1c Meta Info logo

1c Meta Info

Community
comol
1c-meta-info

Facts about 1C metadata objects — passport, typed attributes, tabular-part columns, forms, predefined items, objects by category or Russian description — from the graph and code-metadata MCP. Use before code or metadata that depends on an object's structure, and to find objects by synonym.

Overview

Publishercomol
Repositoryai_rules_1c
Skill name1c-meta-info
Stars
496
Forks
112
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by comol on GitHub. Read the source before you install it.

Installation

Install the 1c Meta Info AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/comol/ai_rules_1c/tree/main/content/skills/1c-meta-info
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/comol/ai_rules_1c.git /tmp/ai_rules_1c
mkdir -p .claude/skills
cp -r /tmp/ai_rules_1c/content/skills/1c-meta-info .claude/skills/1c-meta-info
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 1c Meta Info in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads 1c Meta Info on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so 1c Meta Info is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

1c-meta-info — facts about a metadata object

Facts only; a verdict about an object needs the validators of 1c-validate. Search discipline and freshness — content/rules/mcp-first-search.md.

For each graph call, explicitly pass the returned project_id verified against the current source roots; substitute <resolved-project-id> below. Discover through list_graph_projects using the mcp-1c-tools router first when needed. Keep project scope outside JSON query operations and template arguments. An extension requires verified layer coverage/provenance; neither the first project nor the base-only response is an extension lookup. Code-server selectors use their own live schema and mappings (content/rules/multi-contour-search.md).

Address

Graph object lookups accept qualified names such as Справочник.Контрагенты, Документ.РеализацияТоваровУслуг, РегистрНакопления.ТоварыНаСкладах, ОбщийМодуль.РаботаСКонтрагентами. For Code get_metadata_details, reuse the canonical full_path from metadatasearch, for example Документы.НачислениеЗарплаты; a Graph-style singular prefix may cause a slower live-XML fallback. Both calls name the argument object_name, never full_name or object_full_name. Identity tools have their own arguments (resolve_qualified_name takes qualified_name). Invoke-1CEdit.ps1 -Object uses the singular qualified form.

Tools and exact arguments

NeedCallArguments
Passport of a known objectget_object_dossier (graph)object_name, optional sections as a list of structure, forms, subscriptions, roles, dependencies, code, business_info
Header attributes, properties, predefinedget_metadata_details (code)object_name, sections="attributes,tabular_parts,properties,predefined", detail_level="outline" | "full", max_items, cursor, include_provenance=false
Tabular-part columnsget_metadata_details (code)sections="tabular_parts" or tabular_part="<name>" — current graph generations can include columns; tabular_part_columns_not_indexed on an older/incomplete generation routes here in one step
Objects by category / structuresearch_metadata (graph)query = JSON operation, e.g. {"operation":"list_objects_by_category","category_name":"Документы"}
Object by synonym / descriptionsearch_metadata_by_description (graph)query, top_k=10, filter_type = Russian plural category (Документы, Справочники), use_fuzzy, alpha
Business-meaning searchbusiness_search (graph)query, top_k, filter_type, include_structure — only when list_graph_capabilities shows the lane
Identification fallbackmetadatasearch (code)query, names_only=true, limit=5, object_type
Identityresolve_qualified_name(qualified_name), find_by_guid(guid)—
Cypher templaterun_graph_cypher_templatetemplate_id, arguments.object_name = bare name (Контрагенты), optional arguments.category_name

Calls

json
{"tool": "get_object_dossier", "args": {"project_id": "<resolved-project-id>", "object_name": "Документ.НачислениеЗарплаты", "sections": ["structure", "forms"]}}
{"tool": "get_metadata_details", "args": {"object_name": "Документы.НачислениеЗарплаты", "sections": "tabular_parts", "detail_level": "outline", "max_items": 200}}
{"tool": "search_metadata_by_description", "args": {"project_id": "<resolved-project-id>", "query": "начисление премии сотрудникам", "filter_type": "Документы", "top_k": 5}}
{"tool": "search_metadata", "args": {"project_id": "<resolved-project-id>", "query": "{\"operation\": \"list_attributes_with_type\", \"type_name\": \"СправочникСсылка.Контрагенты\"}"}}
{"tool": "metadatasearch", "args": {"query": "Контрагенты", "names_only": true, "limit": 5}}

Rules

  • Retrieve the smallest projection that answers: names for identification, one section for a field list; never expand a hit into a full dossier without need.
  • Page with cursor until complete before claiming an exhaustive list; an empty page section does not prove absence.
  • Configurations with extensions: when the graph covers the relevant layers, use one discovered base project_id; effective source version via resolve_effective_entity, layer diff via compare_base_and_extension(object_name, extension_name) — 1c-impact. Uncovered contours use their mapped index or own files; scope and evidence boundaries — content/rules/multi-contour-search.md.
  • Typed answers map to actions by code — content/rules/mcp-policy.md → C. Server answers → actions.

Paging contract, JSON operation catalogue, template list: content/skills/mcp-1c-tools/docs/1c-graph-metadata-mcp.md, content/skills/mcp-1c-tools/docs/1c-code-metadata-mcp.md → Reading large metadata objects.

Frequently asked questions

What does the 1c Meta Info AI skill do?

Facts about 1C metadata objects — passport, typed attributes, tabular-part columns, forms, predefined items, objects by category or Russian description — from the graph and code-metadata MCP. Use before code or metadata that depends on an object's structure, and to find objects by synonym.

Why use 1c Meta Info on TypingMind?

Because you install it once and use it with any model. 1c Meta Info is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install 1c Meta Info in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/comol/ai_rules_1c/tree/main/content/skills/1c-meta-info. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use 1c Meta Info?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with 1c Meta Info?

As many as you like. As long as a model supports skills, you can use 1c Meta Info with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the 1c Meta Info AI skill free?

It is published on GitHub by comol. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇