Agent skill

Edt MCP Bilingual

by DitriXNew in DitriXNew/EDT-MCP

Correctness checklist for 1C's bilingual (Russian/English) model in EDT-MCP — synonym language-code vs name, object resolution by Name vs synonym vs TYPE token, dialect-aware vs literal code search.

AGPL-3.0Auto-check passedWriting & Content

Install Edt MCP Bilingual

skills CLI
$ npx skills add DitriXNew/EDT-MCP --skill edt-mcp-bilingual -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install DitriXNew/EDT-MCP edt-mcp-bilingual --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/DitriXNew/EDT-MCP.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/edt-mcp-bilingual .claude/skills/edt-mcp-bilingual && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
edt-mcp-bilingual
GitHub stars
296
Token cost
~850 tokens
SKILL.md length
366 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Correctness checklist for 1C's bilingual (Russian/English) model in EDT-MCP — synonym language-code vs name, object resolution by Name vs synonym vs TYPE token, dialect-aware vs literal code search.

  • Works in 5 steps: The metadata synonym is keyed by the… → An object resolves by its programmatic… → Writing a synonym — symmetric, through… → …
  • Searching metadata objects
  • SKILL.md covers 1. The metadata synonym is…, 2. An object resolves by its…, 3. Writing a synonym —… and 4. BSL: ru/en dialects, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Edt MCP Bilingual is an agent skill from DitriXNew/EDT-MCP. Correctness checklist for 1C's bilingual (Russian/English) model in EDT-MCP — synonym language-code vs name, object resolution by Name vs synonym vs TYPE token, dialect-aware vs literal code search. Use when reading, writing, resolving, formatting or searching metadata objects, synonyms, BSL identifiers or query keywords.

Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Translation, Codebase onboarding and MCP servers. It works with Model Context Protocol. The licence is AGPL-3.0.

When your agent uses it

  • Searching metadata objects
  • BSL identifiers

Example prompts

  • “/edt-mcp-bilingual”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. The metadata synonym is keyed by the language CODE
  2. An object resolves by its programmatic Name; the TYPE token is bilingual
  3. Writing a synonym — symmetric, through the shared resolver
  4. BSL: ru/en dialects
  5. 1C queries are bilingual

What it can do on your machine

Read from SKILL.md and the folder at commit 6d18531. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Edt MCP Bilingual loads about 850 tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 366 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~850

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from DitriXNew/EDT-MCP at commit 6d18531, republished under its AGPL-3.0 licence (© DitriXNew). 366 words, ~850 tokens.

Download SKILL.mdSave it as .claude/skills/edt-mcp-bilingual/SKILL.md (or your agent's skills folder).
name
edt-mcp-bilingual
description
Correctness checklist for 1C's bilingual (Russian/English) model in EDT-MCP — synonym language-code vs name, object resolution by Name vs synonym vs TYPE token, dialect-aware vs literal code search. Use when reading, writing, resolving, formatting or searching metadata objects, synonyms, BSL identifiers or query keywords.

EDT-MCP — two-language (ru/en) correctness

1C is bilingual at several layers, and most plugin bugs live here. Before editing any tool that resolves/reads/writes/searches metadata or code, walk this checklist.

1. The metadata synonym is keyed by the language CODE

The synonym is an EMap<String,String> whose key is the language code ("ru", "en"), NOT the Language object's name.

  • ✅ Write/read through MetadataLanguageUtils: resolveLanguageCode(config, explicit) and getSynonymForLanguage(map, code).
  • ✅ Reference language-resolution logic: CreateMetadataObjectTool.resolveLanguage — explicit → getDefaultLanguage().getLanguageCode() → the first language's code → null.
  • ❌ NOT config.getDefaultLanguage().getName() (returns "Russian"/"Русский" — the name, not the key; on a multi-language config it silently misses the EMap).
  • ❌ Don't hardcode "ru" as the fallback — use the first configured language's code.

2. An object resolves by its programmatic Name; the TYPE token is bilingual

  • The object name (the segment after the type) is a programmatic identifier, resolved by getName() (see MetadataTypeUtils.findObject). A synonym is NOT accepted as an identifier.
  • The TYPE token (Справочник/Catalog, Документ/Document …) is bilingual, handled by MetadataTypeUtils (toEnglishSingular, normalizeFqn, getAllFqnVariants).
  • Say it honestly in the schema description: "only the TYPE token may be Russian/English; the object name is a programmatic identifier, not a synonym." Don't mislead with "Russian names supported".

3. Writing a synonym — symmetric, through the shared resolver

  • When creating an object/attribute, if a synonym is given, write getSynonym().put(resolveLanguageCode(...), synonym).
  • A write tool must return the written synonym+language in its response (symmetry with read tools).
Show full SKILL.md (144 more words)Show less

4. BSL: ru/en dialects

  • AST/index tools (find_references, get_symbol_info, go_to_definition, call_hierarchy) are dialect-aware — they resolve by symbol name with equalsIgnoreCase, no normalization needed.
  • search_in_code is a literal matcher, NOT dialect-aware: searching an English keyword won't find its Russian equivalent. Reflect this honestly in the tool description; for identifier search, direct the user to the AST tools.
  • Cyrillic in regexes — escape via \uXXXX (as in BslSyntaxChecker), not raw UTF-8 literals (corruption risk under a non-UTF-8 build).

5. 1C queries are bilingual

Query keywords have ru/en dialects (SELECT/ВЫБРАТЬ, FROM/ИЗ, WHERE/ГДЕ). validate_query delegates to the platform parser (dialect-aware) — don't assume a single dialect; keep UTF-8 when passing query text.

Test invariant

Any change to resolution/reading/writing must have a test covering both languages: one object addressed by its English Name, Russian Name, and (where applicable) synonym — identical result; the synonym keyed by language code, not by name. Reference: WriteModuleSourceToolTest.testResolveRussianObjectName.

© DitriXNew, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/edt-mcp-bilingual of DitriXNew/EDT-MCP.

Open the folder on GitHubat commit 6d18531

Compare with similar skills

Edt MCP Bilingual next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Edt MCP Bilingual compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Edt MCP Bilingual this skillDitriXNew/EDT-MCP296—~850Automated safety check: PassAGPL-3.0
Ainiee Next TranslationShadowLoveElysia/AiNiee-Next176—~3.3kAutomated safety check: PassAGPL-3.0
Add Tauri Commandopenfootmanager/openfootmanager1.1k—~1.6kAutomated safety check: PassGPL-3.0
Gearcoleco Romhackingdrhelius/Gearcoleco142—~3.9kAutomated safety check: PassGPL-3.0
CodegraphcontextCodeGraphContext/CodeGraphContext4.3k—~675Automated safety check: NotesMIT
Extension Puppeteer Debuggingmengxi-ream/read-frog10k—~2kAutomated safety check: NotesGPL-3.0

Similar skills

  • Ainiee Next Translation

    ShadowLoveElysia/AiNiee-Next

    在用户要求翻译小说、文档、字幕或其他文件内容时,按 AiNiee-Next 的输入优先、长文本询问和 MCP 边界执行;进入 AiNiee 工作流后,原文获取与术语预分析也必须走受控读取工具,禁止自行解包解析。

    176 GitHub stars~3.3k tokensUpdated 13 days ago
    Writing & ContentAuto-check passed
  • Add Tauri Command

    openfootmanager/openfootmanager

    Expose new backend behaviour to the frontend over Tauri IPC.

    1.1k GitHub stars~1.6k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Gearcoleco Romhacking

    drhelius/Gearcoleco

    Hack, modify, and translate ColecoVision and Super Game Module ROMs using the Gearcoleco emulator MCP server.

    142 GitHub stars~3.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Codegraphcontext

    CodeGraphContext/CodeGraphContext

    Use CodeGraphContext (CGC) to index a repo into a graph DB and query it via CLI or MCP.

    4.3k GitHub stars~675 tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Extension Puppeteer Debugging

    mengxi-ream/read-frog

    Debug the built Read Frog extension in real Chrome. An agent skill from mengxi-ream/read-frog.

    10k GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • China Travel Kit

    tczyliu/china-travel-kit

    Research and plan first-time independent trips in China with bilingual, source-aware city data and official live-check entry points.

    194 GitHub stars~1.3k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

More from DitriXNew/EDT-MCP

All 24 skills in this repo
  • Edt MCP Autopilot

    DitriXNew/EDT-MCP

    Autonomous, spec-driven, multi-agent pipeline that takes an EDT-MCP task or issue end-to-end — research → critics → architect → parallel development → review loop → tests → live-stand check →…

    296 GitHub stars~2.5k tokensUpdated 3 days ago
    Auto-check passed
  • Edt MCP Build Test

    DitriXNew/EDT-MCP

    How to build the EDT-MCP Eclipse plugin (Tycho/Maven) and run its unit and e2e tests, plus the test conventions for this repo.

    296 GitHub stars~1.4k tokensUpdated 3 days ago
    Auto-check passed
  • Edt MCP E2E Testing

    DitriXNew/EDT-MCP

    How to write/run the AUTOMATED black-box e2e suite (tests/e2e/) that covers every EDT-MCP tool (62 today) against a live server with git-fixture isolation, happy + negative + error-quality coverage…

    296 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed
  • Edt MCP Tool Descriptions

    DitriXNew/EDT-MCP

    How to size, write and A/B-test the text of a tool — its description and its inputSchema parameter prose — so that cutting it does not cost call quality, and so that a tool that IS getting called…

    296 GitHub stars~3k tokensUpdated 3 days ago
    Auto-check passed
  • Edt MCP Yaxunit

    DitriXNew/EDT-MCP

    How to write and run YAXUnit unit tests for a 1C configuration through 1C:EDT + the EDT-MCP runyaxunittests / debugyaxunittests tools.

    296 GitHub stars~2.5k tokensUpdated 3 days ago
    Auto-check passed
  • Edt MCP Testing

    DitriXNew/EDT-MCP

    How to manually e2e-test each EDT-MCP server tool against a live EDT workbench + TestConfiguration.

    296 GitHub stars~2.1k tokensUpdated 3 days ago
    Auto-check passed

Questions about Edt MCP Bilingual

What does Edt MCP Bilingual do?

Correctness checklist for 1C's bilingual (Russian/English) model in EDT-MCP — synonym language-code vs name, object resolution by Name vs synonym vs TYPE token, dialect-aware vs literal code search. Edt MCP Bilingual is an agent skill from DitriXNew/EDT-MCP. Correctness checklist for 1C's bilingual (Russian/English) model in EDT-MCP — synonym language-code vs name, object resolution by Name vs synonym vs TYPE token, dialect-aware vs literal code search.

When should I use Edt MCP Bilingual?

Edt MCP Bilingual fits situations like: searching metadata objects; BSL identifiers.

How do I install Edt MCP Bilingual in Claude Code?

Run `npx skills add DitriXNew/EDT-MCP --skill edt-mcp-bilingual -a claude-code`. Or copy the skill folder (.claude/skills/edt-mcp-bilingual in DitriXNew/EDT-MCP) into .claude/skills/edt-mcp-bilingual in your project. Claude Code loads it when a task matches its description.

How do I install Edt MCP Bilingual in Codex?

Run `npx skills add DitriXNew/EDT-MCP --skill edt-mcp-bilingual -a codex`. Or copy the skill folder (.claude/skills/edt-mcp-bilingual in DitriXNew/EDT-MCP) into .agents/skills/edt-mcp-bilingual in your project. Codex loads it when a task matches its description.

Can I use Edt MCP Bilingual in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DitriXNew/EDT-MCP --skill edt-mcp-bilingual -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/edt-mcp-bilingual, .gemini/skills/edt-mcp-bilingual, .github/skills/edt-mcp-bilingual and .opencode/skills/edt-mcp-bilingual in your project.

What does Edt MCP Bilingual need to run?

SKILL.md names no scripts, command-line tools or credentials: Edt MCP Bilingual is instructions for the agent only.

Does Edt MCP Bilingual access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Edt MCP Bilingual safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Edt MCP Bilingual use?

Edt MCP Bilingual is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Edt MCP Bilingual use?

About 850 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Edt MCP Bilingual?

Skills that share tags, products or a category with Edt MCP Bilingual: Ainiee Next Translation (ShadowLoveElysia/AiNiee-Next, 176 stars), Add Tauri Command (openfootmanager/openfootmanager, 1.1k stars), Gearcoleco Romhacking (drhelius/Gearcoleco, 142 stars) and Codegraphcontext (CodeGraphContext/CodeGraphContext, 4.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Edt MCP Bilingual?

DitriXNew (a GitHub user) maintains it in DitriXNew/EDT-MCP, which has 296 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 7, 2026.

Source: DitriXNew/EDT-MCP on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.