[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PZ4Q7V42MQJD5GS6DYM03J":3,"skill-same:01M6PZ4Q7V42MQJD5GS6DYM03J":93},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":27,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":35,"commitSha":74,"skillDirectory":75,"forksCount":13,"repositoryHtmlUrl":76,"repositoryHomepageUrl":6,"ownerHtmlUrl":77,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":78,"install":79,"resources":92},"01M6PZ4Q7V42MQJD5GS6DYM03J","sql-sentinel",null,"Audit SQL for the cost & performance anti-patterns that burn warehouse credits. Scores warehouse health 0-100 and outputs a prioritized cost-reduction plan for BigQuery, Snowflake, Redshift, and Postgres.","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fsql-sentinel\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"sql","sql sentinel","sentinel","anti-patterns","clone","critical","patterns","main","postgres","community","credits","only","performance","plan","data","audit","snowflake","redshift","run","commit","2026-11-10 10:12:30",false,"---\nname: sql-sentinel\ndescription: \"Audit SQL for the cost & performance anti-patterns that burn warehouse credits. Scores warehouse health 0-100 and outputs a prioritized cost-reduction plan for BigQuery, Snowflake, Redshift, and Postgres.\"\ncategory: data\nrisk: critical\nsource: community\nsource_repo: takeaseatventure\u002Fsql-sentinel\nsource_type: community\ndate_added: \"2026-06-26\"\nauthor: takeaseat\ntags: [sql, bigquery, snowflake, redshift, postgres, data-warehouse, cost-optimization, performance, audit, finops]\ntools: [claude, cursor, codex, gemini]\nplugin:\n  targets:\n    codex: blocked\n    claude: blocked\n  setup:\n    type: manual\n    summary: \"Clone the upstream analyzer only after pinning or reviewing the exact commit to run.\"\n    docs: SKILL.md\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Ftakeaseatventure\u002Fsql-sentinel\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# sql-sentinel\n\n## Overview\n\nA static-analysis skill that audits SQL for the cost & performance anti-patterns that dominate warehouse bills — `SELECT *`, full-table scans, non-sargable predicates, Cartesian joins, the `NOT IN` NULL trap, and 15 more. It scores warehouse query health 0-100 (A-F) and outputs a prioritized cost-reduction plan, each finding with a `why`, a concrete `fix`, and an estimated savings.\n\nBuilt for analytics engineers (dbt, Looker), data platform teams running FinOps \u002F \"reduce cloud spend\" initiatives, and anyone reviewing a SQL pull request before it hits production. Works across BigQuery, Snowflake, Redshift, and Postgres. Zero dependencies, MIT licensed.\n\nThe executable engine and full rule set live in the source repository: https:\u002F\u002Fgithub.com\u002Ftakeaseatventure\u002Fsql-sentinel. Treat that repository as third-party executable code.\n\n## When to Use This Skill\n\n- A user writes or reviews a query for BigQuery, Snowflake, Redshift, Postgres, or Spark SQL.\n- A user asks \"why is this query so slow?\" or \"why is my warehouse bill so high?\"\n- A user is about to promote a dashboard query or dbt model to production.\n- A data engineer wants a second pair of eyes before a code review or a cost-optimization sweep.\n- A team is running a \"reduce cloud spend\" or FinOps initiative.\n\n## How It Works\n\nThe engine splits a SQL script into statements (honoring quotes and comments), runs 20 rules over each statement, scores health 0-100 weighted by severity (critical 25, high 12, medium 5, low 1), and returns a prioritized cost-reduction plan.\n\n### Step 1: Run the audit\n\nInstall or clone the source repository only after choosing a reviewed commit, tag, or release to trust. Do not run code from a mutable default branch just because this skill links to it:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Ftakeaseatventure\u002Fsql-sentinel.git\ncd sql-sentinel\ngit checkout \u003Creviewed-commit-or-tag>\nnode scripts\u002Fsql-sentinel.js path\u002Fto\u002Fquery.sql\n```\n\nOr programmatically:\n\n```javascript\nconst { auditSql } = require('.\u002Fscripts\u002Fsql-sentinel');\nconst report = auditSql(yourSqlString, { dialect: 'bigquery' });\nconsole.log(report.healthScore);      \u002F\u002F 0-100\nconsole.log(report.grade);            \u002F\u002F 'A' | 'B' | 'C' | 'D' | 'E' | 'F'\nconsole.log(report.prioritizedPlan);  \u002F\u002F array, worst findings first\n```\n\n### Step 2: Read the prioritized plan\n\nThe output leads with critical findings (Cartesian joins, mass DELETE) and descends to low-severity style issues. Each finding explains *why* it costs money and *how* to fix it.\n\n## Examples\n\n### Example 1: A messy dashboard query\n\n```sql\nSELECT DISTINCT *\nFROM user_events, raw_logs\nWHERE LOWER(event_name) LIKE '%signup%'\n  AND user_id NOT IN (SELECT id FROM deleted_users)\nORDER BY created_at;\n```\n\nThe audit scores this 17\u002F100 (grade F) and flags 7 findings:\n- CRITICAL: comma-join produces a Cartesian product (can turn a $0.02 query into a $200 query)\n- HIGH: `SELECT *` forces full column scan (30-90% wasted bytes on wide tables)\n- HIGH: leading-wildcard `LIKE '%signup%'` defeats indexes\n- HIGH: `LOWER(event_name)` defeats indexes (non-sargable)\n- HIGH: `NOT IN (SELECT ...)` — NULL semantics hazard\n- MEDIUM: `SELECT DISTINCT` dedup cost\n- MEDIUM: `ORDER BY` without `LIMIT` sorts the full result\n\n### Example 2: A clean, sargable query\n\n```sql\n-- This scores 90+\u002F100 (grade A) — no findings\nSELECT id, email, created_at\nFROM users\nWHERE created_at >= TIMESTAMP '2026-01-01'\n  AND created_at \u003C  TIMESTAMP '2026-02-01'\nORDER BY id\nLIMIT 100;\n```\n\n## The 20 rules (ruleset v1.0.0)\n\n| Rule | Severity | Catches |\n|---|---|---|\n| SQL001 | high | `SELECT *` full column scan |\n| SQL002 | critical | No `WHERE` → full table scan |\n| SQL003 | high | `LIKE '%term'` non-sargable |\n| SQL004 | high | Function on column kills index |\n| SQL005 | critical | `CROSS JOIN` \u002F comma-join |\n| SQL006 | medium | `SELECT DISTINCT` dedup cost |\n| SQL007 | medium | `ORDER BY` without `LIMIT` |\n| SQL008 | high | `NOT IN (SELECT ...)` NULL trap |\n| SQL009 | medium | Implicit type cast |\n| SQL010 | low | Many `OR`s (use `IN`\u002F`UNION`) |\n| SQL011 | medium | `COUNT(DISTINCT)` at scale (use HLL) |\n| SQL012 | low | `LIMIT` without `ORDER BY` |\n| SQL013 | medium | Scalar subquery in `SELECT` |\n| SQL014 | medium | 5+ JOINs broadcast\u002Fspill risk |\n| SQL015 | high | Fact table, no partition filter |\n| SQL017 | low | String concat in `SELECT` |\n| SQL018 | medium | Window `OVER ()` no `PARTITION` |\n| SQL020 | critical | `DELETE`\u002F`UPDATE` without `WHERE` |\n| SQL021 | low | `SELECT *` in `EXISTS`\u002F`IN` |\n| SQL022 | medium | `UNION` vs `UNION ALL` |\n\nRun the test suite to verify each rule fires on real SQL:\n\n```bash\ncd scripts && node test.js   # 26 tests, zero dependencies\n```\n\n## Limitations\n\n- This is a **static** analyzer. It finds anti-patterns in the *text* of SQL; it does not read query plans, row counts, or billing. A flagged query on a 100-row table is cheap; the same query on a billion-row table is the problem the rule exists to prevent.\n- The fact-table heuristic (SQL015) keys off table *names* (`*_events`, `*_log`) and is advisory, not definitive.\n- It does not execute SQL — safe to run on any `.sql` file.\n","# sql-sentinel\n\n## Overview\n\nA static-analysis skill that audits SQL for the cost & performance anti-patterns that dominate warehouse bills — `SELECT *`, full-table scans, non-sargable predicates, Cartesian joins, the `NOT IN` NULL trap, and 15 more. It scores warehouse query health 0-100 (A-F) and outputs a prioritized cost-reduction plan, each finding with a `why`, a concrete `fix`, and an estimated savings.\n\nBuilt for analytics engineers (dbt, Looker), data platform teams running FinOps \u002F \"reduce cloud spend\" initiatives, and anyone reviewing a SQL pull request before it hits production. Works across BigQuery, Snowflake, Redshift, and Postgres. Zero dependencies, MIT licensed.\n\nThe executable engine and full rule set live in the source repository: https:\u002F\u002Fgithub.com\u002Ftakeaseatventure\u002Fsql-sentinel. Treat that repository as third-party executable code.\n\n## When to Use This Skill\n\n- A user writes or reviews a query for BigQuery, Snowflake, Redshift, Postgres, or Spark SQL.\n- A user asks \"why is this query so slow?\" or \"why is my warehouse bill so high?\"\n- A user is about to promote a dashboard query or dbt model to production.\n- A data engineer wants a second pair of eyes before a code review or a cost-optimization sweep.\n- A team is running a \"reduce cloud spend\" or FinOps initiative.\n\n## How It Works\n\nThe engine splits a SQL script into statements (honoring quotes and comments), runs 20 rules over each statement, scores health 0-100 weighted by severity (critical 25, high 12, medium 5, low 1), and returns a prioritized cost-reduction plan.\n\n### Step 1: Run the audit\n\nInstall or clone the source repository only after choosing a reviewed commit, tag, or release to trust. Do not run code from a mutable default branch just because this skill links to it:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Ftakeaseatventure\u002Fsql-sentinel.git\ncd sql-sentinel\ngit checkout \u003Creviewed-commit-or-tag>\nnode scripts\u002Fsql-sentinel.js path\u002Fto\u002Fquery.sql\n```\n\nOr programmatically:\n\n```javascript\nconst { auditSql } = require('.\u002Fscripts\u002Fsql-sentinel');\nconst report = auditSql(yourSqlString, { dialect: 'bigquery' });\nconsole.log(report.healthScore);      \u002F\u002F 0-100\nconsole.log(report.grade);            \u002F\u002F 'A' | 'B' | 'C' | 'D' | 'E' | 'F'\nconsole.log(report.prioritizedPlan);  \u002F\u002F array, worst findings first\n```\n\n### Step 2: Read the prioritized plan\n\nThe output leads with critical findings (Cartesian joins, mass DELETE) and descends to low-severity style issues. Each finding explains *why* it costs money and *how* to fix it.\n\n## Examples\n\n### Example 1: A messy dashboard query\n\n```sql\nSELECT DISTINCT *\nFROM user_events, raw_logs\nWHERE LOWER(event_name) LIKE '%signup%'\n  AND user_id NOT IN (SELECT id FROM deleted_users)\nORDER BY created_at;\n```\n\nThe audit scores this 17\u002F100 (grade F) and flags 7 findings:\n- CRITICAL: comma-join produces a Cartesian product (can turn a $0.02 query into a $200 query)\n- HIGH: `SELECT *` forces full column scan (30-90% wasted bytes on wide tables)\n- HIGH: leading-wildcard `LIKE '%signup%'` defeats indexes\n- HIGH: `LOWER(event_name)` defeats indexes (non-sargable)\n- HIGH: `NOT IN (SELECT ...)` — NULL semantics hazard\n- MEDIUM: `SELECT DISTINCT` dedup cost\n- MEDIUM: `ORDER BY` without `LIMIT` sorts the full result\n\n### Example 2: A clean, sargable query\n\n```sql\n-- This scores 90+\u002F100 (grade A) — no findings\nSELECT id, email, created_at\nFROM users\nWHERE created_at >= TIMESTAMP '2026-01-01'\n  AND created_at \u003C  TIMESTAMP '2026-02-01'\nORDER BY id\nLIMIT 100;\n```\n\n## The 20 rules (ruleset v1.0.0)\n\n| Rule | Severity | Catches |\n|---|---|---|\n| SQL001 | high | `SELECT *` full column scan |\n| SQL002 | critical | No `WHERE` → full table scan |\n| SQL003 | high | `LIKE '%term'` non-sargable |\n| SQL004 | high | Function on column kills index |\n| SQL005 | critical | `CROSS JOIN` \u002F comma-join |\n| SQL006 | medium | `SELECT DISTINCT` dedup cost |\n| SQL007 | medium | `ORDER BY` without `LIMIT` |\n| SQL008 | high | `NOT IN (SELECT ...)` NULL trap |\n| SQL009 | medium | Implicit type cast |\n| SQL010 | low | Many `OR`s (use `IN`\u002F`UNION`) |\n| SQL011 | medium | `COUNT(DISTINCT)` at scale (use HLL) |\n| SQL012 | low | `LIMIT` without `ORDER BY` |\n| SQL013 | medium | Scalar subquery in `SELECT` |\n| SQL014 | medium | 5+ JOINs broadcast\u002Fspill risk |\n| SQL015 | high | Fact table, no partition filter |\n| SQL017 | low | String concat in `SELECT` |\n| SQL018 | medium | Window `OVER ()` no `PARTITION` |\n| SQL020 | critical | `DELETE`\u002F`UPDATE` without `WHERE` |\n| SQL021 | low | `SELECT *` in `EXISTS`\u002F`IN` |\n| SQL022 | medium | `UNION` vs `UNION ALL` |\n\nRun the test suite to verify each rule fires on real SQL:\n\n```bash\ncd scripts && node test.js   # 26 tests, zero dependencies\n```\n\n## Limitations\n\n- This is a **static** analyzer. It finds anti-patterns in the *text* of SQL; it does not read query plans, row counts, or billing. A flagged query on a 100-row table is cheap; the same query on a billion-row table is the problem the rule exists to prevent.\n- The fact-table heuristic (SQL015) keys off table *names* (`*_events`, `*_log`) and is advisory, not definitive.\n- It does not execute SQL — safe to run on any `.sql` file.\n",{"name":5,"risk":33,"tags":53,"tools":58,"author":63,"plugin":64,"source":37,"license":14,"category":42,"date_added":71,"description":7,"source_repo":72,"source_type":37,"license_source":73},[28,54,44,45,36,55,56,40,43,57],"bigquery","data-warehouse","cost-optimization","finops",[59,60,61,62],"claude","cursor","codex","gemini","takeaseat",{"setup":65,"targets":69},{"docs":66,"type":67,"summary":68},"SKILL.md","manual","Clone the upstream analyzer only after pinning or reviewing the exact commit to run.",{"codex":70,"claude":70},"blocked","2026-06-26","takeaseatventure\u002Fsql-sentinel","https:\u002F\u002Fgithub.com\u002Ftakeaseatventure\u002Fsql-sentinel\u002Fblob\u002Fmain\u002FLICENSE","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Fsql-sentinel","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":80,"prompt":90,"zipAvailable":91},[81,84,87],{"tool":82,"command":83},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill sql-sentinel",{"tool":85,"command":86},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill sql-sentinel",{"tool":88,"command":89},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill sql-sentinel","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fsql-sentinel\u002FSKILL.md",true,[],[94,119,142,166,189,213],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":103,"publishedAt":48},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[100],{"categoryNo":101,"categoryName":102,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[104,105,106,107,108,109,96,110,111,112,113,39,37,35,114,33,115,116,117,118],"ZeRO","trust","zero trust","architecture","assessment","verification","segmentation","devops-security","access","configure","active","scope","scripts","relevant","implementing",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":48},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[126,127,128,129,130,131,132,46,133,134,135,136,137,39,138,37,139,140,33,141],"delegate","zcode","zcode delegate","review","cli","orchestration","tasks","Bash","model","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":48},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[149,150,151,152,153,61,154,155,156,157,158,159,160,37,35,161,162,163,164,165],"transcript","youtube transcript","youtube","safe","github","research","license","https","text","fetch","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":179,"publishedAt":48},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[172,173,176],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":174,"categoryName":175,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":177,"categoryName":178,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000030","开发工程师",[149,150,151,180,152,62,153,61,155,181,182,183,184,158,185,37,35,186,187,188],"youtube transcript skills","search","api","Video","browse","api-integration","free","card","channels",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":199,"publishedAt":48},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker","Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[195,198],{"categoryNo":196,"categoryName":197,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":174,"categoryName":175,"taxonomyType":20,"taxonomyTypeDesc":21},[151,200,201,130,152,202,203,204,205,155,183,206,207,208,209,35,210,161,211,212],"youtube notetaker","notetaker","workflow","official","notes","code","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":220,"publishedAt":48},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[219],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[221,151,222,223,152,62,181,224,225,182,183,184,158,38,185,37,35,186,226,164],"youtube full","full","google","server","dlp","automatic"]