
567 - majiayu000 Bundle Motherduck Explore 2
Discover and explore databases, tables, columns, and data shares in MotherDuck. Use when you need to understand what data is available, preview table contents, or search the data catalog.
567 - majiayu000 Bundle Implement Sonnet 2
Implement code using sonnet model with full main context access
567 - majiayu000 Bundle Oss License 2
OSSライセンス確認とコンプライアンスガイド。 許可/禁止ライセンス一覧、確認ツール使用法をガイド。
567 - majiayu000 Bundle Reference Sdk 2
Check reference SDK implementations using btca ask
567 - majiayu000 Bundle Instructor 2
Structured outputs with Instructor. Extract typed data from LLMs using Pydantic models and validation. Use for data extraction, structured generation, and type-safe LLM responses.
567 - majiayu000 Bundle Llamaindex 2
Build LLM applications with LlamaIndex. Create indexes, query engines, and data connectors. Use for RAG applications, document search, and knowledge base systems.
567 - majiayu000 Bundle Aitask Refresh Code Models 3
Research latest AI code agent models via web and update models_*.json configuration files.
567 - majiayu000 Bundle Axiom Foundation Models 2
Use when implementing on-device AI with Apple's Foundation Models framework — prevents context overflow, blocking UI, wrong model use cases, and manual JSON parsing when @Generable should be used. iOS 26+, macOS 26+, iPadOS 26+, axiom-visionOS 26+
567 - majiayu000 Bundle Audit 18
Generate usage report for MiniMax and token optimization Use when: (1) /audit is invoked, (2) task relates to audit functionality.
567 - majiayu000 Bundle How To Publish Paks 2
A practical guide for creating and publishing Agent Skills (paks) to the Paks registry. Covers SKILL.md format, frontmatter structure, validation, versioning, and publishing workflow.
567 - majiayu000 Bundle Nest Server Updating 2
Knowledge base for updating @lenne.tech/nest-server. Use when discussing nest-server updates, upgrades, migrations, breaking changes, or version compatibility. Provides resources, migration guide patterns, and error solutions. For execution, use the nest-server-updater agent.
567 - majiayu000 Bundle Treesitter 2
Parse and extract code symbols using tree-sitter. Use when you need to extract functions, classes, or understand code structure from files or code blocks.
567 - majiayu000 Bundle Axiom Swiftdata 2
Use when working with SwiftData - @Model definitions, @Query in SwiftUI, @Relationship macros, ModelContext patterns, CloudKit integration, iOS 26+ features, and Swift 6 concurrency with @MainActor — Apple's native persistence framework
567 - majiayu000 Bundle Motherduck Ducklake 2
Decide when DuckLake is the right MotherDuck storage pattern. Use when evaluating fully managed DuckLake, BYOB, own-compute DuckLake access, data inlining, object-storage layout, or file-aware maintenance instead of native MotherDuck storage.
567 - majiayu000 Bundle Zod Validation 6
Runtime type validation with Zod for schema definition, form validation, API contracts, and TypeScript type inference. Use when validating user input, defining API schemas, or building type-safe data pipelines. Triggers on zod, schema validation, form validation, type inference, runtime validation, typescript validation.
567 - majiayu000 Bundle Google Search 2
Google Search grounding allows LLM applications to access real-time information and provide verifiable citations. This skill covers both direct tool integration (like Gemini's googlesearch) and custom
567 - majiayu000 Bundle Setup 39
This skill should be used when user encounters "Slack MCP error", "invalid_auth", "missing_scope", "Slack not working", "Slack token invalid", "channel_not_found", or needs help configuring Slack integration.
567 - majiayu000 Bundle Setup 40
This skill should be used when user encounters "Linear auth failed", "Linear OAuth error", "Linear MCP error", "Linear not working", "unauthorized", or needs help configuring Linear integration.
567 - majiayu000 Bundle Readme I18N 4
維護 README 的多語言版本，確保中文與英文內容對照同步。
567
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 add-telegram-swarm, moai-tool-ast-grep, nanobanana-prompt. 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.