1c Impact logo

1c Impact

Community
comol
1c-impact

Usages, dependencies, call chains and change impact of 1C objects and routines — callers, downstream breakage, register movements, extension changes — via the graph MCP with code-metadata fallback. Mandatory before renames, removals, refactoring and public-contract changes (Gate 4).

Overview

Publishercomol
Repositoryai_rules_1c
Skill name1c-impact
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 Impact 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-impact
  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-impact .claude/skills/1c-impact
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 1c Impact 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 Impact 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 Impact 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-impact — usages, call graph, change impact

Evidence for content/rules/verification-gates.md → Gate 4 and for the pre-refactor analysis of content/rules/tooling-playbooks.md → Refactoring. Refactoring blind when these servers are exposed is a defect; when they are not, follow Gate 4 graceful degradation.

All graph project-data calls require the explicit returned project_id bound to the current roots; substitute <resolved-project-id> in the examples. Reuse it for searches, impact, evidence and pagination, with verified layer provenance for an extension. Follow the live schema for tools without this selector and for code-server scope; use verified fixed/session/entity scope or another scoped route, never invent arguments (content/rules/multi-contour-search.md).

Tools and exact arguments

NeedCall (graph first)Fallback (code)
What breaks if the object changestrace_impact(object_name, direction="downstream", depth=3, relationship_types?)graph_dependencies(object_name, direction="both" | "forward" | "reverse", limit=50)
Who calls / what is calledtrace_call_chain(routine_name, object_name?, direction="callers" | "callees", depth=3)get_method_call_hierarchy(method_name, direction="both", depth=3)
Attributes that reference an objectfind_usages_of_object(object_name)graph_dependencies(..., direction="reverse")
Objects that use a typefind_objects_using_object(object_name)same
Documents declaring movements into a registerfind_register_movement_docs(register_name) or get_register_writers(register, direction="incoming")codesearch(query="Движения.<Регистр>") (source evidence only)
Direct BSL access / targets shared by several objectsfind_object_referrers(object_name?, access?, min_referrers=1); access="read" / "write", omit for bothBounded codesearch then scoped native source search
Release-level transitive impactaffected_subgraph(roots, max_depth?, direction?, edge_types?) with entity references from resolve_graph_entity—

Object/call tools use object_name, routine_name, register_name, method_name; get_register_writers instead uses register / document. Do not invent aliases. Recorder movements and direct BSL access are separate relations: an independent register can have no recorders but still have BSL writers. find_object_referrers proves static access with file/line evidence; a record-set factory is write intent, not proof of a committed write.

Calls

json
{"tool": "trace_impact", "args": {"project_id": "<resolved-project-id>", "object_name": "РегистрНакопления.ТоварыНаСкладах", "direction": "downstream", "depth": 3}}
{"tool": "trace_call_chain", "args": {"project_id": "<resolved-project-id>", "routine_name": "ПровестиДокумент", "object_name": "ОбщийМодуль.ПроведениеСервер", "direction": "callers", "depth": 3}}
{"tool": "find_usages_of_object", "args": {"project_id": "<resolved-project-id>", "object_name": "Справочник.Контрагенты"}}
{"tool": "find_register_movement_docs", "args": {"project_id": "<resolved-project-id>", "register_name": "РегистрНакопления.ТоварыНаСкладах"}}
{"tool": "get_method_call_hierarchy", "args": {"method_name": "ПровестиДокумент", "direction": "callers", "depth": 3}}
{"tool": "find_object_referrers", "args": {"project_id": "<resolved-project-id>", "object_name": "РегистрСведений.ПлановыеЕжегодныеОтпуска", "access": "write", "min_referrers": 1}}
{"tool": "affected_subgraph", "args": {"project_id": "<resolved-project-id>", "roots": ["РегистрНакопления.ТоварыНаСкладах"], "max_depth": 2, "direction": "downstream"}}

Configurations with extensions

When the graph covers the relevant base/extension layers: list_graph_projects, match the current roots, keep the base project_id, and never register extensions as projects. Repeat discovery only when workspace/server context changes or the mapping becomes invalid. Effective implementation in that index — resolve_effective_entity(project_id, object_name, entity_kind="MetadataObject", entity_name?); what one indexed extension changed — compare_base_and_extension(project_id, object_name, extension_name). Keep the base and extension comparison inside that same project. Neither a plain hit nor an indexed effective view alone proves what runs in a named infobase.

For separate indexes or missing graph layers, use each contour's mapped code tools or own files. Account for base, primary, secondary and relevant infrastructure contours before project-wide impact/absence claims; disclose missing coverage. Routing and runtime-evidence boundaries — content/rules/multi-contour-search.md.

Rules

  • Read truncated, exhaustive (including data.exhaustive), degraded and warnings; an exhaustive claim needs a complete page set, verified scope and current sources. source_refresh.drift invalidates a Graph freshness claim even when tasks are completed; removed metadata/forms can survive an incremental refresh. See the graph catalog's refresh boundaries before relying on an old hit or requesting maintenance.
  • Callers of a public Экспорт routine are a promotion trigger (content/rules/verification-policy.md); the caller list belongs in the delivery evidence.
  • Typed answers map to actions by code — content/rules/mcp-policy.md → C. Server answers → actions.

Evidence-first tools (find_graph_path, explain_graph_evidence, compare_graph_scope), domain relations (rights, subscriptions, DCS lineage): content/skills/mcp-1c-tools/docs/1c-graph-metadata-mcp.md.

Frequently asked questions

What does the 1c Impact AI skill do?

Usages, dependencies, call chains and change impact of 1C objects and routines — callers, downstream breakage, register movements, extension changes — via the graph MCP with code-metadata fallback. Mandatory before renames, removals, refactoring and public-contract changes (Gate 4).

Why use 1c Impact on TypingMind?

Because you install it once and use it with any model. 1c Impact 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 Impact in TypingMind?

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

Which AI models can use 1c Impact?

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 Impact?

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

Is the 1c Impact 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 👇