dym-browser-use-qa

dym-browser-use-qa is a skill for Claude Code from Rheinmir/setup. It costs 101 tokens per session (1,356 once invoked), scanned A, original, MIT.

A browser-based quality check that scores whether a website or app completes a user task, using screenshots and recorded errors as evidence. It checks both what users see and failures reported by the browser.

In plain words
What is it for?
Use it to review flows such as sign-up, form submission, or navigation and produce a defensible UI or UX verdict.
Why use it?
It replaces a subjective visual opinion with a result tied to a concrete task. It can reveal console, network, and interaction errors that a screenshot may miss.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to review flows such as sign-up, form submission, or navigation and produce a defensible UI or UX verdict.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rheinmir/setup/dym-browser-use-qa
Install

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.

Any agent
npx skills add Rheinmir/setup --skill dym-browser-use-qa
Clone the repo
git clone --depth 1 https://github.com/Rheinmir/setup

Made for: Claude Code.

Wrote 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.

agentmods badge for dym-browser-use-qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/rheinmir/setup/dym-browser-use-qa/github.svg)](https://agentmods.dev/skills/rheinmir/setup/dym-browser-use-qa)
Your own site
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-browser-use-qa"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-browser-use-qa/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dym-browser-use-qa

Your own site · 80×15
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-browser-use-qa"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-browser-use-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,356 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00101 $0.01356
Opus 5.5 $0.00040 $0.00542
Sonnet 5.5 $0.00020 $0.00271
Haiku 4.5 $0.00010 $0.00136

Measured yesterday against content hash 20ba7704db59, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dym-browser-use-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 yesterday.

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.

.overstack/doyourmagic/browser-use/skills/dym-browser-use-qa/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dym-browser-use-qa

Chắt từ skills/qa/references/methodology.md của browser-use (đọc 09/2026). Phần đáng lấy nhất KHÔNG phải cách lái trình duyệt — mà là kỷ luật ra verdict.

When to use

  • Cần một câu trả lời "tốt/xấu mức nào" có số, không phải "đây là ảnh chụp, anh xem đi".
  • /br qc hoặc /qc-uiux cần một mục chấm UI/UX đứng vững trước phản biện.

Steps

  1. Diễn lại yêu cầu thành một tác vụ người dùng cụ thể — "test signup" → "tạo tài khoản bằng email mới → tới được dashboard". Định nghĩa thành công TRƯỚC khi chạm trình duyệt. Yêu cầu mơ hồ → chọn happy path hiển nhiên nhất và ghi rõ đã chọn gì trong báo cáo.
  2. Lái như người dùng thật — /dym-browser-use repl cho luồng nhiều bước. Chụp ảnh sau MỖI hành động có ý nghĩa và kiểm chứng trang đổi đúng như kỳ vọng — đừng giả định cú bấm đã ăn.
  3. Moi lỗi ảnh chụp không thấy sau mỗi bước — drain_events() lọc Runtime.exceptionThrown, Runtime.consoleAPICalled type=="error", Network.loadingFailed, Network.responseReceived status>=400. Một trang trông đẹp nhưng ném lỗi ở mọi cú bấm không phải điểm 5.
  4. Thăm dò quá happy path một nhịp — submit trường bắt buộc để trống, email sai định dạng, nút back. Sản phẩm tốt xử lý êm; sản phẩm hỏng rò stack trace hoặc im lặng không phản hồi.
  5. Chấm, kèm dẫn chứng.

Thang điểm

Điểm Nghĩa
5 Tác vụ xong sạch. Không lỗi, không vướng, phản hồi nhanh, chỉn chu.
4 Tác vụ xong. Vướng vặt về thẩm mỹ/UX (tải chậm, chữ khó hiểu, một console warning) nhưng không chặn.
3 Tác vụ xong nhưng có ma sát thật — một bước rối, phải lách, một lỗi không chặn. Dùng được, không tốt.
2 Chỉ xong một phần. Một bug đáng kể chặn mất một đoạn, hoặc phải thử lại mới qua.
1 Không xong được. Nút chết, crash, spinner vô tận, trang không tải, mất dữ liệu.

Neo điểm vào HOÀN THÀNH TÁC VỤ trước, rồi mới chỉnh theo lỗi và độ chỉn chu. "Chạy được nhưng ném 3 lỗi console" là 3–4, không phải 5. "Đẹp nhưng nút submit không làm gì" là 1, không phải 4 — đẹp không cứu được luồng gãy.

Read the full file on GitHub · 80 lines

Changes

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.

  1. yesterday First seen · 80 lines · 101 tokens per session scan A 20ba7704db59

Subscribe to this mod's changes

dym-browser-use-qa is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 101 tokens to every session and 1,356 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-11-07.

Related

dym-browser-use-qa compared with skills from other repositories

dym-browser-use-qa next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dym-browser-use-qaRheinmir/setupSkill1120d agoMITA101Claude Code
cua-driverdavidondrej/skillsSkill4.3k2d agoMITA68Claude Code, Codex
create-verification-skillget-bb/bbSkill5.1ktodayMITA57Claude Code, Codex
webapp-testinganthropics/skillsSkill189kyesterdaynoneA35Claude Code
browser-qahashgraph-online/awesome-codex-pluginsSkill1.5kyesterdayApache-2.0A58Claude Code, Codex
test-electron-appPostHog/posthog-fossSkill728todayMITA112Claude Code
smoke-testSkyvern-AI/skyvernSkill23ktodayAGPL-3.0A50Claude Code, Codex