[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DVCW6MN1EWVQ22QNN2ZASN":3,"skill-same:01M7DVCW6MN1EWVQ22QNN2ZASN":75},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7DVCW6MN1EWVQ22QNN2ZASN","mk-qa-manual",null,"Spec-driven manual QA and Playwright E2E generation: navigates apps like a human tester, producing reports or .spec.ts files. Prompts for credentials. NOT for autonomous flows (mk:agent-browser).","ngocsangyem\u002FMeowKit","ngocsangyem","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F33769536?v=4","01M6J3FSMJAG9PVQEGRT7AQ9J2","Sang Nguyen","01M6J3FSRTJG0MNP6NV71639RM",16,"MIT","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-qa-manual\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"mk-qa-manual\"\ndescription: \"Spec-driven manual QA and Playwright E2E generation: navigates apps like a human tester, producing reports or .spec.ts files. Prompts for credentials. NOT for autonomous flows (mk:agent-browser).\"\n---\n\n\u003C!-- Design decisions:\n- Dynamic routing model: each action uses the best skill (Phase 1.2 routing tree)\n- Auth protocol: prompt-always — NEVER guess credentials (absolute constraint)\n- playwright-cli preferred for DOM interaction — generates PW code as side-effect\n- agent-browser preferred for auth flows — session persistence support\n- Role-based locators mandatory (getByRole, getByLabel) — not CSS selectors\n- Script for Playwright execution — deterministic, not LLM judgment\n-->\n\n# QA Manual Testing & E2E Code Generation\n\nOrchestrates browser skills to act like a human tester: navigate, interact, verify, and report.\n\n## When to Use\n\n**Trigger:** \"test this flow\", \"QA this page\", \"generate E2E tests\", \"test login flow\", \"manual testing\", \"write Playwright tests for\"\n\n**Explicit:**\n- `the qa-manual skill tasks\u002Fplans\u002F260315-auth-flow.md --report` → manual QA report\n- `the qa-manual skill tasks\u002Fplans\u002F260315-checkout.md --generate` → Playwright .spec.ts\n- `the qa-manual skill https:\u002F\u002Fapp.example.com` → explore and test from URL\n- `the qa-manual skill [spec]` → auto-detect use case from spec content\n\n## Workflow Integration\n\nOperates in **Phase 4 (Review)** for QA reports or **Phase 3 (Build)** for E2E code generation.\n\n## Skill Routing\n\nEach action uses the best browser skill:\n\n| Action | Skill | Why |\n|--------|-------|-----|\n| DOM interaction (click, fill, type) | `mk:playwright-cli` | Generates Playwright code as side-effect |\n| Navigation + page load | `mk:playwright-cli` | goto + wait, code output |\n| Visual verification (screenshot) | `mk:agent-browser` | Annotated snapshots |\n| Auth flow (login, session, MFA) | `mk:agent-browser` | Session persistence, auth import |\n| Execute Playwright test | Script: `npx playwright test` | Deterministic |\n\n## Authentication Protocol\n\n**On auth encounter** (login page, MFA, 401\u002F403):\n\n1. **STOP** current flow immediately\n2. **Show user:**\n   ```\n   ⚠️ Authentication required at: [current URL]\n   mk:qa-manual needs credentials to continue.\n   Please provide:\n   - Username\u002Femail: ___________\n   - Password: ___________\n   Type 'skip' to skip this flow or 'abort' to stop testing.\n   ```\n3. **WAIT** for user input — do NOT proceed without it\n4. On credentials → fill form using `mk:playwright-cli`, continue flow\n5. On 'skip' → mark flow SKIPPED, move to next\n6. On 'abort' → end session, output partial report\n\n**NEVER:** Guess credentials. Use hardcoded test credentials. Proceed past auth without input. Store credentials in any file.\n\n## Process\n\nSee `references\u002Fqa-process.md` for detailed Use Case A and Use Case B processes.\n\n**Use Case A — Manual QA:** Load spec → extract flows → navigate each → verify outcomes → report\n\n**Use Case B — E2E Code Gen:** Run Use Case A → record interactions → generate .spec.ts with role-based locators\n\n## Output Format\n\nSee `references\u002Foutput-templates.md` for full templates.\n\n**QA Report** → structured pass\u002Ffail per flow with evidence\n**Playwright Code** → production-ready .spec.ts using `getByRole`, `getByLabel`, `getByText`\n\n## Scripts\n\n| Script | Purpose | Invocation |\n|--------|---------|------------|\n| `scripts\u002Frun-playwright.sh` | Execute generated .spec.ts | After E2E code generation |\n\n## References\n\n| Reference | When to load | Content |\n|-----------|-------------|---------|\n| **[qa-process.md](.\u002Freferences\u002Fqa-process.md)** | Steps 1-4 | Detailed Use Case A + B processes |\n| **[output-templates.md](.\u002Freferences\u002Foutput-templates.md)** | Step output | QA report + Playwright code templates |\n\n## Failure Handling\n\n| Failure | Detection | Recovery | Message |\n|---------|-----------|----------|---------|\n| Auth encountered | URL\u002Fform patterns | Auth protocol above | \"⚠️ Authentication required...\" |\n| Page load timeout | 30s timeout | Retry ×2 then report | \"Page load timed out at [URL]\" |\n| Element not found | Selector fails | Re-snapshot, try alternate | \"Element not found, re-scanning...\" |\n| Spec not found | File missing | Ask user | \"Spec file not found. Provide path or URL.\" |\n| Playwright exec fails | Non-zero exit | Show error + fix hints | \"Test failed: [error]. Fix: [hint]\" |\n\n## Gotchas\n\n- **Testing against stale deployment**: Running E2E tests against yesterday's build → Verify deployment version matches expected before starting test run\n- **Credentials hardcoded in generated spec files**: Auto-generated .spec.ts contains login credentials → Always use environment variables for credentials; never inline in test code","\u003C!-- Design decisions:\n- Dynamic routing model: each action uses the best skill (Phase 1.2 routing tree)\n- Auth protocol: prompt-always — NEVER guess credentials (absolute constraint)\n- playwright-cli preferred for DOM interaction — generates PW code as side-effect\n- agent-browser preferred for auth flows — session persistence support\n- Role-based locators mandatory (getByRole, getByLabel) — not CSS selectors\n- Script for Playwright execution — deterministic, not LLM judgment\n-->\n\n# QA Manual Testing & E2E Code Generation\n\nOrchestrates browser skills to act like a human tester: navigate, interact, verify, and report.\n\n## When to Use\n\n**Trigger:** \"test this flow\", \"QA this page\", \"generate E2E tests\", \"test login flow\", \"manual testing\", \"write Playwright tests for\"\n\n**Explicit:**\n- `the qa-manual skill tasks\u002Fplans\u002F260315-auth-flow.md --report` → manual QA report\n- `the qa-manual skill tasks\u002Fplans\u002F260315-checkout.md --generate` → Playwright .spec.ts\n- `the qa-manual skill https:\u002F\u002Fapp.example.com` → explore and test from URL\n- `the qa-manual skill [spec]` → auto-detect use case from spec content\n\n## Workflow Integration\n\nOperates in **Phase 4 (Review)** for QA reports or **Phase 3 (Build)** for E2E code generation.\n\n## Skill Routing\n\nEach action uses the best browser skill:\n\n| Action | Skill | Why |\n|--------|-------|-----|\n| DOM interaction (click, fill, type) | `mk:playwright-cli` | Generates Playwright code as side-effect |\n| Navigation + page load | `mk:playwright-cli` | goto + wait, code output |\n| Visual verification (screenshot) | `mk:agent-browser` | Annotated snapshots |\n| Auth flow (login, session, MFA) | `mk:agent-browser` | Session persistence, auth import |\n| Execute Playwright test | Script: `npx playwright test` | Deterministic |\n\n## Authentication Protocol\n\n**On auth encounter** (login page, MFA, 401\u002F403):\n\n1. **STOP** current flow immediately\n2. **Show user:**\n   ```\n   ⚠️ Authentication required at: [current URL]\n   mk:qa-manual needs credentials to continue.\n   Please provide:\n   - Username\u002Femail: ___________\n   - Password: ___________\n   Type 'skip' to skip this flow or 'abort' to stop testing.\n   ```\n3. **WAIT** for user input — do NOT proceed without it\n4. On credentials → fill form using `mk:playwright-cli`, continue flow\n5. On 'skip' → mark flow SKIPPED, move to next\n6. On 'abort' → end session, output partial report\n\n**NEVER:** Guess credentials. Use hardcoded test credentials. Proceed past auth without input. Store credentials in any file.\n\n## Process\n\nSee `references\u002Fqa-process.md` for detailed Use Case A and Use Case B processes.\n\n**Use Case A — Manual QA:** Load spec → extract flows → navigate each → verify outcomes → report\n\n**Use Case B — E2E Code Gen:** Run Use Case A → record interactions → generate .spec.ts with role-based locators\n\n## Output Format\n\nSee `references\u002Foutput-templates.md` for full templates.\n\n**QA Report** → structured pass\u002Ffail per flow with evidence\n**Playwright Code** → production-ready .spec.ts using `getByRole`, `getByLabel`, `getByText`\n\n## Scripts\n\n| Script | Purpose | Invocation |\n|--------|---------|------------|\n| `scripts\u002Frun-playwright.sh` | Execute generated .spec.ts | After E2E code generation |\n\n## References\n\n| Reference | When to load | Content |\n|-----------|-------------|---------|\n| **[qa-process.md](.\u002Freferences\u002Fqa-process.md)** | Steps 1-4 | Detailed Use Case A + B processes |\n| **[output-templates.md](.\u002Freferences\u002Foutput-templates.md)** | Step output | QA report + Playwright code templates |\n\n## Failure Handling\n\n| Failure | Detection | Recovery | Message |\n|---------|-----------|----------|---------|\n| Auth encountered | URL\u002Fform patterns | Auth protocol above | \"⚠️ Authentication required...\" |\n| Page load timeout | 30s timeout | Retry ×2 then report | \"Page load timed out at [URL]\" |\n| Element not found | Selector fails | Re-snapshot, try alternate | \"Element not found, re-scanning...\" |\n| Spec not found | File missing | Ask user | \"Spec file not found. Provide path or URL.\" |\n| Playwright exec fails | Non-zero exit | Show error + fix hints | \"Test failed: [error]. Fix: [hint]\" |\n\n## Gotchas\n\n- **Testing against stale deployment**: Running E2E tests against yesterday's build → Verify deployment version matches expected before starting test run\n- **Credentials hardcoded in generated spec files**: Auto-generated .spec.ts contains login credentials → Always use environment variables for credentials; never inline in test code",{"name":5,"description":7},"main","c7ff0a9e672de2c0590b03f6459385c2d7a63c1a","kit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-qa-manual",3,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit","https:\u002F\u002Fdocs.meowkit.dev\u002F","https:\u002F\u002Fgithub.com\u002Fngocsangyem","Keep moving forward","2026-11-15 03:54:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add ngocsangyem\u002FMeowKit --skill mk-qa-manual",{"tool":39,"command":40},"bunx","bunx skills add ngocsangyem\u002FMeowKit --skill mk-qa-manual",{"tool":42,"command":43},"pnpm","pnpm dlx skills add ngocsangyem\u002FMeowKit --skill mk-qa-manual","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-qa-manual\u002FSKILL.md",true,[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"examples\u002F01-login-flow-manual-qa.md","REFERENCE","参考文档",1517,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-qa-manual\u002Fexamples\u002F01-login-flow-manual-qa.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"examples\u002F02-checkout-e2e-generation.md",5782,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-qa-manual\u002Fexamples\u002F02-checkout-e2e-generation.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"examples\u002F03-url-exploration.md",1641,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-qa-manual\u002Fexamples\u002F03-url-exploration.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Foutput-templates.md",10700,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-qa-manual\u002Freferences\u002Foutput-templates.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fqa-process.md",5189,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-qa-manual\u002Freferences\u002Fqa-process.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Frun-playwright.sh","SCRIPT","脚本",848,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-qa-manual\u002Fscripts\u002Frun-playwright.sh",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7DVHF481B4J41T4855KGM50","mk-worktree","Manages git worktrees for parallel agent isolation: creates parallel\u002F{name}-{timestamp} branches, merges with conflict detection. NOT for user feature branches (use git worktree directly).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-worktree\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7DVHAWVKDKPB1EA3F1NC4JC","mk-workflow-orchestrator","Auto-invoked 7-phase workflow for complex-feature intent; fasttrack mode for pre-approved specs. NOT for explicit single tasks (mk:cook), green-field builds (mk:autobuild), or simple fixes (mk:fix).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-workflow-orchestrator\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7DVH6SYBHWW00TRZXCC56JW","mk-web-to-markdown","Fetch a URL and return clean markdown, for arbitrary external pages (blog, RFC, GitHub issue, vendor doc) not covered by mk:docs-finder. Static-only by default; opt-in JS rendering available.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-web-to-markdown\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7DVH3HGW47BX3PEF30JV6EJ","mk-vulnerability-scanner","Vulnerability analysis: OWASP Top 10, current threat landscape, supply chain security, attack surface mapping, risk prioritization. Use for security audits. NOT for STRIDE\u002FCSO infra audits (mk:cso).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-vulnerability-scanner\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7DVGZBKMB9WDFH9MFMA99FV","mk-vue","Vue 3 authoring\u002Freview: components, composables, reactivity, Pinia, Pinia Colada, file routing, forms. Composition API + script setup. Auto-activates on .vue files. Deep review: mk:vue-best-practices.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-vue\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":19},"01M7DVGSE12AA1M7599HB8HRCT","mk-vue-testing-best-practices","Vue 3 testing best-practices review: Vitest + Vue Test Utils for components, composables, Pinia, Router, async\u002FSuspense, forms, a11y, plus Playwright E2E strategy. Advisory only.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-vue-testing-best-practices\u002FSKILL.md",[],[]]