Files
claude-skills-reference/docs/skills/engineering-team/playwright-pro-browserstack.md
Alireza Rezvani 5adbfdce47 release: sync dev → main — a11y-audit, /seo-auditor, /plugin-audit, 28 plugins (#380)
* fix: add missing plugin.json files and restore trailing newlines

- Add plugin.json for review-fix-a11y skill
- Add plugin.json for free-llm-api skill
- Restore POSIX-compliant trailing newlines in JSON index files

* feat(engineering): add review-fix-a11y skill (WCAG 2.2 a11y audit + fix) (#375)

Adds review-fix-a11y (WCAG 2.2 a11y audit + fix) and free-llm-api skills.

Includes:
- review-fix-a11y: WCAG 2.2 audit workflow, a11y_audit.py scanner, contrast_checker.py
- free-llm-api: ChatAnywhere, Groq, Cerebras, OpenRouter, llm-mux, One API setup
- secret_scanner.py upgrade with secrets-patterns-db integration (1,600+ patterns)

Co-authored-by: ivanopenclaw223-alt <ivanopenclaw223-alt@users.noreply.github.com>

* chore: sync codex skills symlinks [automated]

* Revert "feat(engineering): add review-fix-a11y skill (WCAG 2.2 a11y audit + fix) (#375)"

This reverts commit 49c9f2109f.

* chore: sync codex skills symlinks [automated]

* Revert "feat(engineering): add review-fix-a11y skill (WCAG 2.2 a11y audit + fix) (#375)"

This reverts commit 49c9f2109f.

* feat(engineering-team): add a11y-audit skill — WCAG 2.2 accessibility audit & fix (#376)

Built from scratch (replaces reverted PR #375 contribution).

Skill package:
- SKILL.md: 1132 lines, 3-phase workflow (scan → fix → verify),
  per-framework fix patterns (React, Next.js, Vue, Angular, Svelte, HTML),
  CI/CD integration guide, 20+ issue type coverage
- scripts/a11y_scanner.py: static scanner detecting 20+ violation types
  across HTML/JSX/TSX/Vue/Svelte/CSS — severity-ranked, CI-friendly exit codes
- scripts/contrast_checker.py: WCAG contrast calculator with AA/AAA checks,
  --suggest mode, --batch CSS scanning, named color support
- references/wcag-quick-ref.md: WCAG 2.2 Level A/AA criteria table
- references/aria-patterns.md: ARIA roles, live regions, keyboard interaction
- references/framework-a11y-patterns.md: React, Vue, Angular, Svelte fix patterns
- assets/sample-component.tsx: sample file with intentional violations
- expected_outputs/: scan report, contrast output, JSON output samples
- /a11y-audit slash command, settings.json, plugin.json, README.md

Validation: 97.6/100 (EXCELLENT), quality 73.9/100 (B-), scripts 2/2 PASS

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: sync codex skills symlinks [automated]

* docs: sync counts across all docs — 205 skills, 268 tools, 19 commands, 22 plugins

Update CLAUDE.md, README.md, docs/index.md, docs/getting-started.md,
mkdocs.yml, marketplace.json with consistent counts. Sync Gemini CLI
index with new skills (code-to-prd, plugin-audit).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(marketplace): add 6 missing standalone plugins — total 22→28

Added to marketplace:
- a11y-audit (WCAG 2.2 accessibility audit)
- executive-mentor (adversarial thinking partner)
- docker-development (Dockerfile, compose, multi-stage)
- helm-chart-builder (Helm chart scaffolding)
- terraform-patterns (IaC module design)
- research-summarizer (structured research synthesis)

Also fixed version 1.0.0 → 2.1.2 on 4 plugin.json files
(executive-mentor, docker-development, helm-chart-builder, research-summarizer)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(commands): add /seo-auditor — 7-phase SEO audit pipeline for documentation

- 7 phases: discovery → meta tags → content quality → keywords → links → sitemap → report
- Integrates 8 marketing-skill scripts: seo_checker, content_scorer,
  humanizer_scorer, headline_scorer, seo_optimizer, sitemap_analyzer,
  schema_validator, topic_cluster_mapper
- References 6 SEO knowledge bases for audit framework, AI search,
  content optimization, URL design, internal linking, AI detection
- Auto-fixes: generic titles, missing descriptions, broken links, orphan pages
- Preserves high-ranking pages — only fixes critical issues on those
- Registered in both commands/ (distributable) and .claude/commands/ (local)

Also: sync all doc counts — 28 plugins, 26 eng-core skills, 21 commands

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix(seo): fix multi-line YAML description parser, add 2 orphan pages to nav

- generate-docs.py: extract_description_from_frontmatter() now handles
  multi-line YAML block scalars (|, >, indented continuation) — fixes
  14 pages that had 56-65 char truncated descriptions
- mkdocs.yml: add epic-design and research-summarizer to nav (orphan pages)
- Regenerated 251 pages, rebuilt sitemap (278 URLs)
- SEO audit: 0 broken links, 17→3 short descriptions, 278/278 pages
  have "Claude Code Skills" in <title>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Leo <leo@openclaw.ai>
Co-authored-by: ivanopenclaw223-alt <ivanopenclaw223@gmail.com>
Co-authored-by: ivanopenclaw223-alt <ivanopenclaw223-alt@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 13:03:48 +01:00

5.0 KiB

title, description
title description
BrowserStack Integration — Agent Skill & Codex Plugin Run tests on BrowserStack. Use when user mentions 'browserstack', 'cross-browser', 'cloud testing', 'browser matrix', 'test on safari', 'test on. Agent skill for Claude Code, Codex CLI, Gemini CLI, OpenClaw.

BrowserStack Integration

:material-code-braces: Engineering - Core :material-identifier: `browserstack` :material-github: Source
Install: claude /plugin install engineering-skills

Run Playwright tests on BrowserStack's cloud grid for cross-browser and cross-device testing.

Prerequisites

Environment variables must be set:

  • BROWSERSTACK_USERNAME — your BrowserStack username
  • BROWSERSTACK_ACCESS_KEY — your access key

If not set, inform the user how to get them from browserstack.com/accounts/settings and stop.

Capabilities

1. Configure for BrowserStack

/pw:browserstack setup

Steps:

  1. Check current playwright.config.ts
  2. Add BrowserStack connect options:
// Add to playwright.config.ts
import { defineConfig } from '@playwright/test';

const isBS = !!process.env.BROWSERSTACK_USERNAME;

export default defineConfig({
  // ... existing config
  projects: isBS ? [
    {
      name: "chromelatestwindows-11",
      use: {
        connectOptions: {
          wsEndpoint: `wss://cdp.browserstack.com/playwright?caps=${encodeURIComponent(JSON.stringify({
            'browser': 'chrome',
            'browser_version': 'latest',
            'os': 'Windows',
            'os_version': '11',
            'browserstack.username': process.env.BROWSERSTACK_USERNAME,
            'browserstack.accessKey': process.env.BROWSERSTACK_ACCESS_KEY,
          }))}`,
        },
      },
    },
    {
      name: "firefoxlatestwindows-11",
      use: {
        connectOptions: {
          wsEndpoint: `wss://cdp.browserstack.com/playwright?caps=${encodeURIComponent(JSON.stringify({
            'browser': 'playwright-firefox',
            'browser_version': 'latest',
            'os': 'Windows',
            'os_version': '11',
            'browserstack.username': process.env.BROWSERSTACK_USERNAME,
            'browserstack.accessKey': process.env.BROWSERSTACK_ACCESS_KEY,
          }))}`,
        },
      },
    },
    {
      name: "webkitlatestos-x-ventura",
      use: {
        connectOptions: {
          wsEndpoint: `wss://cdp.browserstack.com/playwright?caps=${encodeURIComponent(JSON.stringify({
            'browser': 'playwright-webkit',
            'browser_version': 'latest',
            'os': 'OS X',
            'os_version': 'Ventura',
            'browserstack.username': process.env.BROWSERSTACK_USERNAME,
            'browserstack.accessKey': process.env.BROWSERSTACK_ACCESS_KEY,
          }))}`,
        },
      },
    },
  ] : [
    // ... local projects fallback
  ],
});
  1. Add npm script: "test:e2e:cloud": "npx playwright test --project='chrome@*' --project='firefox@*' --project='webkit@*'"

2. Run Tests on BrowserStack

/pw:browserstack run

Steps:

  1. Verify credentials are set
  2. Run tests with BrowserStack projects:
    BROWSERSTACK_USERNAME=$BROWSERSTACK_USERNAME \
    BROWSERSTACK_ACCESS_KEY=$BROWSERSTACK_ACCESS_KEY \
    npx playwright test --project='chrome@*' --project='firefox@*'
    
  3. Monitor execution
  4. Report results per browser

3. Get Build Results

/pw:browserstack results

Steps:

  1. Call browserstack_get_builds MCP tool
  2. Get latest build's sessions
  3. For each session:
    • Status (pass/fail)
    • Browser and OS
    • Duration
    • Video URL
    • Log URLs
  4. Format as summary table

4. Check Available Browsers

/pw:browserstack browsers

Steps:

  1. Call browserstack_get_browsers MCP tool
  2. Filter for Playwright-compatible browsers
  3. Display available browser/OS combinations

5. Local Testing

/pw:browserstack local

For testing localhost or staging behind firewall:

  1. Install BrowserStack Local: npm install -D browserstack-local
  2. Add local tunnel to config
  3. Provide setup instructions

MCP Tools Used

Tool When
browserstack_get_plan Check account limits
browserstack_get_browsers List available browsers
browserstack_get_builds List recent builds
browserstack_get_sessions Get sessions in a build
browserstack_get_session Get session details (video, logs)
browserstack_update_session Mark pass/fail
browserstack_get_logs Get text/network logs

Output

  • Cross-browser test results table
  • Per-browser pass/fail status
  • Links to BrowserStack dashboard for video/screenshots
  • Any browser-specific failures highlighted