flowing-abyss

Generate Obsidian Excalidraw diagrams from text content as vault-native .md files for the Obsidian Excalidraw plugin. INVOKE when user wants to create a visual diagram. Triggers: "Excalidraw", "draw diagram", "flowchart", "mind map", "visualize", "diagram", "нарисуй диаграмму", "визуализируй", "создай схему", "майнд мап", "блок-схема".

Create source tracking notes for books, articles, videos, papers, courses, films, podcasts, and other reference materials. INVOKE when user wants to track any content source. Triggers: "track book", "add source", "new book", "article", "video", "paper", "course", "film", "podcast", "добавь книгу", "запиши источник", "читаю книгу", "смотрю курс", "добавь статью", "добавь видео", "источник". Handles status, ratings, and scientificity levels.

Manage project task notes in Obsidian vault. INVOKE when user wants to: create, read, find, update a task. Triggers (EN): "create task", "add task to project", "find task", "update task", "take task". Triggers (RU): "создай задачу", "найди задачу", "обнови задачу", "читай задачу", "бери задачу". NOT for inline tasks — use task-inline skill instead.

Create regular knowledge notes in base/notes/. INVOKE whenever user wants to capture or document a concept, topic, or idea. Triggers: "create note", "new note", "note about", "write down", "document this", "запиши", "создай заметку", "новая заметка", "сохрани", "запомни", "заметка про". NOT for projects, sources, people, system notes, or flashcards.

Create notes for people and organizations. INVOKE when user wants to create a note for a person, author, company, or organization. Triggers: "create contact", "add person", "new creator", "company", "organization", "production", "author", "создай контакт", "добавь человека", "новый автор", "добавь компанию", "запиши контакт".

Create and manage project notes. Two types: single and longform. INVOKE when user asks to create or update a project note. Triggers: "create project", "new project", "project note", "update project", "создай проект", "обнови проект", "longform", "chapters", "scenes".

Create supplementary materials attached to existing notes: experiments, meetings, reports, logs, conspectuses, practice sessions, annotations, AI outputs, links collections. Two-step process: (1) create aggregator space, (2) create concrete addition in base/additions/. INVOKE when user wants to attach any supplementary material to an existing note. Triggers: "addition", "create addition", "experiment", "meeting notes", "report", "conspectus", "log", "practice", "annotations", "links", "link collection", "аддишн", "конспект", "встреча", "отчёт", "эксперимент", "практика", "аннотации", "ссылки", "добавь к заметке".

Create and edit Obsidian Bases (.base files) — YAML-based database-like views of notes with table/card/list views, filters, formulas, and summaries. INVOKE when user wants to create or edit a .base file or needs database-like views of vault notes. Triggers: "create base", "base file", "table view", "card view", "filters", "formulas", "database view", "obsidian bases", "создай базу", "база данных заметок", "табличный вид", ".base файл".

Use when building or editing any AI feature in n8n: AI Agents, Text Classifier, Information Extractor, Sentiment Analysis, Summarization Chain, Basic LLM Chain, embeddings, vector stores, single one-shot LLM calls, or AI media generation (image / audio / video) via the native LangChain provider nodes. Triggers on any `@n8n/n8n-nodes-langchain.*` node, "agent", "chat assistant", "LLM with tools", "tool calling", "fromAi", "system prompt", "memory window", "structured output", "outputParser", "function calling", "RAG", "vector store", "embeddings", "classify with AI", "extract fields with LLM", "sentiment analysis", "summarize with LLM", "single LLM call", chat triggers with files, AI image / video / audio generation, or any multi-turn or one-shot LLM behavior.

Use when you want to expose an n8n workflow as a tool the coding agent can call. Two cases. (1) Wrap n8n API capabilities the MCP doesn't natively expose: folder CRUD, tag rename/delete, instance metadata, credential creation. (2) Expose a general-purpose workflow as an agent tool: a workflow that calls a third-party API, runs business logic, or does any task you want the agent to invoke. Triggers on "expose as MCP tool", "build a tool for my agent", "I need to know X" where X isn't an MCP tool, "create folder", "rename tag", or any capability gap.

Use when building anything multi-step, anything that looks repeatable, anything the user mentions reusing, or any workflow with more than ~10 nodes. Triggers on "reuse", "I do this in another workflow", "extract", "modular", "shared logic", "subworkflow", multi-step builds, or any task that mentions logic the user has built before.

Use when starting, designing, organizing, finishing, or shipping an n8n workflow. Covers visual layout (sticky notes), descriptions that capture the *why*, node names, validation, testing, folders/projects, and publishing. Triggers on create_workflow_from_code, update_workflow, validate_workflow, publish_workflow, archive_workflow, "design", "lay out", "organize", "structure", "sticky", "describe this workflow", "ship", "deploy", "publish", "name this workflow", or any folder/project organization request.

Use when working with n8n workflows in any capacity. The always-on protocol for the n8n-skills plugin, loaded by the SessionStart hook every session. Routes to the right skill, summarizes every n8n MCP tool (closing the deferred-description gap), and lists the cross-cutting rules.