northcua — скилл для Claude Code: что делает и установка
Скилл northcua для Claude Code запускает NorthCUA Harness для Desktop/Web-задач, локальных браузерных батчей и проверки evidence. Он подключается при установке, настройке или проверке запуска NorthCUA.
Apache-2.0 ★ 128 обновлён 2026-11-09
npx skills add beipo-ai/NorthCUA --skill northcua -a claude-codeЧто делает northcua
Скилл northcua ведёт установку и запуск NorthCUA Harness из чистого checkout: помогает выбрать Web или native Desktop, настроить модель, выполнить ограниченную задачу и отдельно проверить результат, trace и вердикт evaluator. Для локальных серий он запускает controller, browser workers и существующий scheduler через команды batch.
Инструкции охватывают конфигурацию config init, проверку через config validate, режимы Python, serving и remote device, загрузку runtime skills и разбор сбоев. Для установки из исходников или wheel нужен uv 0.13.6+; реальная модель требует ключа и при необходимости endpoint, а для проверки без credentials есть scripted demo. Физический дисплей эксклюзивен: параллельные Desktop-задачи запускать нельзя. Локальный provider использует ОС и сеть хоста и не является VM.
Какие задачи решает
- настроить NorthCUA Harness из чистого checkout
- запустить Desktop или Web-задачу с выбранной моделью
- обработать несколько локальных задач через browser workers
- отделить завершение агента от проверки результата
- разобрать ошибку модели, браузера или зависшей задачи
Примеры запросов агенту
- Установи и настрой NorthCUA Harness из чистого checkout, затем выполни одну bounded Web-задачу.
- Запусти несколько локальных задач через
local-process, real browser workers и batch-команды с concurrency 1–2. - Проверь сохранённый trace, фактический результат и вердикт evaluator после Desktop-задачи.
Как установить northcua
1Через Skills CLI (Vercel)
npx skills add beipo-ai/NorthCUA --skill northcua -a claude-code2Вручную: положить файлы
~/.claude/skills/northcua/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/northcua/
1Через Skills CLI (Vercel)
npx skills add beipo-ai/NorthCUA --skill northcua -a codex2Вручную: положить файлы
.agents/skills/northcua/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add beipo-ai/NorthCUA --skill northcua -a cursor2Вручную: положить файлы
.cursor/skills/northcua/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install beipo-ai/NorthCUA skills/northcua2Вручную: положить файлы
.github/skills/northcua/SKILL.md1Через Skills CLI (Vercel)
npx skills add beipo-ai/NorthCUA --skill northcua -a gemini-cli2Командой платформы
gemini skills install https://github.com/beipo-ai/NorthCUA --path skills/northcuaВручную: положить файлы
.devin/skills/northcua/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Claude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы о northcua
Как установить northcua в Claude Code?
Выполни npx skills add beipo-ai/NorthCUA --skill northcua -a claude-code, затем используй файл ~/.claude/skills/northcua/SKILL.md.
Что делает northcua?
northcua управляет NorthCUA Harness: помогает установить и настроить проект, запускать Desktop/Web-задачи и локальные браузерные батчи, а также проверять evidence и итог evaluator.
Что нужно для работы northcua?
Для установки из исходников или wheel нужен uv 0.13.6+. Реальная модель требует model, key и при необходимости endpoint; credential-free scripted demo запускается без ключа. Для Desktop-задач нужен физический дисплей.
Исходный текст
SKILL.md · Apache-2.0
--- name: northcua description: Install, configure and operate the NorthCUA Harness, including Desktop/Web tasks, local browser batches and evidence checks. Use for running this project, not its training or data-generation research. --- # Operate NorthCUA from a clean checkout The project is **NorthCUA**, the shipped component is **NorthCUA Harness**, and the package/CLI is `northcua`. This skill is distributed with the repository. Resolve the real location of this file (including symlinks); the repository root is two directories above its folder. Run commands there, or use an installed release and the corresponding version of these guides. Do not copy this file alone: its linked guides are part of the skill's operating contract. For a new installation, use the `main` branch of [NorthCUA](https://github.com/beipo-ai/NorthCUA), following the first-run guide's clone/install commands. Check [resource availability](../../docs/resources.md) for the current report and model links; do not assume a referenced model checkpoint has been published or that this project is already available on PyPI. ## Choose the user's workflow - **Nothing installed / first task:** follow [from-zero setup](../../docs/first-run.md). It includes Bash/zsh and PowerShell setup, model templates, native permissions, a credential-free browser/native check and success criteria. - **Model or parameter configuration:** [configuration](../../docs/configuration.md). `config init --model ... --base-url ...` populates both agents. The user normally supplies only model, key and optional endpoint via [the env template](../../.env.example). Read [models](../../docs/models.md) for endpoint requirements and weight availability. Use the matching shell instructions: PowerShell does not source a Bash `.env` file. Keep credentials as environment references; do not ask for keys in chat. Before a Desktop run, match the model's coordinate convention: for 0–1000 relative output, set `desktop.coordinate_policy.input_space: normalized_1000` in the app YAML used by that run; `clamp_to_bounds: true` keeps edge positions inside the capture. The default is `image_pixels`. Read [coordinate configuration](../../docs/configuration.md#desktop-coordinates) for the mapping. Web refs and viewport CSS-pixel actions follow their own contract; this Desktop setting does not change them. - **Several local tasks / recovery:** follow [local batch](../../docs/local-batch.md) end to end. It starts a real controller, real browser workers and the existing scheduler without cloud services. Then consult [batch operations](../../docs/batch.md). - **Python, serving, remote device:** [execution modes](../../docs/running.md). Local application WebSocket and controller submission are different protocols. - **Custom runtime skill:** [skill loading](../../docs/skills.md). - **Failure, missing browser, model error or stuck task:** [troubleshooting](../../docs/troubleshooting.md). - **Result inspection / evaluation:** [evaluation](../../docs/evaluation.md). Read the chosen tutorial before executing; it contains dependencies and expected outputs. Do not infer command flags from another CUA project or old experiment scripts. Use `northcua <group> --help` for optional controls and `config schema` for current app/batch fields. `config validate` does not call the model. ## Execution contract 1. Determine the requested target (Web or native Desktop), execution mode, model endpoint and success criterion. Use the local scripted demo when checking the installation without credentials; label it as such. Use the user's real model for their actual task. Do not substitute demo success for task success. 2. Use uv 0.13.6+ for source or wheel installation; older uv releases can omit Darwin PyObjC dependencies. First read the [known upstream dependency risk](../../docs/security/dependencies.md): the retained NexAU constraint requires affected Transformers 4.x; do not load untrusted tokenizer/model configuration or treat the policy exception as a fix. Install from this repository's lock or matching release wheels. Activate the environment in every terminal. `uv run --no-sync` preserves installed extras. Create configuration in a new writable directory; preserve existing outputs. 3. Run one bounded task first. Desktop GUI tools return screenshots directly; there is no alternative observation mode. A physical display is exclusive: do not run concurrent Desktop tasks or use another agent's GUI session. 4. Inspect terminal status, the actual outcome, saved trace and evaluator verdict separately. A passing configuration check or actor completion is not outcome verification. Retain failed evidence and report unverified modes honestly. 5. For local batching use `local-process`, real browser workers and the existing batch commands. The `fake` provider is only a scheduling simulation. Start with concurrency 1–2; keep task IDs/output paths stable for resume. Drain and wait for the current runner to exit before resuming. Do not hand-edit state DBs. 6. Stop the processes you started and confirm cleanup. Preserve results for the user. The local provider shares the host OS and network; it is not a VM. The self-contained path needs no NorthJetty, cloud key, private dataset or historical deployment checkout. E2B deployments and prepared Desktop HTTP endpoints are optional environments managed separately. Use the [recommended Desktop settings](../../examples/desktop-settings/README.md) through the ordinary Desktop entry points when those model/prompt recipes are useful. Report the exact commands/mode, source revision, model type (scripted or real), actual outcomes, evidence paths, recovery/cleanup result and any remaining blocker. For an independent acceptance run, use a fresh output directory and follow these instructions without relying on author-provided success claims.
© beipo-ai · Apache-2.0 · beipo-ai/NorthCUA