[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C5FXEPKZ9J49RQFGETM3KN":3,"skill-same:01M6C5FXEPKZ9J49RQFGETM3KN":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":31,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":14,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":6,"updatedAt":60,"install":61,"resources":74},"01M6C5FXEPKZ9J49RQFGETM3KN","e2e-test",null,"Self-Healing E2E Testing Workflow for ACM-AI. Runs Playwright tests with autonomous failure recovery, selector healing, API contract validation, and evidence collection. Integrates with agent-browser and chrome-devtools MCP.","CoralShades\u002Facm-ai","CoralShades","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F220297585?v=4","01M6C5211QSJHZ8HXSDDWCR507","Coral Shades AI Agency","01M6C52161FNQDRQ0FRR8DAA9D",0,"MIT","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fe2e-test\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"e2e test","test","e2e","browser","evidence","autonomous","api","collection","recovery","devtools","testing","validation","playwright","e2e testing","chrome","workflow","MCP","2026-11-10 10:12:30",false,"---\nname: e2e-test\ndescription: Self-Healing E2E Testing Workflow for ACM-AI. Runs Playwright tests with autonomous failure recovery, selector healing, API contract validation, and evidence collection. Integrates with agent-browser and chrome-devtools MCP.\n---\n\n# Self-Healing E2E Testing Workflow\n\n## When to Use\n- After implementing frontend\u002Fbackend changes to verify nothing broke\n- Before marking a story as complete (verification protocol)\n- When running full regression testing\n- When investigating reported UI bugs\n- When validating accessibility compliance\n\n## Quick Start\n\n### Run Tests by Tier\n```bash\nnpx playwright test --project=smoke             # Tier 1: \u003C30s, all pages load\nnpx playwright test --project=critical          # Tier 2: \u003C5min, core workflows\nnpx playwright test --project=feature           # Tier 3: \u003C15min, feature tests\nnpx playwright test --project=accessibility     # Accessibility audits\nnpx playwright test                             # Full suite\n```\n\n### Tag-Based Execution\n```bash\nnpx playwright test --grep @smoke              # Smoke tests only\nnpx playwright test --grep @critical           # Critical path tests\nnpx playwright test --grep @feature            # Feature tests\nnpx playwright test --grep @a11y               # Accessibility audits\nnpx playwright test --grep \"@api-contracts\"    # API contract validation\n```\n\n## Self-Healing Workflow (6 Phases)\n\n1. **Parallel Research**: Analyze changed files, identify affected routes & APIs\n2. **Test Selection**: Choose relevant test tier based on change scope\n3. **Execute with Healing**: Run tests with selector fallback + state recovery\n4. **Evidence Collection**: Screenshots, console logs, network traces on failure\n5. **Auto-Fix (up to 3 attempts)**: If test fails due to code issue:\n   a. Analyze failure (selector drift? API change? missing element?)\n   b. Apply fix (add data-testid, update selector, fix component)\n   c. Re-run failed test\n6. **Report**: Generate healing report with recommendations\n\n## Framework Architecture\n\n```\ntests\u002Fe2e\u002Fframework\u002F\n  self-healing\u002F\n    config.ts              # Thresholds, strategy chain, recovery levels\n    selector-engine.ts     # Multi-strategy selector resolution\n    state-recovery.ts      # Stuck-state recovery state machine\n    api-contract-validator.ts  # API response shape validation\n    evidence-collector.ts  # Screenshot, console, network evidence\n    healing-reporter.ts    # Aggregated healing report\n  route-walker.ts          # Automated route walking utility\n  accessibility.ts         # axe-core WCAG 2.1 AA wrapper\n\ntests\u002Fsupport\u002Ffixtures\u002F\n  self-healing.ts          # HealingPage, EvidenceCollector fixtures\n\ntests\u002Fe2e\u002Fspecs\u002F\n  smoke-walker.spec.ts     # @smoke - Route walking\n  api-contracts.spec.ts    # @smoke @api-contracts - API shapes\n  settings-pages.spec.ts   # @feature - Settings sub-pages\n  upload-wizard.spec.ts    # @critical - Upload wizard flow\n  jobs-pipeline.spec.ts    # @critical - Job lifecycle\n  building-detail.spec.ts  # @feature - Building detail page\n  accessibility.spec.ts    # @a11y - WCAG audits\n```\n\n## Test Tiers\n\n| Tier | Project | Trigger | Timeout | Coverage |\n|------|---------|---------|---------|----------|\n| Smoke | `smoke` | Every PR | \u003C30s | Route walking, API health |\n| Critical | `critical` | Merges to main | \u003C5min | Upload wizard, jobs pipeline |\n| Feature | `feature` | Nightly | \u003C15min | Settings, building detail |\n| A11y | `accessibility` | Nightly | \u003C5min | WCAG 2.1 AA audits |\n\n## Integration with Agent-Browser\n\nThe self-healing workflow uses `agent-browser` for interactive debugging, visual verification, and state comparison. See `.claude\u002Fskills\u002Fagent-browser\u002FSKILL.md` for full command reference.\n\n### Core Debugging Workflow\n```bash\n# 1. Navigate to the failing page\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Fsource\u002Fsource%3Atest001\n\n# 2. Get interactive element refs\nagent-browser snapshot -i\n# Output: @e1 [button] \"Main Block\", @e2 [input] \"Search records...\", @e3 [button] \"Group by Room\"\n\n# 3. Interact using refs\nagent-browser click @e1              # Click building in sidebar\nagent-browser fill @e2 \"asbestos\"    # Type in search\nagent-browser wait --load networkidle\n\n# 4. Re-snapshot after page changes (refs are invalidated)\nagent-browser snapshot -i\n\n# 5. Visual comparison\nagent-browser screenshot --annotate   # Numbered element labels on screenshot\nagent-browser diff snapshot           # See what changed since last snapshot\n```\n\n### Visual Regression Testing\n```bash\n# Save baseline before changes\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Facm && agent-browser wait --load networkidle\nagent-browser screenshot baseline-acm.png\n\n# After code changes, compare\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Facm && agent-browser wait --load networkidle\nagent-browser diff screenshot --baseline baseline-acm.png\n# Output: mismatch percentage and diff image with changed pixels in red\n```\n\n### Page-by-Page Verification\n```bash\n# Verify upload wizard steps\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Fupload\nagent-browser snapshot -i\n# Look for: @eN [input type=\"file\"], @eN [button] \"Upload\"\n\n# Verify settings pages\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Fsettings\u002Fmodels\nagent-browser snapshot -i\n# Look for: form inputs, save buttons\n\n# Verify ACM register\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Fsource\u002Fsource%3Atest\nagent-browser snapshot -i -C          # Include cursor-interactive elements (AG Grid cells)\n```\n\n### Failure Investigation Pattern\n```bash\n# When a Playwright test fails:\n# 1. Open the exact URL that failed\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Fsource\u002Fsource%3Atest001\n\n# 2. Check for the missing element\nagent-browser snapshot -i -s \"[data-testid='item-grid']\"\n# If empty: element is missing or has wrong testid\n\n# 3. Get full page text for debugging\nagent-browser get text body > \u002Ftmp\u002Fpage-content.txt\n\n# 4. Check console errors\nagent-browser eval 'JSON.stringify(window.__e2e_errors || [])'\n\n# 5. Take annotated screenshot as evidence\nagent-browser screenshot --annotate --full test-results\u002Fevidence\u002Ffailure.png\n```\n\n### Data Extraction for Test Verification\n```bash\n# Extract AG Grid row count\nagent-browser eval 'document.querySelectorAll(\".ag-row\").length'\n\n# Extract building sidebar items\nagent-browser eval --stdin \u003C\u003C'EVALEOF'\nJSON.stringify(\n  Array.from(document.querySelectorAll('[data-testid=\"building-sidebar\"] button'))\n    .map(b => b.textContent?.trim())\n)\nEVALEOF\n\n# Check network requests made by the page\nagent-browser eval 'JSON.stringify(performance.getEntriesByType(\"resource\").filter(r => r.name.includes(\"\u002Fapi\u002F\")).map(r => r.name))'\n```\n\n### Responsive Testing\n```bash\n# Test at different viewports\nagent-browser open http:\u002F\u002Flocalhost:8503 --viewport 1280x720   # Desktop\nagent-browser screenshot desktop.png\nagent-browser open http:\u002F\u002Flocalhost:8503 --viewport 768x1024   # Tablet\nagent-browser screenshot tablet.png\nagent-browser open http:\u002F\u002Flocalhost:8503 --viewport 375x667    # Mobile\nagent-browser screenshot mobile.png\n```\n\n## Selector Strategy Chain\n\nWhen a selector fails, the engine tries alternatives in priority order:\n\n| Priority | Strategy | Confidence | Example |\n|----------|----------|------------|---------|\n| 1 | data-testid | 1.0 | `[data-testid=\"acm-grid\"]` |\n| 2 | role+name | 0.95 | `getByRole('button', { name: 'Submit' })` |\n| 3 | aria-label | 0.9 | `getByLabel('Search records')` |\n| 4 | text content | 0.8 | `getByText('Upload')` |\n| 5 | CSS selector | 0.6 | `.ag-row` |\n| 6 | XPath | 0.4 | `\u002F\u002Fdiv[@class=\"grid\"]` |\n\n## State Recovery Levels\n\nWhen a test gets stuck, recovery escalates:\n\n1. **WAIT**: Extend timeout, poll slower (2s delay)\n2. **REFRESH**: `page.reload()` + re-navigate to URL\n3. **RESET**: Clear cookies\u002FlocalStorage, navigate from `\u002F`\n4. **FAIL**: Mark test as failed after 3 attempts\n\n## Evidence Artifacts\n\nOn test failure, evidence is automatically collected:\n- Screenshots: `test-results\u002Fevidence\u002F{testName}\u002Fscreenshot.png`\n- Console logs: `test-results\u002Fevidence\u002F{testName}.json`\n- Network requests: included in evidence JSON\n- Healing report: `test-results\u002Fhealing-report.json`\n- Playwright report: `playwright-report\u002F`\n- JUnit XML: `test-results\u002Fjunit.xml`\n\n## API Contract Validation\n\nKey endpoints validated for response shape:\n- `GET \u002Fapi\u002Fhealth` - status field\n- `GET \u002Fapi\u002Fnotebooks\u002F` - array with id, name\n- `GET \u002Fapi\u002Fsources\u002F` - array with id, title\n- `GET \u002Fapi\u002Fmodels\u002F` - array with name, provider\n- `GET \u002Fapi\u002Fmodels\u002Fdefaults` - chat_model field\n- `GET \u002Fapi\u002Facm\u002Ffield-schema` - item_fields, building_fields objects\n\n## Known Considerations\n\n- **Port 8503**: Frontend dev server runs on 8503 (not 8502)\n- **AG Grid virtual DOM**: Rows off-screen need scroll-into-view before assertions\n- **AI-dependent tests**: Use mock route interception for CI (no real LLM)\n- **axe-core**: Start with critical-only assertions, track improvement\n- **Windows paths**: Use forward slashes and `$CLAUDE_PROJECT_DIR`\n","# Self-Healing E2E Testing Workflow\n\n## When to Use\n- After implementing frontend\u002Fbackend changes to verify nothing broke\n- Before marking a story as complete (verification protocol)\n- When running full regression testing\n- When investigating reported UI bugs\n- When validating accessibility compliance\n\n## Quick Start\n\n### Run Tests by Tier\n```bash\nnpx playwright test --project=smoke             # Tier 1: \u003C30s, all pages load\nnpx playwright test --project=critical          # Tier 2: \u003C5min, core workflows\nnpx playwright test --project=feature           # Tier 3: \u003C15min, feature tests\nnpx playwright test --project=accessibility     # Accessibility audits\nnpx playwright test                             # Full suite\n```\n\n### Tag-Based Execution\n```bash\nnpx playwright test --grep @smoke              # Smoke tests only\nnpx playwright test --grep @critical           # Critical path tests\nnpx playwright test --grep @feature            # Feature tests\nnpx playwright test --grep @a11y               # Accessibility audits\nnpx playwright test --grep \"@api-contracts\"    # API contract validation\n```\n\n## Self-Healing Workflow (6 Phases)\n\n1. **Parallel Research**: Analyze changed files, identify affected routes & APIs\n2. **Test Selection**: Choose relevant test tier based on change scope\n3. **Execute with Healing**: Run tests with selector fallback + state recovery\n4. **Evidence Collection**: Screenshots, console logs, network traces on failure\n5. **Auto-Fix (up to 3 attempts)**: If test fails due to code issue:\n   a. Analyze failure (selector drift? API change? missing element?)\n   b. Apply fix (add data-testid, update selector, fix component)\n   c. Re-run failed test\n6. **Report**: Generate healing report with recommendations\n\n## Framework Architecture\n\n```\ntests\u002Fe2e\u002Fframework\u002F\n  self-healing\u002F\n    config.ts              # Thresholds, strategy chain, recovery levels\n    selector-engine.ts     # Multi-strategy selector resolution\n    state-recovery.ts      # Stuck-state recovery state machine\n    api-contract-validator.ts  # API response shape validation\n    evidence-collector.ts  # Screenshot, console, network evidence\n    healing-reporter.ts    # Aggregated healing report\n  route-walker.ts          # Automated route walking utility\n  accessibility.ts         # axe-core WCAG 2.1 AA wrapper\n\ntests\u002Fsupport\u002Ffixtures\u002F\n  self-healing.ts          # HealingPage, EvidenceCollector fixtures\n\ntests\u002Fe2e\u002Fspecs\u002F\n  smoke-walker.spec.ts     # @smoke - Route walking\n  api-contracts.spec.ts    # @smoke @api-contracts - API shapes\n  settings-pages.spec.ts   # @feature - Settings sub-pages\n  upload-wizard.spec.ts    # @critical - Upload wizard flow\n  jobs-pipeline.spec.ts    # @critical - Job lifecycle\n  building-detail.spec.ts  # @feature - Building detail page\n  accessibility.spec.ts    # @a11y - WCAG audits\n```\n\n## Test Tiers\n\n| Tier | Project | Trigger | Timeout | Coverage |\n|------|---------|---------|---------|----------|\n| Smoke | `smoke` | Every PR | \u003C30s | Route walking, API health |\n| Critical | `critical` | Merges to main | \u003C5min | Upload wizard, jobs pipeline |\n| Feature | `feature` | Nightly | \u003C15min | Settings, building detail |\n| A11y | `accessibility` | Nightly | \u003C5min | WCAG 2.1 AA audits |\n\n## Integration with Agent-Browser\n\nThe self-healing workflow uses `agent-browser` for interactive debugging, visual verification, and state comparison. See `.claude\u002Fskills\u002Fagent-browser\u002FSKILL.md` for full command reference.\n\n### Core Debugging Workflow\n```bash\n# 1. Navigate to the failing page\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Fsource\u002Fsource%3Atest001\n\n# 2. Get interactive element refs\nagent-browser snapshot -i\n# Output: @e1 [button] \"Main Block\", @e2 [input] \"Search records...\", @e3 [button] \"Group by Room\"\n\n# 3. Interact using refs\nagent-browser click @e1              # Click building in sidebar\nagent-browser fill @e2 \"asbestos\"    # Type in search\nagent-browser wait --load networkidle\n\n# 4. Re-snapshot after page changes (refs are invalidated)\nagent-browser snapshot -i\n\n# 5. Visual comparison\nagent-browser screenshot --annotate   # Numbered element labels on screenshot\nagent-browser diff snapshot           # See what changed since last snapshot\n```\n\n### Visual Regression Testing\n```bash\n# Save baseline before changes\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Facm && agent-browser wait --load networkidle\nagent-browser screenshot baseline-acm.png\n\n# After code changes, compare\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Facm && agent-browser wait --load networkidle\nagent-browser diff screenshot --baseline baseline-acm.png\n# Output: mismatch percentage and diff image with changed pixels in red\n```\n\n### Page-by-Page Verification\n```bash\n# Verify upload wizard steps\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Fupload\nagent-browser snapshot -i\n# Look for: @eN [input type=\"file\"], @eN [button] \"Upload\"\n\n# Verify settings pages\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Fsettings\u002Fmodels\nagent-browser snapshot -i\n# Look for: form inputs, save buttons\n\n# Verify ACM register\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Fsource\u002Fsource%3Atest\nagent-browser snapshot -i -C          # Include cursor-interactive elements (AG Grid cells)\n```\n\n### Failure Investigation Pattern\n```bash\n# When a Playwright test fails:\n# 1. Open the exact URL that failed\nagent-browser open http:\u002F\u002Flocalhost:8503\u002Fsource\u002Fsource%3Atest001\n\n# 2. Check for the missing element\nagent-browser snapshot -i -s \"[data-testid='item-grid']\"\n# If empty: element is missing or has wrong testid\n\n# 3. Get full page text for debugging\nagent-browser get text body > \u002Ftmp\u002Fpage-content.txt\n\n# 4. Check console errors\nagent-browser eval 'JSON.stringify(window.__e2e_errors || [])'\n\n# 5. Take annotated screenshot as evidence\nagent-browser screenshot --annotate --full test-results\u002Fevidence\u002Ffailure.png\n```\n\n### Data Extraction for Test Verification\n```bash\n# Extract AG Grid row count\nagent-browser eval 'document.querySelectorAll(\".ag-row\").length'\n\n# Extract building sidebar items\nagent-browser eval --stdin \u003C\u003C'EVALEOF'\nJSON.stringify(\n  Array.from(document.querySelectorAll('[data-testid=\"building-sidebar\"] button'))\n    .map(b => b.textContent?.trim())\n)\nEVALEOF\n\n# Check network requests made by the page\nagent-browser eval 'JSON.stringify(performance.getEntriesByType(\"resource\").filter(r => r.name.includes(\"\u002Fapi\u002F\")).map(r => r.name))'\n```\n\n### Responsive Testing\n```bash\n# Test at different viewports\nagent-browser open http:\u002F\u002Flocalhost:8503 --viewport 1280x720   # Desktop\nagent-browser screenshot desktop.png\nagent-browser open http:\u002F\u002Flocalhost:8503 --viewport 768x1024   # Tablet\nagent-browser screenshot tablet.png\nagent-browser open http:\u002F\u002Flocalhost:8503 --viewport 375x667    # Mobile\nagent-browser screenshot mobile.png\n```\n\n## Selector Strategy Chain\n\nWhen a selector fails, the engine tries alternatives in priority order:\n\n| Priority | Strategy | Confidence | Example |\n|----------|----------|------------|---------|\n| 1 | data-testid | 1.0 | `[data-testid=\"acm-grid\"]` |\n| 2 | role+name | 0.95 | `getByRole('button', { name: 'Submit' })` |\n| 3 | aria-label | 0.9 | `getByLabel('Search records')` |\n| 4 | text content | 0.8 | `getByText('Upload')` |\n| 5 | CSS selector | 0.6 | `.ag-row` |\n| 6 | XPath | 0.4 | `\u002F\u002Fdiv[@class=\"grid\"]` |\n\n## State Recovery Levels\n\nWhen a test gets stuck, recovery escalates:\n\n1. **WAIT**: Extend timeout, poll slower (2s delay)\n2. **REFRESH**: `page.reload()` + re-navigate to URL\n3. **RESET**: Clear cookies\u002FlocalStorage, navigate from `\u002F`\n4. **FAIL**: Mark test as failed after 3 attempts\n\n## Evidence Artifacts\n\nOn test failure, evidence is automatically collected:\n- Screenshots: `test-results\u002Fevidence\u002F{testName}\u002Fscreenshot.png`\n- Console logs: `test-results\u002Fevidence\u002F{testName}.json`\n- Network requests: included in evidence JSON\n- Healing report: `test-results\u002Fhealing-report.json`\n- Playwright report: `playwright-report\u002F`\n- JUnit XML: `test-results\u002Fjunit.xml`\n\n## API Contract Validation\n\nKey endpoints validated for response shape:\n- `GET \u002Fapi\u002Fhealth` - status field\n- `GET \u002Fapi\u002Fnotebooks\u002F` - array with id, name\n- `GET \u002Fapi\u002Fsources\u002F` - array with id, title\n- `GET \u002Fapi\u002Fmodels\u002F` - array with name, provider\n- `GET \u002Fapi\u002Fmodels\u002Fdefaults` - chat_model field\n- `GET \u002Fapi\u002Facm\u002Ffield-schema` - item_fields, building_fields objects\n\n## Known Considerations\n\n- **Port 8503**: Frontend dev server runs on 8503 (not 8502)\n- **AG Grid virtual DOM**: Rows off-screen need scroll-into-view before assertions\n- **AI-dependent tests**: Use mock route interception for CI (no real LLM)\n- **axe-core**: Start with critical-only assertions, track improvement\n- **Windows paths**: Use forward slashes and `$CLAUDE_PROJECT_DIR`\n",{"name":5,"description":7},"main","1ca81b0a7de199942400f965edd4d7544077ac5d",".claude\u002Fskills\u002Fe2e-test","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai","https:\u002F\u002Fgithub.com\u002FCoralShades","coralshades.com.au","2026-04-18 00:45:07",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add CoralShades\u002Facm-ai --skill e2e-test",{"tool":67,"command":68},"bunx","bunx skills add CoralShades\u002Facm-ai --skill e2e-test",{"tool":70,"command":71},"pnpm","pnpm dlx skills add CoralShades\u002Facm-ai --skill e2e-test","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fe2e-test\u002FSKILL.md",true,[],[76,98,111,127,146,156],{"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":85,"publishedAt":49},"01M6C63HKXA890HHV47WBAX0TB","uncodixfy","Prevents generic AI\u002FCodex UI patterns when generating frontend code. Use this skill whenever generating HTML, CSS, React, Vue, Svelte, or any frontend UI code to enforce clean, human-designed aesthetics inspired by Linear, Raycast, Stripe, and GitHub instead of typical AI-generated UI.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Funcodixfy\u002FSKILL.md",[82],{"categoryNo":83,"categoryName":84,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[78,86,87,88,89,90,91,92,93,94,95,96,97],"github","frontend","css","codex","react","code","linear","ui","vue","generated","use","html",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":102,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":49},"01M6C63FJ2GEBBGZ5XSMV40KXB","runpodctl","Runpod CLI to manage your GPU workloads.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Frunpodctl\u002FSKILL.md",[],[100,106,107,108,109,110],"macos","cli","linux","gpu","Bash",{"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":49},"01M6C63DPAV46TFVQ01SFYPJ7X","langgraph-persistence","INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-persistence\u002FSKILL.md",[],[118,119,120,121,122,123,124,125,126],"langgraph persistence","langgraph","persistence","travel","history","scoping","remember","state","configure",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":136,"publishedAt":49},"01M6C63BNS9CQEBTB8RNSSBFPA","langgraph-human-in-the-loop","INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval\u002Fvalidation workflows, and the 4-tier error handling strategy.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-human-in-the-loop\u002FSKILL.md",[133],{"categoryNo":134,"categoryName":135,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000038","人力资源",[137,138,119,139,140,43,141,142,143,144,145],"langgraph human in the loop","loop","workflows","error handling","human-in-the-loop","command","strategy","approval","resume",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":49},"01M6C639GVYZFX3NFPV5FBDR4F","langgraph-fundamentals","INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-fundamentals\u002FSKILL.md",[],[153,119,140,125,154,155,142,91],"langgraph fundamentals","streaming","writing",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":49},"01M6C6375N34YX2GZ3SD3R7XR2","langchain-rag","INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flangchain-rag\u002FSKILL.md",[],[163,164,165,166,167,168,169,170,171,172],"rag","langchain rag","langchain","embeddings","vector","openai","chroma","faiss","vector stores","system"]