Agent skill

Role Validate

by Nikolay-Shirokov in Nikolay-Shirokov/cc-1c-skills

Валидация роли 1С. An agent skill from Nikolay-Shirokov/cc-1c-skills.

MITAuto-check: notes

Install Role Validate

skills CLI
$ npx skills add Nikolay-Shirokov/cc-1c-skills --skill role-validate -a claude-code

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

GitHub CLI
$ gh skill install Nikolay-Shirokov/cc-1c-skills role-validate --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/Nikolay-Shirokov/cc-1c-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/role-validate .claude/skills/role-validate && 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
role-validate
GitHub stars
671
Token cost
~470 tokens
SKILL.md length
165 words
Files
3 (incl. scripts)
Skills in repo
81
Repo updated
First seen
Licence
MIT

At a glance

Валидация роли 1С. An agent skill from Nikolay-Shirokov/cc-1c-skills.

  • SKILL.md covers Параметры, Команда and Что считается ошибкой
  • Runs PowerShell and Python scripts from its folder

What it does

Role Validate is an agent skill from Nikolay-Shirokov/cc-1c-skills. Валидация роли 1С. Используй после создания или модификации роли для проверки корректности

Its SKILL.md is about 470 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/role-validate.py`).

The repository describes itself as: Набор навыков для AI(ИИ)-агентов (Claude Code, Cursor, Codex и др.), помогающий охватить полный цикл разработки на платформе 1С:Предприятие 8.3. Даёт модели абстракции над… The licence is MIT.

Example prompts

  • “/role-validate”

Requirements

  • Python 3
  • PowerShell
  • Pre-approved tools (allowed-tools): Bash, Read

What it can do on your machine

Read from SKILL.md and the folder at commit 1fa205b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (PowerShell and Python), which the agent can run.

    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

Role Validate loads about 470 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 165 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~470

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read

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); the scripts in this folder are not scanned.

SKILL.md

The full file from Nikolay-Shirokov/cc-1c-skills at commit 1fa205b, republished under its MIT licence (© Nikolay-Shirokov). 165 words, ~470 tokens.

Download SKILL.mdSave it as .claude/skills/role-validate/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
role-validate
description
Валидация роли 1С. Используй после создания или модификации роли для проверки корректности
allowed-tools
Bash, Read
argument-hint
<RightsPath> [-Detailed] [-MaxErrors 30]

/role-validate — валидация роли 1С

Проверяет корректность Rights.xml роли: формат XML, namespace, глобальные флаги, типы объектов, имена прав, RLS-ограничения, шаблоны. Опционально проверяет метаданные роли (UUID, имя, синоним).

Параметры

ПараметрОбяз.Умолч.Описание
RightsPathда—Путь к роли (директория или Rights.xml)
Detailedнет—Подробный вывод (все проверки, включая успешные)
MaxErrorsнет30Макс. ошибок до остановки (по умолчанию 30)
OutFileнет—Записать результат в файл (UTF-8 BOM)

Команда

powershell
powershell.exe -NoProfile -File "${CLAUDE_SKILL_DIR}/scripts/role-validate.ps1" -RightsPath "Roles/МояРоль"

Что считается ошибкой

Ошибка (код возврата 1), а не предупреждение:

  • тип объекта, не имеющий прав в ролях (Enum, CommonModule, CommonPicture, ScheduledJob и т.п.) — конфигурация с блоком прав на перечисление не загружается в базу, конфигуратор зависает без сообщений;
  • незнакомый тип объекта (опечатка);
  • имя права, которого у этого типа нет;
  • вид вложенности, невозможный у данного типа, и недопустимое право у вложенного объекта;
  • право на сервис целиком (HTTPService.Имя и т.п.) — платформа проверяет вложенный объект (метод шаблона URL, операцию, канал), а роль с правом на корень молча не работает: маршруты отвечают 403 Недостаточно прав.

Полные списки «тип → права» и виды вложенности — в role-compile/dsl-reference.md.

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

Files

SKILL.md and 2 other files (scripts) in .claude/skills/role-validate of Nikolay-Shirokov/cc-1c-skills.

  • SKILL.md
  • scripts/role-validate.ps1
  • scripts/role-validate.py

Open the folder on GitHubat commit 1fa205b

Compare with similar skills

Role Validate 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.

Role Validate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Role Validate this skillNikolay-Shirokov/cc-1c-skills671—~470Automated safety check: NotesMIT
Aria Rolesthedaviddias/Front-End-Checklist74k—~515Automated safety check: PassMIT
Azure Role Selectorgithub/awesome-copilot40k2 repos~246Automated safety check: PassMIT
Aria Deprecated Rolethedaviddias/Front-End-Checklist74k—~441Automated safety check: PassMIT
OMP Sub-Agent Role Presetsagentscope-ai/QwenPaw36k—~1.1kAutomated safety check: PassApache-2.0
Building Role Mining For Rbac Optimizationmukul975/Anthropic-Cybersecurity-Skills34k—~2.6kAutomated safety check: PassApache-2.0

Similar skills

  • Aria Roles

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Use valid ARIA role values.

    74k GitHub stars~515 tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed
  • Azure Role Selector

    github/awesome-copilot

    Official

    When user is asking for guidance for which role to assign to an identity given desired permissions, this agent helps them understand the role that will meet the requirements with least privilege…

    40k GitHub starsUsed in 2 repos~246 tokens
    DevOps & CloudAuto-check passed
  • Aria Deprecated Role

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Avoid using deprecated ARIA roles.

    74k GitHub stars~441 tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed
  • OMP Sub-Agent Role Presets

    agentscope-ai/QwenPaw

    Gives the allowed_tools and skills preset for each OMP sub-agent role, to apply when calling spawn_subagent.

    36k GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Building Role Mining For Rbac Optimization

    mukul975/Anthropic-Cybersecurity-Skills

    Apply bottom-up and top-down role mining techniques, including clustering algorithms and formal concept analysis, to discover optimal RBAC roles from existing user-permission assignments…

    34k GitHub stars~2.6k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Securing AWS Lambda Execution Roles

    mukul975/Anthropic-Cybersecurity-Skills

    Hardens AWS Lambda execution roles by writing least-privilege IAM policies, applying permission boundaries, restricting resource-based policies, validating permissions with IAM Access Analyzer, and…

    34k GitHub stars~3.3k tokensUpdated 1 mo ago
    SecurityAuto-check passed

More from Nikolay-Shirokov/cc-1c-skills

All 81 skills in this repo
  • DB Repo

    Nikolay-Shirokov/cc-1c-skills

    Работа с хранилищем конфигурации 1С. An agent skill from Nikolay-Shirokov/cc-1c-skills.

    671 GitHub stars~2.4k tokensUpdated 4 days ago
    Auto-check: notes
  • Form Compile

    Nikolay-Shirokov/cc-1c-skills

    Компиляция управляемой формы 1С из JSON-определения или из метаданных объекта.

    671 GitHub stars~4.5k tokensUpdated 4 days ago
    Auto-check: notes
  • Cf Edit

    Nikolay-Shirokov/cc-1c-skills

    Точечное редактирование конфигурации 1С. An agent skill from Nikolay-Shirokov/cc-1c-skills.

    671 GitHub starsUsed in 1 repo~706 tokens
    Auto-check: notes
  • Form Edit

    Nikolay-Shirokov/cc-1c-skills

    Правка существующей управляемой формы 1С — элементы, реквизиты, команды и свойства самой формы.

    671 GitHub stars~2.9k tokensUpdated 4 days ago
    Auto-check: notes
  • Cf Init

    Nikolay-Shirokov/cc-1c-skills

    Создать пустую конфигурацию 1С (scaffold XML-исходников). An agent skill from Nikolay-Shirokov/cc-1c-skills.

    671 GitHub starsUsed in 1 repo~603 tokens
    Auto-check: notes
  • Cfe Init

    Nikolay-Shirokov/cc-1c-skills

    Создать расширение конфигурации 1С (CFE) — scaffold XML-исходников.

    671 GitHub starsUsed in 1 repo~717 tokens
    Auto-check: notes

Questions about Role Validate

What does Role Validate do?

Валидация роли 1С. An agent skill from Nikolay-Shirokov/cc-1c-skills. Role Validate is an agent skill from Nikolay-Shirokov/cc-1c-skills. Валидация роли 1С.

How do I install Role Validate in Claude Code?

Run `npx skills add Nikolay-Shirokov/cc-1c-skills --skill role-validate -a claude-code`. Or copy the skill folder (.claude/skills/role-validate in Nikolay-Shirokov/cc-1c-skills) into .claude/skills/role-validate in your project. Claude Code loads it when a task matches its description.

How do I install Role Validate in Codex?

Run `npx skills add Nikolay-Shirokov/cc-1c-skills --skill role-validate -a codex`. Or copy the skill folder (.claude/skills/role-validate in Nikolay-Shirokov/cc-1c-skills) into .agents/skills/role-validate in your project. Codex loads it when a task matches its description.

Can I use Role Validate 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 Nikolay-Shirokov/cc-1c-skills --skill role-validate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/role-validate, .gemini/skills/role-validate, .github/skills/role-validate and .opencode/skills/role-validate in your project.

What does Role Validate need to run?

Going by SKILL.md and its folder, Role Validate needs PowerShell and Python for the scripts in its folder. Our summary lists: Python 3; PowerShell. Its frontmatter pre-approves these tools: Bash, Read.

Does Role Validate 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 Role Validate safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Role Validate use?

Role Validate is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Role Validate use?

About 470 tokens (SKILL.md is roughly 1.9k 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 Role Validate?

Skills that share tags, products or a category with Role Validate: Aria Roles (thedaviddias/Front-End-Checklist, 74k stars), Azure Role Selector (github/awesome-copilot, 40k stars), Aria Deprecated Role (thedaviddias/Front-End-Checklist, 74k stars) and OMP Sub-Agent Role Presets (agentscope-ai/QwenPaw, 36k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Role Validate?

Nikolay-Shirokov (a GitHub user) maintains it in Nikolay-Shirokov/cc-1c-skills, which has 671 GitHub stars. The repository holds 81 skills in this directory. The repository was last updated on October 5, 2026.

Source: Nikolay-Shirokov/cc-1c-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.