Skip to main content
skill CX Codex

qa · adobe — Claude Code skill: what it does, how to install

Runs an automated read-only QA sweep on deployed AEM Edge Delivery Services sites. It spots regressions, template flaws, and broken links without editing code.

Apache-2.0 253 installs ★ 335 updated 2026-11-14

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add adobe/skills --skill qa -a claude-code
Open on GitHub

What qa does

The skill performs a read-only audit on a live website. It checks delivery layers, template conformance, SEO metadata, JSON-LD, axe accessibility, and broken links. During browser inspection, it flags JavaScript errors, missing images, and distorted block geometry.

Audit artifacts are saved directly to stardust/qa/, producing report.html, report.json, and visual screenshots in stardust/qa/shots/. The tool never modifies repository code, site documents, or live pages. On repeated runs, visual diffs are compared against stored baselines in stardust/qa/baselines/.

Running full browser checks requires Node 22+, Playwright with Chromium in project dependencies, playwright-cli on PATH, and the impeccable skill installed alongside stardust. Without Playwright, the tool skips rendering and runs delivery checks only.

What it helps with

  • detect broken links and JavaScript errors on a live deployment
  • validate template conformance and axe accessibility standards
  • catch visual regressions against saved baseline screenshots
  • verify Experience Workspace block editability flags

Example prompts for the agent

  • Run a full QA sweep on the live site using /stardust:qa <live-url>
  • Check the deployed pages for broken images and visual differences
  • Inspect live site metadata and template conformance against the scrape

How to install qa

1Skills CLI (Vercel)

npx skills add adobe/skills --skill qa -a claude-code

2Manually: put the files in place

~/.claude/skills/qa/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/qa/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about qa

How to install qa in Claude Code?

Install the skill by running npx skills add adobe/skills --skill qa -a claude-code. It saves the skill definition file to ~/.claude/skills/qa/SKILL.md.

Does the qa skill fix detected defects automatically?

No, this skill is strictly read-only and never modifies code or site content. It writes findings and screenshots into stardust/qa/ for human review.

What prerequisites are needed for browser-level checks?

You need Node 22+, Playwright with Chromium resolvable in the project, playwright-cli on your PATH, and the impeccable skill. Without Playwright, only delivery-layer checks run.

Source text

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

Similar skills

All skills for Testing and QA →

qa by other authors comes first.

qa garrytan qa is a Claude Code skill that tests sites, APIs, and CLIs, then fixes bugs it finds. It responds to requests to test a site or look for errors. CX Codex +1 513installs qa SethGammon qa launches a real Chromium browser, clicks UI elements, tests frontend user flows, and writes a report with screenshots. CX Codex +1 ★ 937repo stars ui-regression fcakyon ui-regression verifies web apps and browser extensions on localhost, staging, or production across user flows, recovery states, locales, and viewports. CX Codex +1 ★ 1,216repo stars dx-aem easingthemes dx-aem is a Claude Code plugin for Adobe Experience Manager: it checks components, inspects dialogs, captures demos and runs Playwright QA. ★ 8repo stars qa-test-planner softaworks Turns a feature description into a test plan, manual test cases, a regression suite or a bug report. Fires only when you name it: qa-test-planner. CX Codex +1 4,400installs test-suite-curation kindlmann test-suite-curation is a Claude Code skill that audits a regression suite for duplicate, outdated, and low-value tests. It activates on requests to review the suite or split it into smoke, core, and extended tiers. CX Codex +1 1,300installs browse-qa ulpi-io browse-qa is a skill that turns feature requests into explicit QA scenarios, runs them through browse, and saves stable flows for regression checks. CX Codex +1 148installs cross-browser-testing kindlmann cross-browser-testing — a skill that picks which browsers to test, wires them into Playwright or a cloud grid, and keeps a log of known engine divergences. CX Codex +1 1,400installs

From the same set108

The whole set →
page-reduce The page-reduce skill turns a webpage into a structural skeleton with tokens for content and interface elements. Use it to map a page for an AEM Edge Delivery Services migration or block planning. CX Codex +1 281installs domain-mask domain-mask shows a real URL under a clean domain through a local HTTPS proxy with a trusted certificate. For demos, screen recordings and screenshots. CX Codex +1 281installs page-prep page-prep is a Claude Code skill that detects and clears cookie banners, paywalls, and blocking modals before web scraping or taking screenshots via Playwright CLI. CX Codex +1 281installs commerce-app-migrate commerce-app-migrate migrates Adobe Commerce App Builder projects from starter kits to the App Management approach. Runs in the project root. CX Codex +1 256installs run-workflow Routes agent requests to the run-workflow MCP server. It lets an agent build, run, publish, and save Adobe Firefly workflows. CX Codex +1 250installs appbuilder-workfront appbuilder-workfront is a Claude Code skill that routes Workfront UI extension projects on Adobe App Builder to skills for front end, serverless actions, and testing. CX Codex +1 245installs wf-planning-solution-architect wf-planning-solution-architect — a skill for designing and troubleshooting Adobe Workfront Planning workspaces: record-type hierarchies, formulas, API limits, and tier selection. CX Codex +1 223installs figma-to-content figma-to-content turns a Figma page design into an AEM Edge Delivery Services page in Document Authoring. It maps sections to project blocks and deploys the result. CX Codex +1 222installs

Project sponsors

Companies that keep this analytics open