ai_rules_1c

1C metadata management — create, edit, validate, and remove configuration objects (catalogs, documents, registers, enums), managed forms, data composition schemas (SKD), spreadsheet layouts (MXL), roles, external processors (EPF/ERF), extensions (CFE), configurations (CF), databases, subsystems, command interfaces, templates. Use when working with 1C metadata structure.

Catalog of MCP servers for 1C development — search, code navigation, metadata, code review, docs, ITS, templates. Use whenever a 1C task requires calling tools from any 1c-*-mcp / 1C-*-mcp server. Each server has its own detail file under `docs/` — load it when you are about to call tools from that server, and only if the server is actually available in the current session.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.

Ultra-compressed communication mode for development tasks. Cuts output tokens ~65–75% by using a terse "caveman" style while keeping full technical accuracy. Active by default for development tasks (writing / editing / refactoring code, fixing bugs, deploying, running shell). Auto-off for analysis, documentation, review and audit tasks (PRDs, specs, code reviews, architecture reviews, rule reviews, summaries, explanations). Force-on with "caveman", "как пещерный", "use caveman", "be brief", "коротко", `/caveman`. Force-off with "stop caveman" / "normal mode" / "обычный режим". Levels: `lite` / `full` (default) / `ultra`.

Compact the current conversation into a self-contained handoff document so a fresh agent (new chat, another machine, another AI client) can continue the work without re-discovering the context. References durable artifacts (`openspec/`, `memory.md`, commits, `1c-templates-mcp` notes) instead of duplicating them. Use when the user says 'handoff', 'compact session', 'save context for continuation', or invokes `/handoff`.

Overlay a numbered grid on an image to determine column proportions for layout generation. Use when creating MXL spreadsheet layouts from screenshots or scanned print forms.

Convert a Markdown file to DOCX (Word). Use when the user asks to convert .md to .docx, generate a Word document from Markdown, or export Markdown notes to Word.

Improve and structure short, unstructured prompts and task statements, turning them into detailed imperative specifications with numbered analysis steps, explicit edge cases, and a clearly described expected output format. Preserves all terms and conditions from the source, does not add new requirements. Use when the user asks to: improve a prompt, refine a task statement, expand a task description, structure a spec, turn a note into a detailed instruction, make a prompt more precise or detailed, prepare a spec from a draft, polish a task, convert a short note into a clear specification. Accepts text as a command argument or a path to a .md file.

Transcribe video and audio files via Gemini API. Use when the user asks to transcribe a recording, generate a meeting summary, extract speech from video or audio, or convert speech to text. Supports mp4, mkv, webm, avi, mov, mp3, wav, ogg, m4a, flac.

Practical guide for creating human-readable and agent-parseable diagrams using Mermaid. Includes conservative, renderer-compatible templates and when-to-use guidance.

PowerShell scripting rules for Windows environment. Use when running shell commands, Docker operations, or HTTP requests on Windows PowerShell.