[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F7YBWKBAPQR8EBDDGX2YF9":3,"skill-same:01M7F7YBWKBAPQR8EBDDGX2YF9":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7F7YBWKBAPQR8EBDDGX2YF9","browser-qa",null,"Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fbrowser-qa\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: browser-qa\ndescription: Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.\nmetadata:\n  origin: ECC\n---\n\n# Browser QA — Automated Visual Testing & Interaction\n\n## When to Use\n\n- After deploying a feature to staging\u002Fpreview\n- When you need to verify UI behavior across pages\n- Before shipping — confirm layouts, forms, interactions actually work\n- When reviewing PRs that touch frontend code\n- Accessibility audits and responsive testing\n\n## How It Works\n\nUses the browser automation MCP (claude-in-chrome, Playwright, or Puppeteer) to interact with live pages like a real user.\n\n### Safety first — blast radius (run read-only by default)\n\nBrowser QA drives real auth and real user journeys, so treat the blast radius explicitly.\nDefault to **read-only**: never run a **mutating** journey (checkout, payment, delete,\nmass-update) against a production URL — require an explicit opt-in **and** a staging\u002Fpreview\nURL. Use seeded **test credentials**, never real production logins, and **redact**\ncredentials\u002Ftokens\u002FPII before saving any screenshot.\n\n### Phase 1: Smoke Test\n```\n1. Navigate to target URL\n2. Check for console errors (filter noise: analytics, third-party)\n3. Verify no 4xx\u002F5xx in network requests\n4. Screenshot above-the-fold on desktop + mobile viewport\n5. Check Core Web Vitals: LCP \u003C 2.5s, CLS \u003C 0.1, INP \u003C 200ms\n   (INP replaced FID in March 2024; thresholds per web.dev)\n```\n\n### Phase 2: Interaction Test\n```\n1. Click every nav link — verify no dead links\n2. Submit forms with valid data — verify success state\n3. Submit forms with invalid data — verify error state\n4. Test auth flow: login → protected page → logout (test creds only, never prod)\n5. Test critical user journeys (checkout, onboarding, search)\n   — read-only by default; only exercise mutating journeys against staging\n     with explicit opt-in (see \"Safety first\" above)\n```\n\n### Phase 3: Visual Regression\n```\n1. Screenshot key pages at 3 breakpoints (375px, 768px, 1440px)\n2. Compare against committed baseline screenshots\n   — no baseline ⇒ report INCONCLUSIVE, never a silent PASS\n3. Flag layout shifts > 5px, missing elements, overflow\n4. Check dark mode if applicable\n```\n\n### Phase 4: Accessibility\n```\n1. Run axe-core or equivalent on each page\n2. Flag WCAG 2.2 AA violations (contrast, labels, focus order)\n3. Verify keyboard navigation works end-to-end\n4. Check screen reader landmarks\n```\n\n> Note: axe-core automatically covers roughly 30–40% of WCAG. A clean run is **necessary,\n> not sufficient** — keyboard nav, focus order, and a screen-reader pass still need a manual\n> check. Don't report \"accessible\" from an automated pass alone.\n\n## Output Format\n\n```markdown\n## QA Report — [URL] — [timestamp]\n\n### Smoke Test\n- Console errors: 0 critical, 2 warnings (analytics noise)\n- Network: all 200\u002F304, no failures\n- Core Web Vitals: LCP 1.2s ✓, CLS 0.02 ✓, INP 89ms ✓\n\n### Interactions\n- [✓] Nav links: 12\u002F12 working\n- [✗] Contact form: missing error state for invalid email\n- [✓] Auth flow: login\u002Flogout working\n\n### Visual\n- [✗] Hero section overflows on 375px viewport\n- [✓] Dark mode: all pages consistent\n\n### Accessibility\n- 2 AA violations: missing alt text on hero image, low contrast on footer links\n\n### Verdict: SHIP WITH FIXES (2 issues, 0 blockers)\n# verdict ∈ SHIP \u002F SHIP WITH FIXES \u002F DO NOT SHIP; use INCONCLUSIVE if no visual baseline\n```\n\n## Integration\n\nWorks with any browser MCP:\n- `mChild__claude-in-chrome__*` tools (preferred — uses your actual Chrome)\n- Playwright via `mcp__browserbase__*`\n- Direct Puppeteer scripts\n\nPair with `\u002Fcanary-watch` for post-deploy monitoring.\n","# Browser QA — Automated Visual Testing & Interaction\n\n## When to Use\n\n- After deploying a feature to staging\u002Fpreview\n- When you need to verify UI behavior across pages\n- Before shipping — confirm layouts, forms, interactions actually work\n- When reviewing PRs that touch frontend code\n- Accessibility audits and responsive testing\n\n## How It Works\n\nUses the browser automation MCP (claude-in-chrome, Playwright, or Puppeteer) to interact with live pages like a real user.\n\n### Safety first — blast radius (run read-only by default)\n\nBrowser QA drives real auth and real user journeys, so treat the blast radius explicitly.\nDefault to **read-only**: never run a **mutating** journey (checkout, payment, delete,\nmass-update) against a production URL — require an explicit opt-in **and** a staging\u002Fpreview\nURL. Use seeded **test credentials**, never real production logins, and **redact**\ncredentials\u002Ftokens\u002FPII before saving any screenshot.\n\n### Phase 1: Smoke Test\n```\n1. Navigate to target URL\n2. Check for console errors (filter noise: analytics, third-party)\n3. Verify no 4xx\u002F5xx in network requests\n4. Screenshot above-the-fold on desktop + mobile viewport\n5. Check Core Web Vitals: LCP \u003C 2.5s, CLS \u003C 0.1, INP \u003C 200ms\n   (INP replaced FID in March 2024; thresholds per web.dev)\n```\n\n### Phase 2: Interaction Test\n```\n1. Click every nav link — verify no dead links\n2. Submit forms with valid data — verify success state\n3. Submit forms with invalid data — verify error state\n4. Test auth flow: login → protected page → logout (test creds only, never prod)\n5. Test critical user journeys (checkout, onboarding, search)\n   — read-only by default; only exercise mutating journeys against staging\n     with explicit opt-in (see \"Safety first\" above)\n```\n\n### Phase 3: Visual Regression\n```\n1. Screenshot key pages at 3 breakpoints (375px, 768px, 1440px)\n2. Compare against committed baseline screenshots\n   — no baseline ⇒ report INCONCLUSIVE, never a silent PASS\n3. Flag layout shifts > 5px, missing elements, overflow\n4. Check dark mode if applicable\n```\n\n### Phase 4: Accessibility\n```\n1. Run axe-core or equivalent on each page\n2. Flag WCAG 2.2 AA violations (contrast, labels, focus order)\n3. Verify keyboard navigation works end-to-end\n4. Check screen reader landmarks\n```\n\n> Note: axe-core automatically covers roughly 30–40% of WCAG. A clean run is **necessary,\n> not sufficient** — keyboard nav, focus order, and a screen-reader pass still need a manual\n> check. Don't report \"accessible\" from an automated pass alone.\n\n## Output Format\n\n```markdown\n## QA Report — [URL] — [timestamp]\n\n### Smoke Test\n- Console errors: 0 critical, 2 warnings (analytics noise)\n- Network: all 200\u002F304, no failures\n- Core Web Vitals: LCP 1.2s ✓, CLS 0.02 ✓, INP 89ms ✓\n\n### Interactions\n- [✓] Nav links: 12\u002F12 working\n- [✗] Contact form: missing error state for invalid email\n- [✓] Auth flow: login\u002Flogout working\n\n### Visual\n- [✗] Hero section overflows on 375px viewport\n- [✓] Dark mode: all pages consistent\n\n### Accessibility\n- 2 AA violations: missing alt text on hero image, low contrast on footer links\n\n### Verdict: SHIP WITH FIXES (2 issues, 0 blockers)\n# verdict ∈ SHIP \u002F SHIP WITH FIXES \u002F DO NOT SHIP; use INCONCLUSIVE if no visual baseline\n```\n\n## Integration\n\nWorks with any browser MCP:\n- `mChild__claude-in-chrome__*` tools (preferred — uses your actual Chrome)\n- Playwright via `mcp__browserbase__*`\n- Direct Puppeteer scripts\n\nPair with `\u002Fcanary-watch` for post-deploy monitoring.\n",{"name":5,"metadata":24,"description":7},{"origin":25},"ECC","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fbrowser-qa",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill browser-qa",{"tool":40,"command":41},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill browser-qa",{"tool":43,"command":44},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill browser-qa","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fbrowser-qa\u002FSKILL.md",true,[],[49,56,61,68,75,82],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":57,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]