skd-validate

skd-validate is a skill for Claude Code from Nikolay-Shirokov/cc-1c-skills. It costs 38 tokens per session (656 once invoked), scanned A, original, MIT.

A validator for 1C data composition schemas, which define how reports obtain and arrange data. It checks a Template.xml file for structural errors, broken references, and duplicate names.

In plain words
What is it for?
Use it to validate a report schema and optionally produce detailed findings or save the result to a file.
Why use it?
It catches common schema problems after a report definition is created or edited, before the file is used further.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the 1c-skills plugin — 81 skills, 2 hooks shipped together

Good fit Use it to validate a report schema and optionally produce detailed findings or save the result to a file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nikolay-shirokov/cc-1c-skills/skd-validate
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Nikolay-Shirokov/cc-1c-skills --skill skd-validate
Clone the repo
git clone --depth 1 https://github.com/Nikolay-Shirokov/cc-1c-skills

Made for: Claude Code.

Or install 1c-skills, the plugin that ships this one along with the rest of its 81 skills, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skd-validate

README.md
[![agentmods](https://agentmods.dev/badge/skills/nikolay-shirokov/cc-1c-skills/skd-validate/github.svg)](https://agentmods.dev/skills/nikolay-shirokov/cc-1c-skills/skd-validate)
Your own site
<a href="https://agentmods.dev/skills/nikolay-shirokov/cc-1c-skills/skd-validate"><img src="https://agentmods.dev/badge/skills/nikolay-shirokov/cc-1c-skills/skd-validate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skd-validate

Your own site · 80×15
<a href="https://agentmods.dev/skills/nikolay-shirokov/cc-1c-skills/skd-validate"><img src="https://agentmods.dev/badge/skills/nikolay-shirokov/cc-1c-skills/skd-validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 656 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00656
Opus 5.5 $0.00015 $0.00262
Sonnet 5.5 $0.00008 $0.00131
Haiku 4.5 $0.00004 $0.00066

Measured 27d ago against content hash 8a9cbfe1960d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skd-validate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 27d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/skd-validate.ps1, scripts/skd-validate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/skd-validate/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/skd-validate — валидация СКД (DataCompositionSchema)

Проверяет структурную корректность Template.xml схемы компоновки данных. Выявляет ошибки формата, битые ссылки, дубликаты имён.

Параметры

Параметр Обяз. Умолч. Описание
TemplatePath да — Путь к Template.xml или каталогу макета
Detailed нет — Подробный вывод (все проверки, включая успешные)
MaxErrors нет 20 Остановиться после N ошибок
OutFile нет — Записать результат в файл

Команда

powershell.exe -NoProfile -File "${CLAUDE_SKILL_DIR}/scripts/skd-validate.ps1" -TemplatePath "src/МойОтчёт/Templates/ОсновнаяСхема"
powershell.exe -NoProfile -File "${CLAUDE_SKILL_DIR}/scripts/skd-validate.ps1" -TemplatePath "Catalogs/Номенклатура/Templates/СКД/Ext/Template.xml"

Проверка по XSD

Порядок элементов, типы и значения дополнительно сверяются с XSD-схемами платформы, если они скачаны в проект. Иначе итоговая строка заканчивается на XSD not checked: <причина> — это не «проверено всё». Когда проверка нужна (например, платформа пишет «нарушен порядок следования»), скачай схемы версии формата выгрузки — атрибут version в Configuration.xml — через /v8-xsd-fetch -Versions <версия> и запусти снова. То же при [WARN] XSD: no schemas for format <версия>.

Нарушение: XSD <версия>, line N: <родитель>/<элемент>: <что не так>.

  • must come before <X> — перенеси элемент непосредственно перед <X>, содержимое не меняй. duplicate — удали повтор. not allowed in <P> — элементу здесь не место. Иначе — текст о недопустимом значении.
  • [WARN] с (no schemas for <версия>) — сверено по схемам более новой версии: ориентир, не вердикт.
  • Если шаблон ты только что собрал или изменил /skd-compile или /skd-edit, нарушение — дефект навыка: сообщи о нём пользователю.

Read the full file on GitHub · 41 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 27d ago Changed · +11 lines 8a9cbfe1960d
  2. 1mo ago First seen · 30 lines · 38 tokens per session scan A 2ee9ebe859c3

Subscribe to this mod's changes

skd-validate is a skill published in the GitHub repository Nikolay-Shirokov/cc-1c-skills (730 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 656 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.