NDDev-it-com

Отлаживает browser-only failures через Chrome DevTools MCP и Playwright CLI. Используй для: консоль, сеть, runtime, layout, memory, performance, Lighthouse. EN triggers: browser debug, console, network, runtime, performance.

Маршрутизирует browser tasks только через managed Playwright CLI и Chrome DevTools MCP. Используй для: UI, визуально, скриншот, Figma, консоль, сеть, перфоманс. EN triggers: browser routing, UI validation, screenshots, visual QA, console, network.

Валидирует UI и сценарии через Playwright CLI evidence. Используй для: проверь UI, браузер, скриншот, регрессия, адаптив, бизнес-логика, визуально. EN triggers: validate UI, browser check, regression, responsive, screenshot.

Низкоуровневая browser automation через Playwright CLI. Используй для: screenshots, snapshots, headed sessions, traces, responsive, UI proof. EN triggers: Playwright CLI validation, screenshots, snapshots, traces.

Проводит visual QA для Figma, screenshots и reference images. Используй для: pixel-perfect, сравни с Figma, сравни с фото, diff. EN triggers: visual diff, pixel-perfect, compare Figma, reference image.

Маршрутизирует старые Webwright-запросы в управляемые CloakBrowser workflows. Используй для: длинная web-задача, RPA, extraction. EN triggers: compatibility browser task, long-horizon web task.

Интернет-ресёрч: изучи интернет, latest/current, релизы, advisories. Используй для: текущая информация. EN: web search.

Экономия токенов: команды через rtk (сжатие вывода), код символами Serena, не целыми файлами. Запуск команд, вывод git/тестов/сборки/линта. EN: token economy, rtk, compress command output, reduce context.

Отлаживает browser-only failures через управляемые Chrome DevTools MCP и Playwright CLI. Используй для: консоль, сеть, runtime, hydration, layout, memory, performance, Lighthouse. EN triggers: browser debug, console errors, network, runtime, layout, memory, performance, Lighthouse.

Маршрутизирует browser tasks только через управляемые Playwright CLI и Chrome DevTools MCP. Используй для: проверь в браузере, UI, визуально, скриншот, Figma, консоль, сеть, перфоманс. EN triggers: browser routing, UI validation, screenshots, visual QA, console, network, performance.

Валидация UI и пользовательских сценариев через управляемый Playwright CLI. Используй для: проверь UI, проверь в браузере, визуально, скриншот, регрессия, адаптив, бизнес-логика. EN triggers: validate UI, browser check, regression, responsive, business logic, screenshot.

Низкоуровневая browser automation через управляемый Playwright CLI. Используй для: screenshots, snapshots, headed sessions, traces, responsive, UI proof. EN triggers: Playwright CLI validation, screenshots, snapshots, traces, responsive.

Проводит visual QA для Figma, screenshots и reference images через управляемые browser providers. Используй для: pixel-perfect, сравни с Figma, сравни с фото, diff. EN triggers: visual diff, pixel-perfect, compare Figma, reference image.

Совместимый маршрут legacy Webwright task intent в управляемые Playwright CLI и Chrome DevTools MCP; Webwright runtime не запускается. Используй для: найти, сравнить, выгрузить, повторить, reusable workflow. EN triggers: Webwright task, long-horizon web task, RPA, extraction, reusable workflow.

Интернет-исследование с авторитетными источниками через WebSearch + WebFetch. Покрывает: изучи интернет, latest/current. Используй для: текущие тренды, индустриальные новости, секьюрити-уведомления, анонсы вендоров, информация вне статичных доков, актуальные релизы. EN triggers: current trends, industry news, security advisories, vendor announcements, latest releases, news search, web search, current state of X.

Экономия токенов через rtk и Serena/LSP: shell-команды идут через rtk (сжатие вывода), код читается символами Serena, а не целыми файлами. Используй для: запуск команд, чтение вывода git/тестов/сборки/линта, экономия контекста, большие файлы. EN triggers: token economy, rtk, compress command output, reduce context, avoid whole-file reads, run commands efficiently, rtk gain.

Отлаживает browser-only failures через управляемые Chrome DevTools MCP и Playwright CLI. Используй для: консоль, сеть, runtime, hydration, layout, memory, performance, Lighthouse. EN triggers: browser debug, console errors, network, runtime, layout, memory, performance, Lighthouse.

Маршрутизирует browser tasks только через управляемые Playwright CLI и Chrome DevTools MCP. Используй для: проверь в браузере, UI, визуально, скриншот, Figma, консоль, сеть, перфоманс. EN triggers: browser routing, UI validation, screenshots, visual QA, console, network, performance.

Валидация UI и пользовательских сценариев через управляемый Playwright CLI. Используй для: проверь UI, проверь в браузере, скриншот, регрессия, адаптив, бизнес-логика. EN triggers: validate UI, browser check, regression, responsive, business logic, screenshot.

Низкоуровневая browser automation через управляемый Playwright CLI. Используй для: screenshots, snapshots, headed sessions, traces, responsive, UI proof. EN triggers: Playwright CLI validation, screenshots, snapshots, traces, responsive.

Проводит visual QA для Figma, screenshots и reference images через управляемые browser providers. Используй для: pixel-perfect, сравни с Figma, сравни с фото, diff. EN triggers: visual diff, pixel-perfect, compare Figma, reference image.

Совместимый маршрут legacy Webwright task intent в управляемые Playwright CLI и Chrome DevTools MCP; Webwright runtime не запускается. Используй для: найти, сравнить, выгрузить, повторить, reusable workflow. EN triggers: Webwright task, long-horizon web task, RPA, extraction, reusable workflow.

Оркестратор cmux v3 для OpenCode: macOS cmux orchestrator, multi-agent terminal workflow, видимый head terminal, typed task envelopes, report-authoritative completion. Используй для: cmux orchestrator, делегируй воркерам. EN triggers: cmux v3 head, visible-terminal orchestration. EN: cmux v3 head.

Воркер cmux v3 для OpenCode: cmux worker role, typed task envelope, heartbeat, scoped JSON report, no push/final sync. Используй для: cmux worker, worker report. EN triggers: cmux v3 worker. EN: cmux v3 worker.

Start here for the nddev-builder toolkit. Indexes the Codex artifact families and the creator, checker, reviewer, and workflow skill that owns each, points at the single reference for schemas and current (Beta, experimental, or under-development) surfaces, and routes the task to the right skill. Use first whenever building, checking, reviewing, or releasing a Codex artifact, or when unsure which builder skill applies.

A guided first run of the nddev-builder toolkit — from zero to a working, checked Codex artifact in ordered steps. Use when new to nddev-builder, onboarding, or unsure which builder skill to start with.

Create or revise a Codex marketplace catalog with valid plugin sources, categories, installation policy, and authentication policy. Use when publishing local or remote plugin collections.

Check a managed Codex requirements.toml layer for supported keys, permission-profile consistency, and a valid lower-layer default. Use before delivering managed /etc/codex or MDM requirements.

Create a managed Codex requirements.toml layer that constrains permission profiles and other admin policy. Use when authoring the /etc/codex or MDM-delivered managed requirements a lower config layer must satisfy.

Install and iterate on a Codex plugin locally in developer mode: the install, reinstall, and cachebuster test loop for a plugin under development, run against an isolated install and never live state. Use when running or iterating on a plugin, its skills, MCP, hooks, or bundled app locally.

Version, catalog, and publish a native Codex plugin for distribution — the release step after dev-test, covering the SemVer manifest bump, marketplace catalog update, distribution source, and portal submission.

Build a whole Codex plugin from intent, not a single artifact. Define the product boundary, scaffold the manifest and every bundled capability (skills, hooks, MCP servers, apps) plus an optional personal marketplace entry, and validate the complete bundle. Use to compose a coherent multi-capability plugin rather than one standalone file.

Use this skill only when the owner explicitly asks to install or verify GDS, its pinned bundle, and selected harness projections on a new macOS, Linux, server, or CI device. Build an exact reversible plan and keep secrets in approved stores. Do not use it to clone every estate repository or change global tools silently.

Use this skill only when the owner explicitly asks to apply one logical change across repositories selected by a GDS portfolio. Create independent repository subplans, canaries, bounded waves, and an aggregate journal. Do not use it for one repository or pretend the portfolio has one Git transaction.

Use this skill only when the owner explicitly asks to finish the current work completely across every affected Git repository: implement, verify, integrate, publish, update dependency pins, and remove only proven-safe completed branches or worktrees. Do not use it for status, routine sync, or unfinished handoff.

Use this skill only when the owner wants to preserve unfinished work for another device or session. Plan an exact checkpoint commit, push the task branch, and create or update a draft pull request when policy requires it. Do not use it to merge, complete, synchronize main, or clean branches and worktrees.

Use this skill only when the owner explicitly asks to create, inspect, synchronize, rehome, detach, freeze, archive, or otherwise change a fork lifecycle. Preserve fork-specific commits and upstream identity; force is never the default. Do not use it for ordinary source repositories or generic branch synchronization.

Use this skill only when the owner explicitly asks to add, replace, reclassify, or remove a module relationship for a project. Validate independent Git boundaries, typed relationships, .gitmodules or package metadata, visibility, and pin policy. Do not use it for ordinary code changes inside an existing module.

Use this skill only when the owner explicitly asks to create, onboard, rename, transfer, archive, rehome, or otherwise change the lifecycle of a Git repository under GDS. Preserve stable identity and plan every provider and local mutation. Do not use it for source-code work or repository deletion hidden as removal.

Use this skill only when the owner explicitly asks to clone or materialize a selected repository set on a device. Resolve selectors, local roots, clone modes, submodules, and resource limits before applying. Do not use it to clone the whole estate by default or synchronize existing checkouts.

Authors a ZCode slash command as commands/<name>.md in a marketplace. Use when adding or defining a slash (/) command, including nested colon-separated commands. For a SKILL.md use add-skill; for a subagent use add-agent.

Scaffolds a new self-contained ZCode marketplace — a complete ~/.zcode setup — under zcode_tools/marketplaces/. Use when creating a brand-new setup or profile such as nddev-builder or nddev-designer, or bootstrapping a marketplace directory from scratch.

Scaffolds a new self-contained plugin bundle inside a ZCode marketplace and registers it in marketplace.json. Use when adding a plugin to a marketplace, or grouping skills, commands, and agents into one installable bundle.

Adds a model provider to a marketplace's config template. Use when adding or configuring an LLM provider — OpenAI, Anthropic, or a custom OpenAI-compatible endpoint — or wiring provider models, base URL, or API-key placeholders into a ZCode setup.

Authors a ZCode skill (SKILL.md) inside a plugin bundle or at user scope. Use when adding a skill or teaching the agent a reusable workflow. For a slash command use add-command; for a subagent use add-agent.

Runs an isolated install-and-verify loop for a marketplace using temporary HOME and ZCODE_HOME, proving components flatten and load without touching live ~/.zcode. Use to behaviorally test a plugin during development, after static validation.

A guided first run of the nddev-builder toolkit — from zero to a working, validated ZCode plugin or marketplace in ordered steps. Use when new to nddev-builder, onboarding, or unsure which skill to start with.

Orients you in the nddev-builder toolkit and in how ZCode 3.5.2 discovers and loads extensions. Use when asking how nddev-builder is structured, how ZCode loads skills/commands/agents, where components go and why, why an installed skill is not loading, what the installer does (flatten to user scope), or the install/remove/switch lifecycle. Read this first before authoring or debugging a marketplace.

The complete golden-path checklist for any change to the ci-workflows repository — editing a workflow, catalog entry, action pin, doc, or skill — so you touch every layer the catalog-driven pipeline expects and leave the validation gate green. Invoke before you edit.

The end-to-end release procedure for ci-workflows — version prep, the signed SemVer tag, the immutable-release verification checklist, and the post-release runtime-coverage re-promotion. Invoke when cutting or verifying a release. Requires an authorized maintainer.

Orient an agent on the ci-workflows repository in a single read — its catalog-as-source-of-truth architecture, the non-negotiable contracts, the validation gate, and which skill or file to reach for each task. Invoke first when you start work in this repository.

The complete golden-path checklist for any change to the ci-workflows repository — editing a workflow, catalog entry, action pin, doc, or skill — so you touch every layer the catalog-driven pipeline expects and leave the validation gate green. Invoke before you edit.

The end-to-end release procedure for ci-workflows — version prep, the signed SemVer tag, the immutable-release verification checklist, and the post-release runtime-coverage re-promotion. Invoke when cutting or verifying a release. Requires an authorized maintainer.

Orient an agent on the ci-workflows repository in a single read — its catalog-as-source-of-truth architecture, the non-negotiable contracts, the validation gate, and which skill or file to reach for each task. Invoke first when you start work in this repository.

Select and continuously verify zero-cost or bounded-cost CI for public and private repositories using a freshness-enforced fact ledger, normalized resource units, plan gates, and no-surprise-spend controls. Use for CI provider/tier architecture and budgeting.

Select and continuously verify zero-cost or bounded-cost CI for public and private repositories using a freshness-enforced fact ledger, normalized resource units, plan gates, and no-surprise-spend controls. Use for CI provider/tier architecture and budgeting.

Проверь browser/UI поведение только через управляемые Playwright CLI и Chrome DevTools MCP. EN: validate browser behavior through CloakBrowser.

Проведи дизайн/visual review через управляемый CloakBrowser boundary. EN: review design implementation with managed browser evidence.

Воркер cmux v3 для Antigravity CLI: cmux worker role, typed task envelope, heartbeat, scoped JSON report, no push/final sync. Используй для: cmux worker, worker report. EN triggers: cmux v3 worker. EN: cmux v3 worker.

Инициализируй Antigravity CLI adapter scope без изменений. EN: initialize Antigravity CLI adapter scope read-only.

Проведи read-only Antigravity rldyour review. EN: read-only Antigravity rldyour review.

Выполни полный Antigravity rldyour task lifecycle. EN: full Antigravity rldyour task lifecycle.

Синхронизируй Antigravity docs, memories и git. EN: synchronize Antigravity docs, memories, and git.

Сделай финальную синхронизацию Antigravity CLI adapter: docs, Serena memories, checks, release evidence. EN: post-task sync.

Проверь browser/UI поведение через Webwright, Playwright CLI и Chrome DevTools MCP. EN: validate browser behavior.

Запусти rldyour repair для Gemini CLI configuration. EN: repair Gemini CLI adapter.

Инициализируй Gemini adapter scope без изменений. EN: initialize Gemini adapter scope read-only.

Спроектируй новый Gemini/rldyour project scope. EN: design a new Gemini/rldyour project scope.

Проведи read-only Gemini rldyour review. EN: read-only Gemini rldyour review.

Выполни полный Gemini rldyour task lifecycle. EN: full Gemini rldyour task lifecycle.

Работай как видимый cmux worker terminal для Gemini. EN: visible cmux Gemini worker terminal.

Проведи дизайн/visual review с evidence и dynamic masks. EN: review design implementation.

Используй для browser QA только через управляемые Playwright CLI и Chrome DevTools MCP. EN: managed CloakBrowser evidence review.

Воркер cmux v3 для MiMoCode: cmux worker role, typed task envelope, heartbeat, scoped JSON report, no push/final sync. Используй для: cmux worker, worker report. EN triggers: cmux v3 worker. EN: cmux v3 worker.

Используй для финальной синхронизации rldyour после задачи. EN: post-task sync.

Используй для visual/Figma/design QA evidence. EN: design and visual review.

Используй для ремонта repo/config/runtime/release drift. EN: repair convergence.

Используй для полного rldyour SDLC: контекст, план, реализация, проверки, sync. EN: full lifecycle implementation.

Используй для security, secrets, permissions, MCP trust boundary. EN: defensive security review.

Используй для sync Serena memories и MiMoCode MEMORY.md projection. EN: memory sync.

Validate a native Claude Code plugin — manifest shape, component discovery, path variables, and the marketplace entry. Use before enabling, bundling, or releasing a plugin.

Create a native Claude Code plugin — `.claude-plugin/plugin.json` plus the component directories it declares. Use when scaffolding a new plugin or adding a component family to one.

Orient in the NDDev Claude Code builder — what each creator/checker skill produces and the native artifact families (plugin, marketplace, skill, command, subagent, hook, MCP). Use first when building or auditing a Claude Code plugin.