Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
Этот скилл MUST быть вызван когда пользователь просит проверить или протестировать 1С через браузер в интерактивном режиме (быстрые ручные проверки).
$ npx skills add Arman-Kudaibergenov/1c-ai-development-kit --skill web-test -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Arman-Kudaibergenov/1c-ai-development-kit web-test --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Arman-Kudaibergenov/1c-ai-development-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/web-test .claude/skills/web-test && rm -rf skills-srcUse ~/.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/
Install the "web-test" agent skill from https://github.com/Arman-Kudaibergenov/1c-ai-development-kit/tree/master/.claude/skills/web-test into .claude/skills/web-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-test", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Arman-Kudaibergenov/1c-ai-development-kit/tree/master/.claude/skills/web-testType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Arman-Kudaibergenov/1c-ai-development-kit --skill web-test -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Arman-Kudaibergenov/1c-ai-development-kit web-test --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arman-Kudaibergenov/1c-ai-development-kit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/web-test .agents/skills/web-test && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "web-test" agent skill from https://github.com/Arman-Kudaibergenov/1c-ai-development-kit/tree/master/.claude/skills/web-test into .agents/skills/web-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-test", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Arman-Kudaibergenov/1c-ai-development-kit --skill web-test -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Arman-Kudaibergenov/1c-ai-development-kit web-test --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arman-Kudaibergenov/1c-ai-development-kit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/web-test .cursor/skills/web-test && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "web-test" agent skill from https://github.com/Arman-Kudaibergenov/1c-ai-development-kit/tree/master/.claude/skills/web-test into .cursor/skills/web-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-test", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Arman-Kudaibergenov/1c-ai-development-kit.git --path .claude/skills/web-test--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Arman-Kudaibergenov/1c-ai-development-kit --skill web-test -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Arman-Kudaibergenov/1c-ai-development-kit web-test --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arman-Kudaibergenov/1c-ai-development-kit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/web-test .gemini/skills/web-test && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "web-test" agent skill from https://github.com/Arman-Kudaibergenov/1c-ai-development-kit/tree/master/.claude/skills/web-test into .gemini/skills/web-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-test", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Arman-Kudaibergenov/1c-ai-development-kit web-testInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Arman-Kudaibergenov/1c-ai-development-kit --skill web-test -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Arman-Kudaibergenov/1c-ai-development-kit.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/web-test .github/skills/web-test && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "web-test" agent skill from https://github.com/Arman-Kudaibergenov/1c-ai-development-kit/tree/master/.claude/skills/web-test into .github/skills/web-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-test", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Arman-Kudaibergenov/1c-ai-development-kit --skill web-test -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Arman-Kudaibergenov/1c-ai-development-kit web-test --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arman-Kudaibergenov/1c-ai-development-kit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/web-test .opencode/skills/web-test && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "web-test" agent skill from https://github.com/Arman-Kudaibergenov/1c-ai-development-kit/tree/master/.claude/skills/web-test into .opencode/skills/web-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-test", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
web-testЭтот скилл MUST быть вызван когда пользователь просит проверить или протестировать 1С через браузер в интерактивном режиме (быстрые ручные проверки).
Web Test is an agent skill from Arman-Kudaibergenov/1c-ai-development-kit. Этот скилл MUST быть вызван когда пользователь просит проверить или протестировать 1С через браузер в интерактивном режиме (быстрые ручные проверки). SHOULD также вызывать для одноразовой верификации поведения веб-интерфейса 1С. Do NOT использовать для создания файлов автотестов — используй playwright-test; для сложных сценариев — используй 1c-web-session.
Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts (for example `recording.md`, `scripts/package-lock.json` and `scripts/package.json`).
It sits in Agent Workflows. It works with Playwright. The repository describes itself as: Comprehensive AI agents, skills and rules toolkit for 1C:Enterprise development in Cursor IDE. The licence is AGPL-3.0.
Read from SKILL.md and the folder at commit 92d389e. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
BashReadWriteGlobGrepFrom allowed-tools in the SKILL.md frontmatter.
Ships 5 files in scripts/ (JavaScript), which the agent can run.
Shell commands in SKILL.md call:
nodenpmFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Web Test loads about 3.4k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 1,037 words of instructions outside code blocks.
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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Bash, Read, Write, Glob, GrepAutomated 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.
The full file from Arman-Kudaibergenov/1c-ai-development-kit at commit 92d389e, republished under its AGPL-3.0 licence (© Arman-Kudaibergenov). 1,037 words, ~3,396 tokens.
.claude/skills/web-test/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.Automates user interactions with 1C:Enterprise web client via Playwright — navigating sections, filling forms, reading tables and reports, filtering lists.
RUN=".claude/skills/web-test/scripts/run.mjs"
# One-shot: opens browser → runs script → closes browser → exits
node $RUN run http://localhost:8081/bpdemo test-scenario.js
# Or pipe inline:
cat <<'SCRIPT' | node $RUN run http://localhost:8081/bpdemo -
await navigateSection('Продажи');
await openCommand('Заказы клиентов');
await clickElement('Создать');
await fillFields({ 'Клиент': 'Альфа' });
await clickElement('Провести и закрыть');
SCRIPTcd .claude/skills/web-test/scripts && npm installRequires Node.js 18+. npm install downloads Playwright and Chromium.
Read .v8-project.json from project root. Each database has id and optional webUrl.
Construct URL as http://localhost:8081/<id> or use webUrl if set.
Use /web-publish first if the database is not published.
node $RUN run <url> script.js # exits when done, no session# 1. Start session (run_in_background=true, prints JSON when ready)
node $RUN start <url>
# 2. Execute scripts against running session
cat <<'SCRIPT' | node $RUN exec -
const form = await getFormState();
console.log(JSON.stringify(form, null, 2));
SCRIPT
# 3. Screenshot
node $RUN shot result.png
# 4. Stop (logout + close)
node $RUN stopstart runs an HTTP server in background. Use exec/shot/stop from other shells.
All browser.mjs exports are globals — no import needed.
console.log() output is captured in the JSON response.
writeFileSync / readFileSync also available.
navigateSection(name) → { navigated, sections, commands }Go to a top-level section (fuzzy match). Returns list of commands in that section.
await navigateSection('Продажи');
// { navigated: 'Продажи', sections: [...], commands: ['Заказы клиентов', ...] }openCommand(name) → form stateOpen a command from the function panel (fuzzy). Returns form state of the opened form.
const form = await openCommand('Заказы клиентов');navigateLink(url) → form stateOpen any 1C object by metadata path (Shift+F11 dialog). Bypasses section/command navigation.
await navigateLink('Документ.ЗаказКлиента');
await navigateLink('РегистрНакопления.ЗаказыКлиентов');
await navigateLink('Справочник.Контрагенты');switchTab(name) → form stateSwitch to an already-open tab/window (fuzzy match).
getFormState() → { fields, buttons, tabs, table, filters, reportSettings? }Returns current form structure. This is the primary way to understand what's on screen.
fields — each field has: name, value, label?, actions? (select, clear, open), required? (true for unfilled mandatory fields)
table — summary only: { name, columns, rowCount }. Use readTable() for actual data.
reportSettings — for DCS reports: human-readable filter settings instead of raw technical names:
const form = await getFormState();
// form.reportSettings = [
// { name: "Склад", enabled: true, value: "Склад бытовой техники", actions: ["select"] },
// { name: "Номенклатура", enabled: false, value: "" }
// ]errorModal — if present, 1C showed an error dialog. Read the message and decide how to proceed.
confirmation — if present, a Yes/No dialog is shown. Call clickElement('Да') or clickElement('Нет').
readTable({ maxRows?, offset? }) → { columns, rows, total, shown, offset }Read actual grid data with pagination. Each row is { columnName: value }.
| Option | Default | Description |
|---|---|---|
maxRows | 20 | Max rows to return per call |
offset | 0 | Skip first N rows |
Special row fields:
_kind: 'group' — hierarchical group row_kind: 'parent' — parent row in hierarchy_tree: 'expanded'|'collapsed' — tree node state_level: N — nesting depth in tree viewhierarchical: true — list has groups (on result object)viewMode: 'tree' — tree view active (on result object)const t = await readTable({ maxRows: 50 });
console.log('Columns:', t.columns);
console.log('Rows:', t.rows.length, 'of', t.total);
// Pagination:
const page2 = await readTable({ maxRows: 50, offset: 50 });readSpreadsheet() → { title?, headers?, data?, totals?, rows?, total }Read report output (SpreadsheetDocument) after clicking "Сформировать".
Returns structured data when header row is detected:
await clickElement('Сформировать');
await wait(5);
const report = await readSpreadsheet();
// { title: "Остатки товаров", headers: ["Номенклатура", "Склад", "Количество"],
// data: [{ "Номенклатура": "Бумага", "Склад": "Основной", "Количество": "150" }, ...],
// totals: { "Количество": "1250" }, total: 42 }Falls back to { rows: string[][], total } when headers can't be detected.
getSections() → { activeSection, sections, commands }Read section panel and commands without navigating.
getCommands() → string[]Commands of the current section.
getPageState() → { activeSection, activeTab, sections, tabs }Sections + all open tabs.
clickElement(text, { dblclick? }) → form stateClick button, hyperlink, tab, or grid row (fuzzy match).
await clickElement('0000-000227', { dblclick: true }); // opens documentsubmenu[] when a menu opens — click again with item name:const r = await clickElement('Ещё');
// r.submenu = ['Расширенный поиск', 'Настройки', ...]
await clickElement('Расширенный поиск');fillFields({ name: value }) → { filled, form }Fill form fields by label (fuzzy match). Auto-detects field type.
| Value | Field type | Method |
|---|---|---|
'Конфетпром' | Reference | Clipboard paste + typeahead |
'5000' | Plain text | Clipboard paste |
'true' / 'да' | Checkbox | Toggle |
'Оплата поставщику' | Radio | Fuzzy label match |
DCS report filters: use human-readable label names. Checkbox is auto-enabled:
await fillFields({
'Склад': 'Склад бытовой техники', // auto-enables "Склад" checkbox + fills value
'Номенклатура': 'Вентилятор' // same: enables checkbox + fills
});Returns { filled: [{ field, ok, value, method }], form: {...} }.
Method is one of: 'toggle' | 'radio' | 'paste' | 'dropdown' | 'form' | 'typeahead'
selectValue(field, search) → form state with selectedSelect a value from reference field via dropdown or selection form. More reliable than fillFields for reference fields that need exact selection from a catalog.
await selectValue('Организация', 'Конфетпром');
// result.selected = { field: 'Организация', search: 'Конфетпром', method: 'dropdown'|'form' }Also supports DCS labels — auto-enables the paired checkbox.
fillTableRow(fields, opts) → form stateFill table row cells via Tab navigation.
// Add new row:
await fillTableRow(
{ 'Номенклатура': 'Бумага', 'Количество': '10', 'Цена': '100' },
{ tab: 'Товары', add: true }
);
// Edit existing row:
await fillTableRow(
{ 'Количество': '20' },
{ tab: 'Товары', row: 0 }
);deleteTableRow(row, { tab? }) → form stateDelete row by 0-based index.
closeForm({ save? }) → form stateClose the current form via Escape.
| Argument | Behavior |
|---|---|
{ save: false } | Auto-clicks "Нет" on confirmation |
{ save: true } | Auto-clicks "Да" on confirmation |
{} (omitted) | Returns confirmation field if dialog appears |
Preferred over clickElement('×') — close buttons on tabs are ambiguous.
filterList(text, opts?) → form stateFilter list. Simple mode searches all columns, advanced mode targets a specific field.
await filterList('КП00-000018'); // simple — all columns
await filterList('Мишка', { field: 'Наименование' }); // advanced — specific column
await filterList('Мишка', { field: 'Наименование', exact: true }); // exact matchWorks on hierarchical catalogs too (flattens the view).
unfilterList({ field? }) → form stateClear filters. Without arguments clears all, with { field } clears specific badge.
screenshot() → PNG Bufferwait(seconds) → form stategetPage() → Playwright Page (raw, for advanced scripting)startRecording(path, opts?) / stopRecording() → MP4 video recordingshowCaption(text, opts?) / hideCaption() → text overlay on pageshowTitleSlide(text, opts?) / hideTitleSlide() → full-screen title card (intro/outro)isRecording() → booleansetHighlight(on) / isHighlightMode() → auto-highlight mode for videohighlight(text) / unhighlight() → manual element highlightingSee recording.md for setup (ffmpeg), highlight mode, API details, and examples.
If .v8-project.json has ffmpegPath, pass it to startRecording({ ffmpegPath }).
await navigateSection('Продажи');
await openCommand('Заказы клиентов');
await clickElement('Создать');
await fillFields({ 'Организация': 'Конфетпром', 'Контрагент': 'Альфа' });
await fillTableRow({ 'Номенклатура': 'Бумага', 'Количество': '10' }, { tab: 'Товары', add: true });
await clickElement('Провести и закрыть');await clickElement('КП00-000227', { dblclick: true });
// Always use { dblclick: true } — single click only selects the rowawait filterList('Конфетпром'); // flatten + search
await clickElement('Конфетпром ООО', { dblclick: true }); // open
await closeForm();
await unfilterList(); // restore hierarchy// Fill report filters using readable labels
await fillFields({ 'Склад': 'Основной склад' });
await clickElement('Сформировать');
await wait(5);
const report = await readSpreadsheet();
console.log('Title:', report.title);
console.log('Data rows:', report.data?.length);page.keyboard.press)| Key | Context | Action |
|---|---|---|
F8 | Reference field focused | Create new catalog item |
Shift+F4 | Reference field focused | Clear field value |
F4 | Reference field focused | Open selection form |
Alt+F | List/table form | Open advanced search dialog |
| Goal | Method |
|---|---|
| Post & close document | clickElement('Провести и закрыть') |
| Save & close catalog | clickElement('Записать и закрыть') |
| Close without saving | closeForm({ save: false }) |
| Close and save | closeForm({ save: true }) |
| Close (manual confirm) | closeForm() — returns confirmation if dialog appears |
{ "ok": true, "output": "...console.log output...", "elapsed": 3.2 }On error (auto-screenshot taken):
{ "ok": false, "error": "Element not found", "output": "...", "screenshot": "error-shot.png", "elapsed": 1.5 }filterList returns 0 rows or readTable is empty after filtering — the item likely doesn't exist in this database. Don't retry the same search 5 times with slight variationsnavigateLink. Couldn't find via simple search? Try advanced search with a specific field. But don't repeat the same methodstart)cat <<'SCRIPT' | node $RUN exec - to avoid escaping issues\u00a0 instead of regular spaces. All matching is normalized internally© Arman-Kudaibergenov, 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
SKILL.md and 6 other files (scripts) in .claude/skills/web-test of Arman-Kudaibergenov/1c-ai-development-kit.
Open the folder on GitHubat commit 92d389e
Web Test 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Web Test this skillArman-Kudaibergenov/1c-ai-development-kit | 166 | — | ~3.4k | Automated safety check: Notes | AGPL-3.0 | |
| Context Mode Output Sandboxmksglu/context-mode | 26k | — | ~4.1k | Automated safety check: Pass | Custom licence | |
| Agent QA Authoringvostride/agent-qa | 902 | — | ~569 | Automated safety check: Pass | Custom licence | |
| Agent QA Result Triagevostride/agent-qa | 902 | — | ~394 | Automated safety check: Pass | Custom licence | |
| Project Releaseswimmwatch/cloakbrowser-mcp | 161 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Lightpandalightpanda-io/agent-skill | 101 | — | ~6k | Automated safety check: Pass | Apache-2.0 |
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
vostride/agent-qa
A skill your agent uses when creating, editing, validating, or running agent-qa tests, suites, or hooks.
vostride/agent-qa
A skill your agent uses when investigating failed agent-qa runs, inspecting artifacts, classifying failures, or comparing recent runs.
swimmwatch/cloakbrowser-mcp
Prepare, publish, verify, or recover a cloakbrowser-mcp release only when the user explicitly requests release work.
lightpanda-io/agent-skill
Lightpanda browser, drop-in replacement for Chrome-based browsing in any AI agent - faster and lighter for tasks without graphical rendering like data retrieval.
sweetcornna/free-search-mcp
Use with the free-search MCP tools whenever a web lookup must yield facts someone will rely on: dates, deadlines, prices, prizes, fees, rules, eligibility, schedules, versions, statistics, news, or…
Arman-Kudaibergenov/1c-ai-development-kit
Этот скилл MUST быть вызван для управления 1С:Предприятие в веб-клиенте через Playwright MCP: запуск/перезапуск/завершение сеанса, навигация, создание и редактирование справочников и документов.
Arman-Kudaibergenov/1c-ai-development-kit
Этот скилл MUST быть вызван для анализа и инспекции любого объекта 1С из XML-выгрузки: конфигурация (cf-info), объект метаданных (meta-info), управляемая форма (form-info), схема компоновки данных…
Arman-Kudaibergenov/1c-ai-development-kit
Этот скилл MUST быть вызван когда пользователь говорит "инициализируем проект", "init project", просит настроить 1С-проект.
Arman-Kudaibergenov/1c-ai-development-kit
Этот скилл MUST быть вызван когда нужно изменить свойства конфигурации, добавить или удалить объект из состава ChildObjects, настроить роли по умолчанию.
Arman-Kudaibergenov/1c-ai-development-kit
Этот скилл MUST быть вызван когда нужно проанализировать состав расширения (CFE): заимствованные объекты, перехватчики, проверить перенесены ли вставки.
Arman-Kudaibergenov/1c-ai-development-kit
Этот скилл MUST быть вызван когда пользователь просит создать новое расширение конфигурации (CFE) для исправления, доработки или дополнения.
Works with
Categories
Этот скилл MUST быть вызван когда пользователь просит проверить или протестировать 1С через браузер в интерактивном режиме (быстрые ручные проверки). Web Test is an agent skill from Arman-Kudaibergenov/1c-ai-development-kit. Этот скилл MUST быть вызван когда пользователь просит проверить или протестировать 1С через браузер в интерактивном режиме (быстрые ручные проверки).
Web Test fits situations like: agent Workflows work in your project.
Run `npx skills add Arman-Kudaibergenov/1c-ai-development-kit --skill web-test -a claude-code`. Or copy the skill folder (.claude/skills/web-test in Arman-Kudaibergenov/1c-ai-development-kit) into .claude/skills/web-test in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Arman-Kudaibergenov/1c-ai-development-kit --skill web-test -a codex`. Or copy the skill folder (.claude/skills/web-test in Arman-Kudaibergenov/1c-ai-development-kit) into .agents/skills/web-test in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Arman-Kudaibergenov/1c-ai-development-kit --skill web-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/web-test, .gemini/skills/web-test, .github/skills/web-test and .opencode/skills/web-test in your project.
Going by SKILL.md and its folder, Web Test needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node and npm). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Bash, Read, Write, Glob, Grep.
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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.
Web Test 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.
About 3.4k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Web Test: Context Mode Output Sandbox (mksglu/context-mode, 26k stars), Agent QA Authoring (vostride/agent-qa, 902 stars), Agent QA Result Triage (vostride/agent-qa, 902 stars) and Project Release (swimmwatch/cloakbrowser-mcp, 161 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Arman-Kudaibergenov (a GitHub user) maintains it in Arman-Kudaibergenov/1c-ai-development-kit, which has 166 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on May 25, 2026.
Source: Arman-Kudaibergenov/1c-ai-development-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.