qa · adobe — скилл для Claude Code: что делает и как установить
Скилл qa проводит автоматический аудит сайта на AEM Edge Delivery Services после деплоя. Он находит визуальные и структурные регрессии, но никогда сам не меняет код.
Apache-2.0 253 установок ★ 335 обновлён 2026-11-14
npx skills add adobe/skills --skill qa -a claude-codeЧто делает qa
Скилл выполняет проверку развёрнутого сайта только в режиме чтения. Он сверяет маршрутизацию, метаданные, разметку JSON-LD, шаблоны, доступность по axe и целостность ссылок. Во время проверки инструмент ищет ошибки JavaScript в консоли браузера, сломанные изображения и сдвиги в геометрии блоков.
Все отчёты сохраняются в папку stardust/qa/, включая report.html, снимок данных report.json и скриншоты в каталоге stardust/qa/shots/. Скилл принципиально ничего не исправляет в репозитории и не трогает контент сайта. Если запустить его повторно, он сопоставит страницу с сохранёнными эталонами из stardust/qa/baselines/.
Для полной проверки требуются Node 22+, библиотека Playwright с браузером Chromium в проекте, утилита playwright-cli в PATH и установленный рядом скилл impeccable. Без Playwright будут работать только базовые сетевые проверки без запуска браузера.
Какие задачи решает
- найти сломанные ссылки и ошибки JavaScript на развёрнутом сайте
- проверить соответствие шаблонов и доступность страниц по axe
- выявить визуальные регрессии по сравнению с сохранёнными снимками экрана
- оценить редактируемость блоков в da.live после публикации
Примеры запросов агенту
- Запусти аудит сайта командой
/stardust:qa <live-url> - Проверь опубликованный сайт на визуальные регрессии и битые изображения
- Сравни текущую вёрстку с базовыми снимками экрана
Как установить qa
1Через Skills CLI (Vercel)
npx skills add adobe/skills --skill qa -a claude-code2Вручную: положить файлы
~/.claude/skills/qa/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/qa/
1Через Skills CLI (Vercel)
npx skills add adobe/skills --skill qa -a codex2Вручную: положить файлы
.agents/skills/qa/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add adobe/skills --skill qa -a cursor2Вручную: положить файлы
.cursor/skills/qa/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install adobe/skills plugins/stardust/skills/qa2Вручную: положить файлы
.github/skills/qa/SKILL.md1Через Skills CLI (Vercel)
npx skills add adobe/skills --skill qa -a gemini-cli2Командой платформы
gemini skills install https://github.com/adobe/skills --path plugins/stardust/skills/qaВручную: положить файлы
.devin/skills/qa/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Через Skills CLI (Vercel)
npx skills add adobe/skills --skill qa -a opencodeClaude.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 qa
Как установить qa в Claude Code?
Установите скилл командой npx skills add adobe/skills --skill qa -a claude-code. Файл настроек сохранится по пути ~/.claude/skills/qa/SKILL.md.
Исправляет ли qa найденные ошибки в коде?
Нет, скилл работает строго в режиме чтения и никогда не меняет файлы репозитория или контент. Все проблемы он заносит в отчёты report.html и report.json внутри каталога stardust/qa/.
Что нужно для запуска всех браузерных тестов?
Потребуются среда Node 22+, пакет Playwright с Chromium в зависимостях проекта, утилита playwright-cli в системном пути и скилл impeccable. Без Playwright скилл выполнит только сетевую проверку разметки и ссылок.
Исходный текст
SKILL.md · Apache-2.0
---
name: qa
description: Read-only automated QA sweep of a deployed stardust site on AEM Edge Delivery Services — validates routing, content fidelity vs the source capture, template conformance, rendered integrity (geometry, JS errors, broken images), visual regression vs baselines, metadata/SEO/JSON-LD, link integrity, accessibility (axe), and performance budgets, then emits a findings report with an allowlist for documented non-defects. Finds issues; never fixes them. Use when the user asks to "QA the site", "validate the migration", "check the live site for issues", "run a QA sweep/regression check", or invokes `$stardust qa` (`/stardust:qa` in Claude Code) <live-url>.
license: Apache-2.0
compatibility: Requires Node 22+, Playwright with Chromium resolvable from the project, and the impeccable skill (github.com/pbakaus/impeccable) installed alongside stardust.
---
# stardust:qa — read-only site QA sweep
One live URL in. One evidence-bound findings report out. **This skill never
edits anything** — not site content, not DA documents, not repo code. Its only
writes are report artifacts under `stardust/qa/`. If the user wants findings
fixed, that is a separate, explicit follow-up outside this skill.
`qa` is the post-deploy counterpart of `rollout`'s delivery verification: where
rollout asks "did every page ship?", qa asks "is everything that shipped
actually correct?" — at all three layers a deploy can silently break:
1. **delivery** — what the pipeline serves (`.plain.html`, full HTML, sheets, sitemap)
2. **rendered** — what a browser shows after block decoration (and what it
does: an autoplay video that only shows its poster is a rendered defect)
3. **regression** — what changed since the last approved state (visual baselines)
A green upper layer never implies the lower one: a publish 200 ≠ delivered,
delivered HTML ≠ rendered correctly.
## Setup
1. Run the master skill's setup (`skills/stardust/SKILL.md` § Setup) if not
already done this session. `qa` works standalone too — it only needs a live
base URL.
2. Resolve the **base URL** (the `*.aem.live` host or production domain). If
the user didn't give one, look in `stardust/rollout/rollout.json`
(`site.liveHost`) or ask.
3. Resolve the **inventory source** — what pages the sweep covers, merged from
any of: `stardust/template-map.json` (also supplies template assignments for
conformance; `scripts/from-knowledge.mjs` writes it from a spec, plus allowlist
entries for 404s the source already had), a paths file, and the live `sitemap.xml` (always fetched;
parity mismatches become findings, so a wrong sitemap can't silently shrink
coverage).
4. Optional inputs that unlock deeper checks:
- `--scrape stardust/scrape` — verbatim fidelity vs the extraction capture
- `--expected-blocks <json>` — explicit per-template block expectations
- `--parity <json>` — dynamic parity file to replay (default
`stardust/dynamics/parity.json`; the `dynamics` check reports
`parity-missing` when absent)
- `--auth-header "token …"` / `--token-env SITE_TOKEN` — protected
origins; the secret is sent to the base origin only
(otherwise derived by fleet consensus)
- `--blocks-dir <dir>` — the site's `blocks/` checkout, so the
`editability` check can honour `@ew-exempt` JSDoc tags (otherwise
pass `--ew-exempt a,b` for index-driven blocks)
5. Browser checks need **playwright resolvable from the project** (`node_modules/playwright`).
If missing, run the delivery-layer checks only (`--checks routing,content,templates,metadata,links`)
and tell the user what was skipped.
6. Append a phase-transition line to `stardust/status.jsonl` per
`reference/run-status.md` (master skill) at sweep start/end.
## Procedure
### Phase 1 — deterministic sweep
```bash
node <plugin>/skills/qa/scripts/qa.mjs \
--base https://main--<site>--<org>.aem.live \
--template-map stardust/template-map.json \
--scrape stardust/scrape
```
Writes `stardust/qa/inventory.json`, `report.json`, `report.html`, screenshots
under `stardust/qa/shots/`, and (first run) visual baselines under
`stardust/qa/baselines/`. Exit 0 = no active errors, 1 = active errors,
2 = infra failure. `reference/checks.md` documents every check, its finding
ids, and severity rationale. Useful variants: `--checks <subset>`,
`--max-pages <n>` (smoke run), `--fail-on warn` (strict gate). The `ai-readability` check
reproduces Adobe's AI Content Visibility Checker per page (served words ÷ rendered words) and
attributes the gap per block (`deploy/reference/ai-readability.md`).
The `editability` check is the post-deploy **Experience Workspace
editability gate** (deploy SKILL.md § 8, EW1–EW10): per page it re-creates
the da.live canvas's instrumentation on the served document, lets the live
page decorate, and counts which authored texts still carry their editor
index. `editability/dead-text` (error) = a block rebuilt authored text and
the author cannot click it in the canvas; `editability/duplicated-index`
(warn) = a presentational clone kept the index. Dead texts inside blocks
declared `@ew-exempt` (or listed in `--ew-exempt`) are info, not errors.
First run on a site: expect a wave of `visual/baseline-created` info findings —
that is the baseline being established, not a defect. Baselines are
screenshots and therefore local (`stardust/.gitignore` excludes
`qa/baselines/` and `qa/shots/`, master skill § Artifacts): later runs on the
same machine diff against them; a fresh clone re-establishes them on its
first sweep. `qa/allowlist.json` is the tracked record of judgement.
### Phase 2 — triage the ambiguous flags (LLM judgment, still read-only)
The deterministic sweep marks two finding classes as *needs triage*; read
`report.json` and judge only those:
- `content/verbatim-below-threshold` — inspect `evidence.missingNodes` against
the live page and the scrape capture: is copy actually lost/corrupted
(defect) or acceptably transformed (candidate for the allowlist)?
- `visual/visual-diff` — open `evidence.baseline` and `evidence.current`
side by side (they are PNGs; view them): real layout/style regression, or
benign dynamism (carousel frame, loaded font, live embed)? Use the
`bands` evidence to locate the changed region.
Record each verdict by **annotating the finding** in your summary to the user
(defect vs non-defect + why). Do not edit `report.json` scores and do not fix
anything.
### Phase 3 — report to the user
Summarize: totals by severity, the confirmed defects first (with page paths
and one-line evidence), then triaged-away flags with their rationale, then
notable warns. Point at `stardust/qa/report.html`. Recommend — but do not
apply — fixes.
### Allowlist workflow (documented non-defects)
`stardust/qa/allowlist.json` (schema in `schemas/qa-allowlist.schema.json`)
keeps known non-defects from drowning every future run — e.g. a source page
that itself ships placeholder copy, or a form endpoint deliberately awaiting a
client credential. Entries match on check/id/path/messagePattern and **must
carry a reason**. Allowlisted findings stay in the report, greyed out, so the
evidence is never deleted.
Only add an entry when the user confirms the flag is a non-defect (or it is
already documented as one in the project's records). Never allowlist to make
a run green.
## Read-only contract
- Writes only under `stardust/qa/` (plus the `status.jsonl` ledger line).
- Never invokes deploy/publish APIs, never PUTs to DA, never edits blocks,
styles, or content — even for "trivial" fixes the sweep itself surfaced.
- Reports failure honestly: a crashed check appears in the report as
`<check>/check-crashed` (error), never silently dropped.
## Scheduling / CI
The runner is plain node with no plugin-runtime dependency, so the same
command works from a GitHub Action or cron for drift monitoring; `--fail-on`
sets the gate. In CI without playwright, pin `--checks` to the delivery-layer
subset.
© adobe · Apache-2.0 · adobe/skills
Похожие скиллы
Все скиллы по теме «Тесты и QA» →Сначала — qa от других авторов.