SKILLEMALL.ai
GitHub ↗ RU Sign in

DC 1c-mcp-toolkit

Прямой HTTP API к живой запущенной базе 1С:Предприятие через обработку MCP_Toolkit.epf (REST на http://localhost:6003/api/*). 12 эндпоинтов: запросы (execute_query), BSL-код (execute_code), метаданные (get_metadata), ссылки и навигация (get_object_by_link, get_link_of_object), поиск ссылок на объект (find_references_to_object), права (get_access_rights), журнал регистрации (get_event_log), справка платформы (get_bsl_syntax_help), управление сессией (restart_1c_session, close_1c_session). EPF и скрипты запуска включены в скилл. Используй когда нужно проверить реальные данные в живой БД, выполнить exploratory-запрос, прямо вызвать экспортную функцию модуля выгрузки, прочитать журнал регистрации, диагностировать данные до или после доработки. Триггеры на русском: "выполни запрос в живой базе", "проверить данные в БД", "сколько записей в", "вызвать функцию модуля 1С", "что в журнале регистрации", "выполни BSL-код в живой 1С", "запусти 1С с MCP-toolkit". Триггеры на английском: "query live 1C database", "execute BSL in 1C", "check 1C data", "explore 1C metadata at runtime".

Desko77/claude-code-skills-1c Agent Skills author: Desko77 MIT 7 files · 3 scripts body ≈ 6 165 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Прямой HTTP API к живой запущенной базе 1С:Предприятие через обработку MCPToolkit.epf (REST на http://localhost:6003/api/). 12 эндпоинтов: запросы…

As a process C 51/100 · Has gaps — References files that are not bundled: bin/MCP_Toolkit.epf, bin/MCP_Toolkit_x86.epf

Integration1CAI and agentsData and analyticstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
D
62/100
safety, quality, tests
Safety 60%
79
Quality 40%
37
Run on models
none yet
Process rating
C
51/100
Has gaps
References files that are not bundled: bin/MCP_Toolkit.epf, bin/MCP_Toolkit_x86.epf
Tools and files w 18
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. Shorten the description to 1024 characters.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  4. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 5

✓ No critical or high findings

Medium and low: 5
  • medium Obfuscation uni-mixed-script-word references/tools-full-reference.md:372
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    `Удалить`, `Delete`, `Записать`, `Write`, `УстановитьПривилегированныйРежим`, `SetPrivilegedMode`, `ПодключитьВнешнююКомпоненту`, `AttachAddIn`, `УстановитьВнеш…
  • medium Obfuscation uni-mixed-script-word scripts/start-1c.ps1:158
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (2 occurrences)
    # params.json: формат из обработки (ПрочитатьJSON2 в ПриОткрытии).
  • medium Dangerous commands cmd-execpolicy-bypass SKILL.md:79
    Runs PowerShell with execution policy bypassed
    > '/c/Program Files/PowerShell/7/pwsh.exe' -NoProfile -ExecutionPolicy Bypass -Command '& "$HOME\.claude\skills\1c-m…kit\scripts\star…ps1" -Platform "8.3.27.2074" -Database "..." -User "..."
  • medium Obfuscation uni-mixed-script-word SKILL.md:370
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    `COMОбъект`, `УдалитьФайлы` и др. Список настраивается в обработке. Для тестов на
  • low Dangerous commands cmd-execpolicy-bypass references/tools-full-reference.md:1007
    Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)
    "data": "Session closed. To start a new session, run:\npowershell -ExecutionPolicy Bypass -File 'C:\\path\\to\\laun…ps1'\nRun synchronously. Exit 0 = session ready. Non-zero = startup failed. On W
    quoted

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1086 chars, limit 1024
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 6165 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: bin/MCP_Toolkit.epf
  • warning missing-ref reference to a missing file: bin/MCP_Toolkit_x86.epf

Process rating: all ten parameters 51/100

Will not run. References files that are not bundled: bin/MCP_Toolkit.epf, bin/MCP_Toolkit_x86.epf
  • 0Tools and files. 2 referenced file(s) missing: bin/MCP_Toolkit.epf, bin/MCP_Toolkit_x86.epf
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 4 mutating operations with no state check
  • 60Result and completion. Output format stated, no completion criterion
  • 60Failures and branches. 2 branches
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 6165 tokens
  • 85Steps. 39 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 18 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1085: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +5Description quotes 11 example trigger phrases
  • +4Structure: 42 headings
  • +3Step-by-step instructions: 39 items
  • +4Has examples (25 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +3All 3 scripts are documented
  • +2Bilingual instructions (RU + EN)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 37.