SKILLEMALL.ai
GitHub ↗ RU Sign in

DD 1c-code-review

Ревью BSL-кода по каталогу дефектов: каждая находка получает идентификатор карточки, важность и ключ локации. Триггеры: ревью BSL, проверь код по антипаттернам, code review 1С, проверь код перед коммитом, а также вызов из команды закрытия задачи.

Desko77/claude-code-skills-1c Agent Skills author: Desko77 MIT 80 files body ≈ 797 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Ревью BSL-кода по каталогу дефектов: каждая находка получает идентификатор карточки, важность и ключ локации.

As a process D 35/100 · Unfinished process — References files that are not bundled: references/catalog/<ИДЕНТИФИКАТОР>.md, references/report-format.md, references/severity.md

AnalyzerSoftware developmenttype 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
65/100
safety, quality, tests
Safety 60%
70
Quality 40%
58
Run on models
none yet
Process rating
D
35/100
Unfinished process
References files that are not bundled: references/catalog/<ИДЕНТИФИКАТОР>.md, references/report-format.md, references/severity.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
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.

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. The text references files that are not there: add them or drop the references.
For the model run — optional
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 6

✓ No critical or high findings

Medium and low: 6
  • medium Obfuscation uni-mixed-script-word references/catalog/CLIENT-05.md:14
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (2 occurrences)
    В клиентском коде вызван синхронный или модальный метод: Вопрос, Предупреждение, ОткрытьЗначение, семейство Ввести, синхронные методы HTTPСоединения - либо опер…
  • medium Obfuscation uni-mixed-script-word references/catalog/INDEX.md:14
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (7 occurrences)
    | CLIENT-05 | Major | CLIENT | модуль формы, любой BSL | EDT: ask_1c_ai, чтение; Конфигуратор: bsl_…-05 | В клиентском коде вызван синхронный или …
  • medium Obfuscation uni-mixed-script-word references/catalog/ledger.json:91
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (2 occurrences)
    "title": "Присваивание свойству ПараметрыЗаписиJSON"
  • medium Obfuscation uni-mixed-script-word references/catalog/MODEL-08.md:1
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (7 occurrences)
    # MODEL-08. Присваивание свойству ПараметрыЗаписиJSON
  • medium Obfuscation uni-mixed-script-word references/catalog/PERF-08.md:14
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (9 occurrences)
    Создается соединение с внешним ресурсом - HTTPСоединение, FTPСоединение, WSОпределения, WSПрокси, ИнтернетПочтовыйПрофиль - или вызывается ожидание завершения ф…
  • medium Obfuscation uni-mixed-script-word references/catalog/QUERY-12.md:1
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (6 occurrences)
    # QUERY-12. Поля внешнего соединения без ЕСТЬNULL

Files scanned: 79. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/catalog/<ИДЕНТИФИКАТОР>.md
  • warning missing-ref reference to a missing file: references/report-format.md
  • warning missing-ref reference to a missing file: references/severity.md
  • warning missing-ref reference to a missing file: references/detectors.md

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: references/catalog/<ИДЕНТИФИКАТОР>.md, references/report-format.md, references/severity.md
  • 0Tools and files. 4 referenced file(s) missing: references/catalog/<ИДЕНТИФИКАТОР>.md, references/report-format.md, references/severity.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 100Steps. 7 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 797 tokens
  • 100Running it twice. No mutating operations
  • low No test case covers injection arriving through data

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +3Description length 246: enough signal without eating the budget
  • +4Structure: 3 headings
  • +3Step-by-step instructions: 7 items
  • +2Bilingual instructions (RU + EN)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.