Adobe Skills is a collection of skills, plugins, agents, and MCP servers that extend AI coding agents with workflows for Adobe products and other tasks. Developers use it to help coding agents work with Adobe analytics and application-building tools. The catalogue entries are the repository’s own skills, plugins, agents, and MCP integrations.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/adobe/skills/qanpx skills add adobe/skills --skill qagit clone --depth 1 https://github.com/adobe/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/adobe/skills/qa)<a href="https://agentmods.dev/skills/adobe/skills/qa"><img src="https://agentmods.dev/badge/skills/adobe/skills/qa.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00138 | $0.01715 |
| Opus 5 | $0.00069 | $0.00857 |
| Sonnet 5 | $0.00028 | $0.00343 |
| Haiku 4.5 | $0.00014 | $0.00171 |
Grade A, and why
qa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
- delivery — what the pipeline serves (
.plain.html, full HTML, sheets, sitemap) - rendered — what a browser shows after block decoration
- 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
- Run the master skill's setup (
skills/stardust/SKILL.md§ Setup) if not already done this session.qaworks standalone too — it only needs a live base URL. - Resolve the base URL (the
*.aem.livehost or production domain). If the user didn't give one, look instardust/rollout/rollout.json(site.liveHost) or ask. - Resolve the inventory source — what pages the sweep covers, merged from
any of:
stardust/template-map.json(also supplies template assignments for conformance), a paths file, and the livesitemap.xml(always fetched; parity mismatches become findings, so a wrong sitemap can't silently shrink coverage). - Optional inputs that unlock deeper checks:
--scrape stardust/scrape— verbatim fidelity vs the extraction capture--expected-blocks <json>— explicit per-template block expectations (otherwise derived by fleet consensus)--blocks-dir <dir>— the site'sblocks/checkout, so theeditabilitycheck can honour@ew-exemptJSDoc tags (otherwise pass--ew-exempt a,bfor index-driven blocks)
- 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. - Append a phase-transition line to
stardust/status.jsonlperreference/run-status.md(master skill) at sweep start/end.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/checks.md 11 KB
- schemas/qa-allowlist.schema.json 1.2 KB
- schemas/qa-report.schema.json 2.1 KB
- scripts/checks/browse.mjs 15 KB runs code
- scripts/checks/content.mjs 19 KB runs code
- scripts/checks/editability.mjs 4.3 KB runs code
- scripts/checks/links.mjs 7.3 KB runs code
- scripts/checks/metadata.mjs 5.3 KB runs code
- scripts/checks/perf.mjs 5.0 KB runs code
- scripts/checks/routing.mjs 4.8 KB runs code
- scripts/checks/templates.mjs 3.8 KB runs code
- scripts/lib.mjs 11 KB runs code
- scripts/qa.mjs 7.2 KB runs code
- scripts/report-html.mjs 10 KB runs code
- scripts/test/flattened.test.mjs 2.3 KB runs code
- scripts/test/single-block-hoard.test.mjs 4.3 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +12 lines 51ea09f3c91c
- yesterday First seen · 121 lines · 138 tokens per session scan A 3ea39f64ae5f
qa is a skill published in the GitHub repository adobe/skills (177 stars, last pushed today), licensed Apache-2.0. It adds 138 tokens to every session and 1,715 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…
actionbook-web-test
Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…
winui-ui-testing
Automated UI testing for Windows desktop apps — generate a batch test script with the winapp ui UI Automation harness, run all tests in one pass, read results. Covers element assertions, interactions, value checking (TextBox, ComboBox, ToggleSwitch), keyboard shortcuts and typing (send-keys), hover, drag-and-drop…
web-test
Тестирование 1С через веб-клиент — автоматизация действий в браузере. Используй когда пользователь просит проверить, протестировать, автоматизировать действия в 1С через браузер.
testing-strategies
Comprehensive testing strategy covering unit, integration, e2e, property-based, and mutation testing with practical patterns.
mcp-case-overrides
Per-case mocked MCP override smoke skill used by skill-up e2e tests.