vkirill/claude-lane-stack/browser-qa

Claude Code and agent skill by vkirill/claude-lane-stack

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Live browser QA + Playwright-compatible replay. Disk .agents/qa/. Use when (terminal Lane Stack): проверь в браузере, кликни сценарий, вёрстка 375, screenshot QA. SKIP: Lane Pilot chats (PM calls `lane_pilot_browser_qa`); DESIGN.md taste (design-lead); product Vue/CSS (writer lane); L0/L1 unit/API (lane-contract).

Install

npx vskill@latest install vkirill/claude-lane-stack/browser-qa

SKILL.md

The same SKILL.md was published earlier as vkirill/claude-lane-stack/browser-qa.

Browser QA

Adapted from lee-to/ai-factory#154 replay rules. Paths and gates are lane-stack. No .ai-factory, no human «работает или нет».

Inside a Lane Pilot chat (LANE_PILOT_AGENT_TYPE set / tools lane_pilot_* present) do not run this file's replay and digest procedure. The PM checks an accepted task with lane_pilot_browser_qa; the check runs in a child thread through bb browser-automation (no MCP browser) and ends with the one fenced JSON verdict its prompt asks for, changing no files. .agents/qa/ replay, qa-digest, chrome-qa, browser-qa-jev and chrome-devtools below are the terminal harness. The PM does not click in its own chat.

Info

If $ARGUMENTS is exactly info, print references/info.md verbatim (Russian), then stop.

Layout

text
.agents/qa/context.md # cross-run, non-secret
.agents/qa/<slug>/
cases.md # source of truth for TC-*
REPORT.md # execution only; never overwrite cases
shots/
replay/TC-00N.js
replay/history/

Copy structure from references/ next to this skill. English on disk. Chat may be Russian. Redact tokens, cookies, OTP, password, jwt → [REDACTED].

Cases

PM / SPEC acceptance → cases.md. One ## TC-00N heading per case (see references/cases.md). Fields: Surface, Priority, Viewport, Preconditions, Steps, Expected.

SurfaceThis agent
browser-uiRequired. Live browser. Replay first.
cli / backend-test / apiDo not click. Note blocked: use L0/L1. No human array-checking.
humanLeave pending. The PM asks the operator.

Default viewports if omitted: 375 768 1280.

Bindings

bash
qa-digest cases .agents/qa/<slug>/cases.md
qa-digest script .agents/qa/<slug>/replay/TC-001.js
qa-digest target local 'http://127.0.0.1:5173/'
git -C . rev-parse HEAD

tree is clean if git status --porcelain has nothing except .agents/qa/; else dirty.

target_fingerprint input is QA TARGET\n<class>\n<normalized_base_url>\n. Normalize: drop userinfo, query, fragment; keep scheme/host/port/base path; strip trailing slash except origin /. Class: local | staging | preview | production | unknown.

Matching replay = embedded case_digest + embedded target_fingerprint + file script_digest all equal REPORT's last proven values.

Stale (uncheck, keep old evidence, do not count as current):

  • HEAD or tree changed → all results stale; scripts stay reusable if matching
  • cases.md source_digest changed → stale only cases whose case_digest changed
  • new TC → pending; removed TC → Stale / removed
  • script bytes ≠ recorded script digest → that case stale, needs proof run
  • missing digest metadata → unproven, not matching

Replay (PR #154)

One case → replay/TC-00N.js. Smallest async (page) => { … }. No imports, no new npm deps. Navigation uses the literal "BASE_URL" placeholder. At run time substitute normalized_base_url in memory; do not rewrite the file just to inject the host.

js
// case_digest: <from qa-digest cases>
// target_fingerprint: <from qa-digest target>
async (page) => { /* goto("BASE_URL"+"/…"); asserts throw */ };
  1. Write the script before the first click. That first execution is the proof. Do not auto-run a new/updated script a second time.
  2. If mechanics were clarified after the observed run and the file changed, mark unproven. Repeat only after preconditions restored. Stateful (submit, pay, delete, email, permissions) needs a fresh go-ahead that says this is a repeat.
  3. Record script_digest as proven only after that exact file executed. Until then: n/a, proof unproven.
  4. Before repair/rebind: cp to replay/history/TC-00N-<old_script_digest>.js. Keep the first error in REPORT. Never run history.
  5. Missing selector = product fail until the same control and behavior are proven in-browser and only the locator changed. Do not pick a similar element. Syntax/runner errors may be repaired (new proof). Assertion mismatch = fail, not a reason to regenerate the script.
  6. Target mismatch → stop. Rebind changes script_digest and needs a new proof. Never treat a staging script as matching localhost.
  7. After HEAD/tree change: replay every matching script (old pass and fail). Capability and side-effect rules still apply.
  8. proven means the script ran, not that the product passed.
  9. Discrete chrome-devtools actions: treat the file as the program; do not rewrite steps because the surface is MCP not npx playwright.
  10. After replay, at most one bounded exploratory pass when the change is cross-cutting (nav, auth, layout, shared state) or a replay needed repair. Skip when the fix is narrow and matching replay already covers it. New bug → REPORT only; add ## TC-00N first, then a script.

Delegation (stages.browser_qa)

providerWho clicksCommand
jev (default)CDP snapshot → Jev Choice (click/type/done). backend = chrome-qa \live-chrome \headlessbrowser-qa-jev --project-cwd . --url … --slug … --case "…"
codexCodex gpt-6-astra / low + browser pluginsbrowser-qa-codex --project-cwd . --url … --slug … --case "…"
claudethis agent via chrome-devtools MCPsteps below

browser-qa-jev writes cases.md, REPORT.md, shots/, jev-run.json. browser-qa-codex writes codex-run.json / codex-result.json. Replay scripts are not produced in jev/codex mode; receipt + shots are the proof.

Preflight

  1. Read .agents/qa/context.md if present (routes, how to start the app, test-user role). No secrets.
  2. Live browser: host-level chrome-devtools MCP (mcp__chrome-devtools__*: list_pages, new_page, navigate_page, take_snapshot, take_screenshot), else MetaMCP chrome-devtools, else existing project Playwright. If the MCP reports no browser, run chrome-qa start (dedicated profile, fixed port, no consent dialog) and retry once. No new dependency. None → every browser-ui case blocked. Do not write pass. WebFetch is not a browser.

Attached to the user's real Chrome (macOS --autoConnect, or --browserUrl): the server exposes every open tab. Create your own page with new_page, act only in pages you created, never snapshot, navigate or close other tabs, close yours when done, and prefer a dedicated QA profile for sensitive sites.

  1. production or unknown, or any side-effect case: do not run until the PM wrote authorized in the spawn prompt. Deny → blocked.
  2. Auth: reuse a safe local fixture from context/docs. Never store prod/personal passwords, cookies, OTP. Disposable local users only if the repo already has a seed command.

Run

  1. cd project root. Slug from PM or qa-<YYYYMMDD-HHMM>.
  2. Write or refresh cases.md from SPEC/acceptance. Do not invent URLs.
  3. qa-digest cases + qa-digest target. If REPORT exists, apply stale rules before changing statuses.
  4. Create REPORT from references/REPORT.md when missing. All new cases start pending.
  5. Each browser-ui case: matching replay first; else write script, run once, shots shots/TC-00N-<w>.png.
  6. Supporting L0/L1 commands may be listed; they do not count as extra TC results.
  7. Last line to PM: DONE .agents/qa/<slug>/REPORT.md plus fail list and 3–5 shots.

NEVER (each with its alternative)

  • Product Vue/TS/CSS and docs/DESIGN.md are not yours: report the defect in REPORT and leave the file.
  • A browser-ui case is pass only after a live browser run of that case; without a live browser it is blocked.
  • Work only in cases from cases.md; for anything else add a ## TC-00N first. This is the Playwright-replay harness, so no Human mode, .ai-factory or /aif-qa.
  • Credentials stay out of files, and the preview host stays out of scripts (BASE_URL placeholder).
  • Cleanup is read-only for shared state: no rm, git reset or shared DB wipe.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/vkirill/claude-lane-stack/browser-qa/badge)](https://verified-skill.com/skills/vkirill/claude-lane-stack/browser-qa)

Something wrong with this skill or its page? Tell us.