[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ENHV1PM76HRB2BB7F67TTP":3,"skill-same:01M7ENHV1PM76HRB2BB7F67TTP":84},{"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":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":37,"ownerDescription":6,"updatedAt":38,"install":39,"resources":51},"01M7ENHV1PM76HRB2BB7F67TTP","blog-google",null,"Google API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth\u002Fservice account, GA4, Ads). Shares config with claude-seo at ~\u002F.config\u002Fclaude-seo\u002Fgoogle-api.json. Use when user says \"google data\", \"page speed\", \"core web vitals\", \"search console\", \"indexation\", \"GA4\", \"keyword research\", \"nlp entities\", \"blog performance\", \"youtube search\", \"google api setup\".","TanNhatCMS\u002Fjarvis","TanNhatCMS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113796420?v=4","01M753MV17KG5CD3152G3WQEQY","KietNT","01M7EKEDYVYQ6PWVJJMZ911VMX",0,"MIT","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-blog-google\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: blog-google\ndescription: >\n  Google API integration for blog performance: PageSpeed Insights, CrUX Core Web\n  Vitals with 25-week history, Search Console performance, URL Inspection, Indexing\n  API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search\n  for embedding, and Google Ads Keyword Planner. Progressive feature availability\n  based on credential tier (API key, OAuth\u002Fservice account, GA4, Ads). Shares\n  config with claude-seo at ~\u002F.config\u002Fclaude-seo\u002Fgoogle-api.json. Use when user\n  says \"google data\", \"page speed\", \"core web vitals\", \"search console\",\n  \"indexation\", \"GA4\", \"keyword research\", \"nlp entities\", \"blog performance\",\n  \"youtube search\", \"google api setup\".\nuser-invokable: true\nargument-hint: \"[setup|pagespeed|crux|crux-history|gsc|inspect|index|ga4|nlp|youtube|keywords|report|quotas] [url|property|query]\"\nlicense: MIT\nmetadata:\n  author: AgriciDaniel\n  version: \"2.2.0\"\n  category: blog\n---\n\n# Blog Google: Google API Data for Blog Performance\n\nDirect access to Google's SEO APIs for blog performance analysis. Provides real\nChrome user metrics, indexation status, search performance, entity analysis, YouTube\nvideo discovery, keyword volumes, and PDF\u002FHTML performance reports.\n\nMost integrations have no usage fee within their documented quotas. Cloud\nNatural Language requires billing and can incur charges after its free monthly\ntier. Google Ads requires an eligible account and developer token. Never enable\nbilling or make a paid request without explicit user approval.\n\n## Prerequisites\n\n**Always check credentials before running any command:**\n```bash\npython3 skills\u002Fblog-google\u002Fscripts\u002Frun.py google_auth --check --json\n```\n\n**Config file:** `~\u002F.config\u002Fclaude-seo\u002Fgoogle-api.json` (shared with claude-seo)\n```json\n{\n  \"api_key\": \"YOUR_GOOGLE_API_KEY\",\n  \"oauth_client_path\": \"\u002Fpath\u002Fto\u002Fclient_secret.json\",\n  \"default_property\": \"sc-domain:example.com\",\n  \"ga4_property_id\": \"properties\u002F123456789\",\n  \"ads_developer_token\": \"...\",\n  \"ads_customer_id\": \"123-456-7890\",\n  \"ads_login_customer_id\": \"123-456-7890\"\n}\n```\n\nIf missing, read `references\u002Fauth-setup.md` and walk the user through setup.\n\n### Credential Tiers\n\n| Tier | Detection | Available Commands |\n|------|-----------|-------------------|\n| **0** (API Key) | `api_key` present | `pagespeed`, `crux`, `crux-history`, `youtube`, `nlp` |\n| **1** (OAuth\u002FSA) | + OAuth token or service account | Tier 0 + `gsc`, `inspect`, `index` |\n| **2** (Full) | + `ga4_property_id` configured | Tier 1 + `ga4` |\n| **3** (Ads) | + `ads_developer_token` + `ads_customer_id` | Tier 2 + `keywords` |\n\nAlways communicate the detected tier before running commands.\n\n## Quick Reference\n\n| Command | What it does | Tier |\n|---------|-------------|------|\n| `\u002Fblog google setup` | Check\u002Fconfigure API credentials |: |\n| `\u002Fblog google pagespeed \u003Curl>` | PSI Lighthouse + CrUX field data | 0 |\n| `\u002Fblog google crux \u003Curl>` | CrUX field data only (p75 metrics) | 0 |\n| `\u002Fblog google crux-history \u003Curl>` | 25-week CWV trend analysis | 0 |\n| `\u002Fblog google youtube \u003Cquery>` | YouTube video search (views, likes, duration) | 0 |\n| `\u002Fblog google nlp \u003Curl-or-text>` | NLP entity extraction + sentiment | 0 |\n| `\u002Fblog google gsc \u003Cproperty>` | Search Console: clicks, impressions, CTR, position | 1 |\n| `\u002Fblog google inspect \u003Curl>` | URL Inspection: index status, canonical | 1 |\n| `\u002Fblog google index \u003Curl>` | Submit URL to Indexing API | 1 |\n| `\u002Fblog google ga4 [property-id]` | GA4 organic traffic report | 2 |\n| `\u002Fblog google keywords \u003Cseed>` | Keyword ideas from Google Ads Keyword Planner | 3 |\n| `\u002Fblog google report \u003Ctype>` | PDF\u002FHTML performance report |: |\n| `\u002Fblog google quotas` | Show rate limits for all APIs |: |\n\n---\n\n## PageSpeed + CrUX\n\n### `\u002Fblog google pagespeed \u003Curl>`\n\nCombined Lighthouse lab data + CrUX field data for a published blog post.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py pagespeed_check \u003Curl> --json`\n**Reference:** `references\u002Fapi-reference.md`\n\nOutput merges lab scores (point-in-time Lighthouse) with field data (28-day\nChrome user metrics). CrUX tries URL-level first, falls back to origin-level.\n\n### `\u002Fblog google crux \u003Curl>`\n\nCrUX field data only (no Lighthouse run). Faster.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py pagespeed_check \u003Curl> --crux-only --json`\n\n### `\u002Fblog google crux-history \u003Curl>`\n\n25-week CrUX History trends. Shows whether CWV metrics are improving, stable, or degrading.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py crux_history \u003Curl> --json`\n\n---\n\n## Search Console\n\n### `\u002Fblog google gsc \u003Cproperty>`\n\nSearch Analytics: clicks, impressions, CTR, position for last 28 days.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py gsc_query --property \u003Cproperty> --json`\n**Default:** 28 days, dimensions=query,page, type=web, limit=1000.\n\nIncludes quick-win detection: queries at position 4-10 with high impressions.\n\nThe dedicated Search Console generative-AI reports are a gradual, subset\nrollout in the Search Console UI. They have separate Search and Discover views;\nthe Search view covers AI Overviews and AI Mode. Do not promise clicks, queries,\nor API retrieval from these dedicated views. Until Google documents an API,\nreport that capability as `SKIPPED` or unavailable and point the user to the UI.\n\nGoogle's July 29 Search Central announcement says Search Console platform\nproperties for Instagram, TikTok, X, and YouTube are globally available. The\ncurrent Help Center still says gradual rollout. Report this as a Google-source\nconflict, verify availability in the user's account, and do not claim that\n`\u002Fblog google gsc` retrieves these platform reports through the current API.\n\n### `\u002Fblog google inspect \u003Curl>`\n\nURL Inspection: real indexation status from Google.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py gsc_inspect \u003Curl> --json`\n\nReturns: verdict (PASS\u002FFAIL), coverage state, robots.txt status, indexing state,\npage fetch state, canonical selection, mobile usability, rich results.\n\nAfter a canonicalization fix, Google may retain the URL in a duplicate cluster\nfor up to two weeks. If the implementation is now correct and the fix is within\nthat window, report `PENDING_REEVALUATION` rather than an immediate failure.\nSearch Console's Request Indexing feature is quota-limited; reserve it for\nimportant URLs.\n\nFor batch inspection: `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py gsc_inspect --batch \u003Cfile> --json`\n\n---\n\n## Indexing API\n\n### `\u002Fblog google index \u003Curl>`\n\nNotify Google of a URL update through the Indexing API.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py indexing_notify \u003Curl> --json`\n**Reference:** `references\u002Fapi-reference.md`\n\nThe Indexing API is officially for JobPosting and BroadcastEvent\u002FVideoObject pages.\nAlways inform the user of this restriction. Daily quota: 200 publish requests.\nDo not present it as a general-purpose replacement for URL Inspection's Request\nIndexing feature.\n\nFor batch: `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py indexing_notify --batch \u003Cfile> --json`\n\n---\n\n## GA4 Traffic\n\n### `\u002Fblog google ga4 [property-id]`\n\nOrganic traffic report: daily sessions, users, pageviews, bounce rate, engagement.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py ga4_report --property \u003Cid> --json`\n**Default:** 28 days, filtered to Organic Search channel group.\n\nFor top landing pages: `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py ga4_report --property \u003Cid> --report top-pages --json`\n\n---\n\n## YouTube (Video Discovery)\n\nYouTube research can add useful, relevant media and distribution context. Any\nthird-party visibility correlation is observational, not a Google ranking or\ncitation requirement. Free, API key only. Used by blog-write and blog-rewrite\nfor video embedding.\n\n### `\u002Fblog google youtube \u003Cquery>`\n\nSearch YouTube for videos relevant to a blog topic.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py youtube_search search \"\u003Cquery>\" --json`\n**Quota:** 100 units per search (10,000 units\u002Fday free).\n\nReturns: title, channel, views, likes, duration, description, tags.\n\nFor video details + comments: `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py youtube_search video \u003Cvideo_id> --json`\n\n---\n\n## NLP Content Analysis\n\nGoogle's entity and sentiment analysis can support topic and editorial review.\nIt does not expose ranking-system scores, and E-E-A-T is not a numeric Google\nranking factor.\n\n### `\u002Fblog google nlp \u003Curl-or-text>`\n\nFull NLP analysis: entities, sentiment, content classification.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py nlp_analyze --url \u003Curl> --json`\n**Free tier:** 5,000 units\u002Fmonth. Requires billing enabled on GCP project.\n\nFor entity extraction only: `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py nlp_analyze --url \u003Curl> --features entities --json`\n\n---\n\n## Keyword Research (Google Ads)\n\nGold-standard keyword volume data. Requires Google Ads account (Tier 3).\n\n### `\u002Fblog google keywords \u003Cseed>`\n\nGenerate keyword ideas from seed terms for blog topic research.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py keyword_planner ideas \"\u003Cseed>\" --json`\n\nFor volume lookup: `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py keyword_planner volume \"\u003Ckw1>,\u003Ckw2>\" --json`\n\n---\n\n## Reports\n\n### `\u002Fblog google report \u003Ctype>`\n\nGenerate a PDF\u002FHTML report with charts and tables.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py google_report --type \u003Ctype> --data \u003Cjson> --domain \u003Cdomain> --format pdf`\n\n| Type | Input | Output |\n|------|-------|--------|\n| `cwv-audit` | PSI + CrUX + CrUX History data | Core Web Vitals audit with gauges, timelines |\n| `gsc-performance` | GSC query data | Search Console report with query tables |\n| `indexation` | Batch inspection data | Indexation status with coverage donut |\n| `full` | All data combined | Comprehensive Google SEO report |\n\n**Note:** PDF generation requires system libraries: `sudo apt install libpango1.0-dev libcairo2-dev`.\nFalls back to HTML if WeasyPrint is unavailable or PDF rendering fails.\n\n---\n\n## Rate Limits\n\n| API | Per-Minute | Per-Day | Auth |\n|-----|-----------|---------|------|\n| PSI v5 | 240 QPM | 25,000 QPD | API Key |\n| CrUX + History | 150 QPM (shared) | Unlimited | API Key |\n| GSC Search Analytics | 1,200 QPM\u002Fsite | 30M QPD | Service Account |\n| GSC URL Inspection | 600 QPM | 2,000 QPD\u002Fsite | Service Account |\n| Indexing API | 380 RPM | 200 publish\u002Fday | Service Account |\n| GA4 Data API | 10 concurrent (50 for 360) | 200K Core Tokens\u002Fday (2M for 360) | Service Account |\n| YouTube Data |: | 10,000 units\u002Fday | API Key |\n| NLP API |: | 5,000 units\u002Fmonth | API Key (billing) |\n\nRead `references\u002Frate-limits-quotas.md` for detailed quota management.\n\n## Blog Workflow Integration\n\nThis skill is both user-invocable (`\u002Fblog google pagespeed`) and callable\ninternally by other blog sub-skills:\n\n- **blog-seo-check**: Runs PSI + CrUX on published post URL for live CWV data\n- **blog-rewrite**: NLP entity analysis to identify E-E-A-T entity gaps\n- **blog-geo**: GSC performance data for real search appearance insights\n- **blog-audit**: Batch CWV + indexation checks across all published blog URLs\n- **blog-write \u002F blog-rewrite**: YouTube search for video embedding\n\nFalls back gracefully when credentials are not configured.\n\n## Report Templates\n\nUse the bundled templates when a workflow requests a durable human-readable\nreport. Keep unavailable account data marked `SKIPPED`; never fill an empty\nsection with estimated metrics.\n\n- `assets\u002Ftemplates\u002Fcwv-audit-report.md` for PageSpeed and CrUX evidence.\n- `assets\u002Ftemplates\u002Fgsc-performance-report.md` for Search Analytics exports.\n- `assets\u002Ftemplates\u002Findexation-status-report.md` for URL Inspection evidence.\n\n## Technical Notes\n\n- INP replaced FID on March 12, 2024. Never reference FID.\n- CLS values from CrUX are string-encoded (e.g., \"0.05\"). Scripts handle parsing.\n- CrUX 404 = insufficient Chrome traffic, not an auth error.\n- Search Analytics data has 2-3 day lag.\n- Indexing API is officially for JobPosting\u002FBroadcastEvent pages only.\n- Most integrations have no usage fee within quota. Cloud Natural Language\n  requires billing and can incur charges; Google Ads requires account and\n  developer-token access.\n- Read `references\u002Fsearch-currentness.md` before diagnosing a named update,\n  canonical change, Discover visibility, Google generative-AI reporting,\n  platform properties, Preferred Sources, AMP, or crawler byte-limit issue.\n- A named update's dates do not prove what caused an individual site's change.\n  Wait one full week after rollout before comparing data, and separate Web,\n  Image, Video, and News performance.\n- Googlebot processes only the first 2MB of supported files and first 64MB of\n  PDFs. Keep critical metadata and primary content before the cutoff.\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| No credentials configured | Run `\u002Fblog google setup`. List Tier 0 commands (API key only). |\n| Service account lacks GSC access | Add `client_email` to GSC > Settings > Users > Add. |\n| CrUX data unavailable (404) | Insufficient Chrome traffic. Use PSI lab data as fallback. |\n| GA4 property not found | Find property ID in GA4 Admin > Property Details. |\n| Indexing API quota exceeded | 200\u002Fday limit. Prioritize most important URLs. |\n| Rate limit (429) | Wait and retry with exponential backoff. |\n","# Blog Google: Google API Data for Blog Performance\n\nDirect access to Google's SEO APIs for blog performance analysis. Provides real\nChrome user metrics, indexation status, search performance, entity analysis, YouTube\nvideo discovery, keyword volumes, and PDF\u002FHTML performance reports.\n\nMost integrations have no usage fee within their documented quotas. Cloud\nNatural Language requires billing and can incur charges after its free monthly\ntier. Google Ads requires an eligible account and developer token. Never enable\nbilling or make a paid request without explicit user approval.\n\n## Prerequisites\n\n**Always check credentials before running any command:**\n```bash\npython3 skills\u002Fblog-google\u002Fscripts\u002Frun.py google_auth --check --json\n```\n\n**Config file:** `~\u002F.config\u002Fclaude-seo\u002Fgoogle-api.json` (shared with claude-seo)\n```json\n{\n  \"api_key\": \"YOUR_GOOGLE_API_KEY\",\n  \"oauth_client_path\": \"\u002Fpath\u002Fto\u002Fclient_secret.json\",\n  \"default_property\": \"sc-domain:example.com\",\n  \"ga4_property_id\": \"properties\u002F123456789\",\n  \"ads_developer_token\": \"...\",\n  \"ads_customer_id\": \"123-456-7890\",\n  \"ads_login_customer_id\": \"123-456-7890\"\n}\n```\n\nIf missing, read `references\u002Fauth-setup.md` and walk the user through setup.\n\n### Credential Tiers\n\n| Tier | Detection | Available Commands |\n|------|-----------|-------------------|\n| **0** (API Key) | `api_key` present | `pagespeed`, `crux`, `crux-history`, `youtube`, `nlp` |\n| **1** (OAuth\u002FSA) | + OAuth token or service account | Tier 0 + `gsc`, `inspect`, `index` |\n| **2** (Full) | + `ga4_property_id` configured | Tier 1 + `ga4` |\n| **3** (Ads) | + `ads_developer_token` + `ads_customer_id` | Tier 2 + `keywords` |\n\nAlways communicate the detected tier before running commands.\n\n## Quick Reference\n\n| Command | What it does | Tier |\n|---------|-------------|------|\n| `\u002Fblog google setup` | Check\u002Fconfigure API credentials |: |\n| `\u002Fblog google pagespeed \u003Curl>` | PSI Lighthouse + CrUX field data | 0 |\n| `\u002Fblog google crux \u003Curl>` | CrUX field data only (p75 metrics) | 0 |\n| `\u002Fblog google crux-history \u003Curl>` | 25-week CWV trend analysis | 0 |\n| `\u002Fblog google youtube \u003Cquery>` | YouTube video search (views, likes, duration) | 0 |\n| `\u002Fblog google nlp \u003Curl-or-text>` | NLP entity extraction + sentiment | 0 |\n| `\u002Fblog google gsc \u003Cproperty>` | Search Console: clicks, impressions, CTR, position | 1 |\n| `\u002Fblog google inspect \u003Curl>` | URL Inspection: index status, canonical | 1 |\n| `\u002Fblog google index \u003Curl>` | Submit URL to Indexing API | 1 |\n| `\u002Fblog google ga4 [property-id]` | GA4 organic traffic report | 2 |\n| `\u002Fblog google keywords \u003Cseed>` | Keyword ideas from Google Ads Keyword Planner | 3 |\n| `\u002Fblog google report \u003Ctype>` | PDF\u002FHTML performance report |: |\n| `\u002Fblog google quotas` | Show rate limits for all APIs |: |\n\n---\n\n## PageSpeed + CrUX\n\n### `\u002Fblog google pagespeed \u003Curl>`\n\nCombined Lighthouse lab data + CrUX field data for a published blog post.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py pagespeed_check \u003Curl> --json`\n**Reference:** `references\u002Fapi-reference.md`\n\nOutput merges lab scores (point-in-time Lighthouse) with field data (28-day\nChrome user metrics). CrUX tries URL-level first, falls back to origin-level.\n\n### `\u002Fblog google crux \u003Curl>`\n\nCrUX field data only (no Lighthouse run). Faster.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py pagespeed_check \u003Curl> --crux-only --json`\n\n### `\u002Fblog google crux-history \u003Curl>`\n\n25-week CrUX History trends. Shows whether CWV metrics are improving, stable, or degrading.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py crux_history \u003Curl> --json`\n\n---\n\n## Search Console\n\n### `\u002Fblog google gsc \u003Cproperty>`\n\nSearch Analytics: clicks, impressions, CTR, position for last 28 days.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py gsc_query --property \u003Cproperty> --json`\n**Default:** 28 days, dimensions=query,page, type=web, limit=1000.\n\nIncludes quick-win detection: queries at position 4-10 with high impressions.\n\nThe dedicated Search Console generative-AI reports are a gradual, subset\nrollout in the Search Console UI. They have separate Search and Discover views;\nthe Search view covers AI Overviews and AI Mode. Do not promise clicks, queries,\nor API retrieval from these dedicated views. Until Google documents an API,\nreport that capability as `SKIPPED` or unavailable and point the user to the UI.\n\nGoogle's July 29 Search Central announcement says Search Console platform\nproperties for Instagram, TikTok, X, and YouTube are globally available. The\ncurrent Help Center still says gradual rollout. Report this as a Google-source\nconflict, verify availability in the user's account, and do not claim that\n`\u002Fblog google gsc` retrieves these platform reports through the current API.\n\n### `\u002Fblog google inspect \u003Curl>`\n\nURL Inspection: real indexation status from Google.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py gsc_inspect \u003Curl> --json`\n\nReturns: verdict (PASS\u002FFAIL), coverage state, robots.txt status, indexing state,\npage fetch state, canonical selection, mobile usability, rich results.\n\nAfter a canonicalization fix, Google may retain the URL in a duplicate cluster\nfor up to two weeks. If the implementation is now correct and the fix is within\nthat window, report `PENDING_REEVALUATION` rather than an immediate failure.\nSearch Console's Request Indexing feature is quota-limited; reserve it for\nimportant URLs.\n\nFor batch inspection: `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py gsc_inspect --batch \u003Cfile> --json`\n\n---\n\n## Indexing API\n\n### `\u002Fblog google index \u003Curl>`\n\nNotify Google of a URL update through the Indexing API.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py indexing_notify \u003Curl> --json`\n**Reference:** `references\u002Fapi-reference.md`\n\nThe Indexing API is officially for JobPosting and BroadcastEvent\u002FVideoObject pages.\nAlways inform the user of this restriction. Daily quota: 200 publish requests.\nDo not present it as a general-purpose replacement for URL Inspection's Request\nIndexing feature.\n\nFor batch: `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py indexing_notify --batch \u003Cfile> --json`\n\n---\n\n## GA4 Traffic\n\n### `\u002Fblog google ga4 [property-id]`\n\nOrganic traffic report: daily sessions, users, pageviews, bounce rate, engagement.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py ga4_report --property \u003Cid> --json`\n**Default:** 28 days, filtered to Organic Search channel group.\n\nFor top landing pages: `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py ga4_report --property \u003Cid> --report top-pages --json`\n\n---\n\n## YouTube (Video Discovery)\n\nYouTube research can add useful, relevant media and distribution context. Any\nthird-party visibility correlation is observational, not a Google ranking or\ncitation requirement. Free, API key only. Used by blog-write and blog-rewrite\nfor video embedding.\n\n### `\u002Fblog google youtube \u003Cquery>`\n\nSearch YouTube for videos relevant to a blog topic.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py youtube_search search \"\u003Cquery>\" --json`\n**Quota:** 100 units per search (10,000 units\u002Fday free).\n\nReturns: title, channel, views, likes, duration, description, tags.\n\nFor video details + comments: `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py youtube_search video \u003Cvideo_id> --json`\n\n---\n\n## NLP Content Analysis\n\nGoogle's entity and sentiment analysis can support topic and editorial review.\nIt does not expose ranking-system scores, and E-E-A-T is not a numeric Google\nranking factor.\n\n### `\u002Fblog google nlp \u003Curl-or-text>`\n\nFull NLP analysis: entities, sentiment, content classification.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py nlp_analyze --url \u003Curl> --json`\n**Free tier:** 5,000 units\u002Fmonth. Requires billing enabled on GCP project.\n\nFor entity extraction only: `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py nlp_analyze --url \u003Curl> --features entities --json`\n\n---\n\n## Keyword Research (Google Ads)\n\nGold-standard keyword volume data. Requires Google Ads account (Tier 3).\n\n### `\u002Fblog google keywords \u003Cseed>`\n\nGenerate keyword ideas from seed terms for blog topic research.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py keyword_planner ideas \"\u003Cseed>\" --json`\n\nFor volume lookup: `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py keyword_planner volume \"\u003Ckw1>,\u003Ckw2>\" --json`\n\n---\n\n## Reports\n\n### `\u002Fblog google report \u003Ctype>`\n\nGenerate a PDF\u002FHTML report with charts and tables.\n\n**Script:** `python3 skills\u002Fblog-google\u002Fscripts\u002Frun.py google_report --type \u003Ctype> --data \u003Cjson> --domain \u003Cdomain> --format pdf`\n\n| Type | Input | Output |\n|------|-------|--------|\n| `cwv-audit` | PSI + CrUX + CrUX History data | Core Web Vitals audit with gauges, timelines |\n| `gsc-performance` | GSC query data | Search Console report with query tables |\n| `indexation` | Batch inspection data | Indexation status with coverage donut |\n| `full` | All data combined | Comprehensive Google SEO report |\n\n**Note:** PDF generation requires system libraries: `sudo apt install libpango1.0-dev libcairo2-dev`.\nFalls back to HTML if WeasyPrint is unavailable or PDF rendering fails.\n\n---\n\n## Rate Limits\n\n| API | Per-Minute | Per-Day | Auth |\n|-----|-----------|---------|------|\n| PSI v5 | 240 QPM | 25,000 QPD | API Key |\n| CrUX + History | 150 QPM (shared) | Unlimited | API Key |\n| GSC Search Analytics | 1,200 QPM\u002Fsite | 30M QPD | Service Account |\n| GSC URL Inspection | 600 QPM | 2,000 QPD\u002Fsite | Service Account |\n| Indexing API | 380 RPM | 200 publish\u002Fday | Service Account |\n| GA4 Data API | 10 concurrent (50 for 360) | 200K Core Tokens\u002Fday (2M for 360) | Service Account |\n| YouTube Data |: | 10,000 units\u002Fday | API Key |\n| NLP API |: | 5,000 units\u002Fmonth | API Key (billing) |\n\nRead `references\u002Frate-limits-quotas.md` for detailed quota management.\n\n## Blog Workflow Integration\n\nThis skill is both user-invocable (`\u002Fblog google pagespeed`) and callable\ninternally by other blog sub-skills:\n\n- **blog-seo-check**: Runs PSI + CrUX on published post URL for live CWV data\n- **blog-rewrite**: NLP entity analysis to identify E-E-A-T entity gaps\n- **blog-geo**: GSC performance data for real search appearance insights\n- **blog-audit**: Batch CWV + indexation checks across all published blog URLs\n- **blog-write \u002F blog-rewrite**: YouTube search for video embedding\n\nFalls back gracefully when credentials are not configured.\n\n## Report Templates\n\nUse the bundled templates when a workflow requests a durable human-readable\nreport. Keep unavailable account data marked `SKIPPED`; never fill an empty\nsection with estimated metrics.\n\n- `assets\u002Ftemplates\u002Fcwv-audit-report.md` for PageSpeed and CrUX evidence.\n- `assets\u002Ftemplates\u002Fgsc-performance-report.md` for Search Analytics exports.\n- `assets\u002Ftemplates\u002Findexation-status-report.md` for URL Inspection evidence.\n\n## Technical Notes\n\n- INP replaced FID on March 12, 2024. Never reference FID.\n- CLS values from CrUX are string-encoded (e.g., \"0.05\"). Scripts handle parsing.\n- CrUX 404 = insufficient Chrome traffic, not an auth error.\n- Search Analytics data has 2-3 day lag.\n- Indexing API is officially for JobPosting\u002FBroadcastEvent pages only.\n- Most integrations have no usage fee within quota. Cloud Natural Language\n  requires billing and can incur charges; Google Ads requires account and\n  developer-token access.\n- Read `references\u002Fsearch-currentness.md` before diagnosing a named update,\n  canonical change, Discover visibility, Google generative-AI reporting,\n  platform properties, Preferred Sources, AMP, or crawler byte-limit issue.\n- A named update's dates do not prove what caused an individual site's change.\n  Wait one full week after rollout before comparing data, and separate Web,\n  Image, Video, and News performance.\n- Googlebot processes only the first 2MB of supported files and first 64MB of\n  PDFs. Keep critical metadata and primary content before the cutoff.\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| No credentials configured | Run `\u002Fblog google setup`. List Tier 0 commands (API key only). |\n| Service account lacks GSC access | Add `client_email` to GSC > Settings > Users > Add. |\n| CrUX data unavailable (404) | Insufficient Chrome traffic. Use PSI lab data as fallback. |\n| GA4 property not found | Find property ID in GA4 Admin > Property Details. |\n| Indexing API quota exceeded | 200\u002Fday limit. Prioritize most important URLs. |\n| Rate limit (429) | Wait and retry with exponential backoff. |\n",{"name":5,"license":15,"metadata":24,"description":28,"argument-hint":29,"user-invokable":30},{"author":25,"version":26,"category":27},"AgriciDaniel","2.2.0","blog","Google API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth\u002Fservice account, GA4, Ads). Shares config with claude-seo at ~\u002F.config\u002Fclaude-seo\u002Fgoogle-api.json. Use when user says \"google data\", \"page speed\", \"core web vitals\", \"search console\", \"indexation\", \"GA4\", \"keyword research\", \"nlp entities\", \"blog performance\", \"youtube search\", \"google api setup\".\n","[setup|pagespeed|crux|crux-history|gsc|inspect|index|ga4|nlp|youtube|keywords|report|quotas] [url|property|query]",true,"main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-imp-blog-google",1,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis","https:\u002F\u002Fgithub.com\u002FTanNhatCMS","https:\u002F\u002Fmrkiet.name.vn","2026-11-07 14:23:08",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":30},[41,44,47],{"tool":42,"command":43},"npx","npx skills add TanNhatCMS\u002Fjarvis --skill blog-google",{"tool":45,"command":46},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill blog-google",{"tool":48,"command":49},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill blog-google","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-blog-google\u002FSKILL.md",[52,58,62,66,72,76,80],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"assets\u002Ftemplates\u002Fcwv-audit-report.md","ASSET","资产文件",1587,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-blog-google\u002Fassets\u002Ftemplates\u002Fcwv-audit-report.md",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"assets\u002Ftemplates\u002Fgsc-performance-report.md",1214,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-blog-google\u002Fassets\u002Ftemplates\u002Fgsc-performance-report.md",{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"assets\u002Ftemplates\u002Findexation-status-report.md",1126,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-blog-google\u002Fassets\u002Ftemplates\u002Findexation-status-report.md",{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fapi-reference.md","REFERENCE","参考文档",8990,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-blog-google\u002Freferences\u002Fapi-reference.md",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fauth-setup.md",5426,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-blog-google\u002Freferences\u002Fauth-setup.md",{"path":77,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Frate-limits-quotas.md",4057,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-blog-google\u002Freferences\u002Frate-limits-quotas.md",{"path":81,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fsearch-currentness.md",10023,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-imp-blog-google\u002Freferences\u002Fsearch-currentness.md",[85,92,100,107,114,121],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7EWYJR0J8DARY7E59Z6Y9MV","web-scrape","Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open\u002Ffetch fails on JS-heavy pages, or when you need clean markdown\u002Fstructured extraction from a site. Requires FIRECRAWL_API_KEY.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fweb-scrape\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7EWYBN5P6F2AJG3FR24T9BP","design-taste-frontend","tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML\u002FCSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, \"AI-made\", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7EWY8FQFNQ2GB7NZZWGSSDX","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-tdd\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7EWY5SHBFRH1HDHVWM9K7TV","systematic-debugging","Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-debugging\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M7EWY3NM0Z0JAKS7HDZ24K66","requesting-code-review","Use when completing tasks, implementing major features, or before merging to verify work meets requirements","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-code-review\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":19},"01M7EWY0WRMWX4M9ZFY0WKC593","brainstorming","You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-brainstorming\u002FSKILL.md",[],[]]