[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75EFSJTGRW0JBQKWTBSCXT3":3,"skill-same:01M75EFSJTGRW0JBQKWTBSCXT3":87},{"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":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M75EFSJTGRW0JBQKWTBSCXT3","meta-ad-builder",null,"Publish finished creatives as live Meta (Facebook\u002FInstagram) ads via the Meta Marketing API, plus research and ad-copy support. Uploads an image or video, builds a multi-variant TEXT_LIQUIDITY creative, and creates a PAUSED ad in an existing ad set. Also pulls top-performing ads (ranked by ROAS) and competitor ads from the Ad Library to inform copy. Use when the user asks to deploy \u002F publish \u002F launch a creative as a Meta or Facebook ad, build a Meta ad, push a video or image into an ad set, pull their top ads, or research competitor ads. Not for generating creative (use the image\u002Fvideo skills) and not for writing AdTable\u002FAirtable rows (use adtable-light).","LongLeo287\u002FSEOSONA-OS","LongLeo287","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F141803367?v=4","01M6JK75C62VCNZKR5BRZ386YV","LongLeo","01M75CK60XQGYJY3YDGGFJQDYT",2,"MIT","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fmarketing_creative\u002Fmeta-ad-builder\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: meta-ad-builder\ndescription: >-\n  Publish finished creatives as live Meta (Facebook\u002FInstagram) ads via the Meta\n  Marketing API, plus research and ad-copy support. Uploads an image or video,\n  builds a multi-variant TEXT_LIQUIDITY creative, and creates a PAUSED ad in an\n  existing ad set. Also pulls top-performing ads (ranked by ROAS) and competitor\n  ads from the Ad Library to inform copy. Use when the user asks to deploy \u002F\n  publish \u002F launch a creative as a Meta or Facebook ad, build a Meta ad, push a\n  video or image into an ad set, pull their top ads, or research competitor ads.\n  Not for generating creative (use the image\u002Fvideo skills) and not for writing\n  AdTable\u002FAirtable rows (use adtable-light).\n---\n\n# Meta ad builder\n\nTurn a finished creative — typically the output of a generative-AI skill in this\nworkspace — into a live Meta ad. The skill covers three phases: **research**\n(optional) → **copy** → **deploy**. It talks to the Meta Marketing API directly\nvia ported, parameterized Python scripts.\n\n## When to use this skill\n\nTrigger on phrases like:\n- \"deploy this video to Meta\" \u002F \"publish this as a Facebook ad\"\n- \"build\u002Flaunch a Meta ad\" \u002F \"push this creative into \u003Cad set>\"\n- \"create a Meta ad with this image and copy\"\n- \"pull my top-performing ads\" \u002F \"what are my best ads by ROAS\"\n- \"research competitor ads\" \u002F \"pull \u003Cbrand>'s ads from the Ad Library\"\n\nDo **not** use this skill to *generate* creative — that's `pixar-style-ad`,\n`claymation-ad`, `generate-youtube-thumbnail`, `uni1-image-ad`, etc. Do not use\nit to write AdTable\u002FAirtable rows — that's `adtable-light`. This skill is the\n*direct Meta Marketing API* deployment step.\n\n## Read order\n\n1. **This file** — workflow, decision tree, safety rules.\n2. **[prompting\u002Fcopy-guide.md](prompting\u002Fcopy-guide.md)** — the 5-body \u002F 5-title \u002F\n   3-description frameworks and the `--copy-file` JSON shape.\n3. **[reference\u002Fdeploy-patterns.md](reference\u002Fdeploy-patterns.md)** — creative\n   spec mechanics, video polling, retry, failure modes.\n4. **[reference\u002Fmeta-api-cheatsheet.md](reference\u002Fmeta-api-cheatsheet.md)** — the\n   full Meta Marketing API reference (campaigns, ad sets, ads, enums, gotchas,\n   Ad Library). Consult as needed; don't read end-to-end.\n\n## Prerequisites\n\n- **Env** (in `.env` — see your repo's `.env.example`):\n  - `META_ACCESS_TOKEN` (required) — long-lived token with `ads_management` scope\n  - `META_AD_ACCOUNT_ID` (required) — with or without the `act_` prefix\n  - `META_PAGE_ID`, `META_IG_USER_ID`, `META_PIXEL_ID` (optional defaults for deploy)\n  - `META_API_VERSION` (optional, default `v23.0`)\n- **Python deps:** `python3 -m pip install -r scripts\u002Frequirements.txt`\n- **A target ad set** that already exists. The skill deploys ads into an existing\n  ad set — it does not create campaigns or ad sets. If the user needs a new ad\n  set, create it in Ads Manager or via the cheatsheet §3–§4 first.\n- **The finished creative on disk** — an image or video file path. Chat-pasted\n  files are not accessible; ask the user for a real path.\n\nRun `bash scripts\u002Fcheck-meta-env.sh` to verify credentials before anything else.\n\n## Workflow\n\n### Phase 1 — Research (optional, when copy should model winners)\n\n```bash\n# Rank the account's ads and pull the winning copy\npython scripts\u002Fpull-top-ads.py --date-preset last_30d --min-spend 100 --limit 15\n\n# Pull a competitor's ads from the Ad Library\npython scripts\u002Fpull-competitor-ads.py --pages \"BrandName\" --limit 50\n```\n\nBoth write JSON under `OUTPUT_BASE` (or `.\u002Foutputs\u002Fmeta-ads\u002F`). Read the top-ad\n`copy` fields to identify winning hook\u002Fproof\u002FCTA patterns before writing new copy.\n\n### Phase 2 — Copy\n\nWrite a `copy.json` following **[copy-guide.md](prompting\u002Fcopy-guide.md)**:\n5 bodies (one per framework angle), 5 titles, 3 descriptions. If Phase 1 ran,\nmirror the voice and patterns of the winners — new creative + proven copy DNA.\nSave `copy.json` somewhere under `outputs\u002F` so it isn't committed.\n\n### Phase 3 — Deploy\n\n**Always dry-run first** — it prints the full creative payload, makes no API calls:\n\n```bash\npython scripts\u002Fdeploy-ad.py --dry-run \\\n  --adset-id \u003CAD_SET_ID> --copy-file copy.json --link \u003CDESTINATION_URL> \\\n  --image path\u002Fto\u002Fcreative.png\n```\n\nReview the payload with the user, then deploy for real:\n\n```bash\npython scripts\u002Fdeploy-ad.py \\\n  --adset-id \u003CAD_SET_ID> --copy-file copy.json --link \u003CDESTINATION_URL> \\\n  --video clip-a.mp4 --video clip-b.mp4 --cta SIGN_UP --pixel-id \u003CPIXEL_ID>\n```\n\n- `--image` \u002F `--video` are repeatable — each becomes its own ad in the ad set.\n- Every ad is created **PAUSED**. Tell the user to review and un-pause in Meta\n  Ads Manager. The skill never launches a spending ad automatically.\n- Results (ad IDs) are written to `deployment_results.json` under `OUTPUT_BASE`.\n\n## Decision tree\n\n| User intent | Phases |\n|---|---|\n| \"Deploy this creative to Meta\" + copy provided | Phase 3 only |\n| \"Build a Meta ad, write the copy too\" | Phase 2 → 3 |\n| \"Make ads modeled on my winners\" | Phase 1 → 2 → 3 |\n| \"What are my best ads \u002F competitor research\" | Phase 1 only |\n\n## Safety rules\n\n- **Ads deploy PAUSED.** Never add an `--active` override or un-pause ads without\n  an explicit user instruction. Confirm the user knows the ads are paused.\n- **Dry-run before every real deploy.** Show the payload; get a go-ahead.\n- **Confirm the target ad set and destination URL** with the user before\n  deploying — an ad in the wrong ad set spends against the wrong budget.\n- **Deploying ads is a shared-state, money-adjacent action.** Treat the live\n  `deploy-ad.py` run as something to confirm, not assume.\n- The skill creates ads only — it does **not** create or edit campaigns, ad sets,\n  budgets, or audiences. Those stay manual.\n\n## Quirks and pitfalls\n\n- **Video processing is async.** `deploy-ad.py` polls the uploaded video until\n  Meta finishes processing before creating the ad — a video deploy can take a\n  few minutes. See [deploy-patterns.md](reference\u002Fdeploy-patterns.md).\n- **Transient `OAuthException` (code 2).** Retried automatically with backoff.\n- **`act_` prefix** is added automatically if missing from `META_AD_ACCOUNT_ID`.\n- **Account-specific data stays out of git.** All output routes through\n  `outputs\u002F` (gitignored): ad IDs, pulled spend\u002Frevenue, competitor data.\n- **Special Ad Categories** (credit, employment, housing, social issues) change\n  ad-set targeting rules — flag to the user; see cheatsheet §3.5.\n\n## Cost note\n\nThe Meta Marketing API itself is free to call. **Ad spend is real money** — but\nbecause every ad deploys PAUSED, nothing spends until the user un-pauses it in\nAds Manager. There are no per-call credits to estimate.\n","# Meta ad builder\n\nTurn a finished creative — typically the output of a generative-AI skill in this\nworkspace — into a live Meta ad. The skill covers three phases: **research**\n(optional) → **copy** → **deploy**. It talks to the Meta Marketing API directly\nvia ported, parameterized Python scripts.\n\n## When to use this skill\n\nTrigger on phrases like:\n- \"deploy this video to Meta\" \u002F \"publish this as a Facebook ad\"\n- \"build\u002Flaunch a Meta ad\" \u002F \"push this creative into \u003Cad set>\"\n- \"create a Meta ad with this image and copy\"\n- \"pull my top-performing ads\" \u002F \"what are my best ads by ROAS\"\n- \"research competitor ads\" \u002F \"pull \u003Cbrand>'s ads from the Ad Library\"\n\nDo **not** use this skill to *generate* creative — that's `pixar-style-ad`,\n`claymation-ad`, `generate-youtube-thumbnail`, `uni1-image-ad`, etc. Do not use\nit to write AdTable\u002FAirtable rows — that's `adtable-light`. This skill is the\n*direct Meta Marketing API* deployment step.\n\n## Read order\n\n1. **This file** — workflow, decision tree, safety rules.\n2. **[prompting\u002Fcopy-guide.md](prompting\u002Fcopy-guide.md)** — the 5-body \u002F 5-title \u002F\n   3-description frameworks and the `--copy-file` JSON shape.\n3. **[reference\u002Fdeploy-patterns.md](reference\u002Fdeploy-patterns.md)** — creative\n   spec mechanics, video polling, retry, failure modes.\n4. **[reference\u002Fmeta-api-cheatsheet.md](reference\u002Fmeta-api-cheatsheet.md)** — the\n   full Meta Marketing API reference (campaigns, ad sets, ads, enums, gotchas,\n   Ad Library). Consult as needed; don't read end-to-end.\n\n## Prerequisites\n\n- **Env** (in `.env` — see your repo's `.env.example`):\n  - `META_ACCESS_TOKEN` (required) — long-lived token with `ads_management` scope\n  - `META_AD_ACCOUNT_ID` (required) — with or without the `act_` prefix\n  - `META_PAGE_ID`, `META_IG_USER_ID`, `META_PIXEL_ID` (optional defaults for deploy)\n  - `META_API_VERSION` (optional, default `v23.0`)\n- **Python deps:** `python3 -m pip install -r scripts\u002Frequirements.txt`\n- **A target ad set** that already exists. The skill deploys ads into an existing\n  ad set — it does not create campaigns or ad sets. If the user needs a new ad\n  set, create it in Ads Manager or via the cheatsheet §3–§4 first.\n- **The finished creative on disk** — an image or video file path. Chat-pasted\n  files are not accessible; ask the user for a real path.\n\nRun `bash scripts\u002Fcheck-meta-env.sh` to verify credentials before anything else.\n\n## Workflow\n\n### Phase 1 — Research (optional, when copy should model winners)\n\n```bash\n# Rank the account's ads and pull the winning copy\npython scripts\u002Fpull-top-ads.py --date-preset last_30d --min-spend 100 --limit 15\n\n# Pull a competitor's ads from the Ad Library\npython scripts\u002Fpull-competitor-ads.py --pages \"BrandName\" --limit 50\n```\n\nBoth write JSON under `OUTPUT_BASE` (or `.\u002Foutputs\u002Fmeta-ads\u002F`). Read the top-ad\n`copy` fields to identify winning hook\u002Fproof\u002FCTA patterns before writing new copy.\n\n### Phase 2 — Copy\n\nWrite a `copy.json` following **[copy-guide.md](prompting\u002Fcopy-guide.md)**:\n5 bodies (one per framework angle), 5 titles, 3 descriptions. If Phase 1 ran,\nmirror the voice and patterns of the winners — new creative + proven copy DNA.\nSave `copy.json` somewhere under `outputs\u002F` so it isn't committed.\n\n### Phase 3 — Deploy\n\n**Always dry-run first** — it prints the full creative payload, makes no API calls:\n\n```bash\npython scripts\u002Fdeploy-ad.py --dry-run \\\n  --adset-id \u003CAD_SET_ID> --copy-file copy.json --link \u003CDESTINATION_URL> \\\n  --image path\u002Fto\u002Fcreative.png\n```\n\nReview the payload with the user, then deploy for real:\n\n```bash\npython scripts\u002Fdeploy-ad.py \\\n  --adset-id \u003CAD_SET_ID> --copy-file copy.json --link \u003CDESTINATION_URL> \\\n  --video clip-a.mp4 --video clip-b.mp4 --cta SIGN_UP --pixel-id \u003CPIXEL_ID>\n```\n\n- `--image` \u002F `--video` are repeatable — each becomes its own ad in the ad set.\n- Every ad is created **PAUSED**. Tell the user to review and un-pause in Meta\n  Ads Manager. The skill never launches a spending ad automatically.\n- Results (ad IDs) are written to `deployment_results.json` under `OUTPUT_BASE`.\n\n## Decision tree\n\n| User intent | Phases |\n|---|---|\n| \"Deploy this creative to Meta\" + copy provided | Phase 3 only |\n| \"Build a Meta ad, write the copy too\" | Phase 2 → 3 |\n| \"Make ads modeled on my winners\" | Phase 1 → 2 → 3 |\n| \"What are my best ads \u002F competitor research\" | Phase 1 only |\n\n## Safety rules\n\n- **Ads deploy PAUSED.** Never add an `--active` override or un-pause ads without\n  an explicit user instruction. Confirm the user knows the ads are paused.\n- **Dry-run before every real deploy.** Show the payload; get a go-ahead.\n- **Confirm the target ad set and destination URL** with the user before\n  deploying — an ad in the wrong ad set spends against the wrong budget.\n- **Deploying ads is a shared-state, money-adjacent action.** Treat the live\n  `deploy-ad.py` run as something to confirm, not assume.\n- The skill creates ads only — it does **not** create or edit campaigns, ad sets,\n  budgets, or audiences. Those stay manual.\n\n## Quirks and pitfalls\n\n- **Video processing is async.** `deploy-ad.py` polls the uploaded video until\n  Meta finishes processing before creating the ad — a video deploy can take a\n  few minutes. See [deploy-patterns.md](reference\u002Fdeploy-patterns.md).\n- **Transient `OAuthException` (code 2).** Retried automatically with backoff.\n- **`act_` prefix** is added automatically if missing from `META_AD_ACCOUNT_ID`.\n- **Account-specific data stays out of git.** All output routes through\n  `outputs\u002F` (gitignored): ad IDs, pulled spend\u002Frevenue, competitor data.\n- **Special Ad Categories** (credit, employment, housing, social issues) change\n  ad-set targeting rules — flag to the user; see cheatsheet §3.5.\n\n## Cost note\n\nThe Meta Marketing API itself is free to call. **Ad spend is real money** — but\nbecause every ad deploys PAUSED, nothing spends until the user un-pauses it in\nAds Manager. There are no per-call credits to estimate.\n",{"name":5,"description":7},"main","4fd50b1281e8cd978866b6b4556242605cabf708","2_KNOWLEDGE\u002Fframeworks\u002Fmarketing_creative\u002Fmeta-ad-builder",1,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS","https:\u002F\u002Fseosona-os.vercel.app","https:\u002F\u002Fgithub.com\u002FLongLeo287","https:\u002F\u002Fwww.facebook.com\u002FResourceRookie2023","2026-10-09 15:14:13",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add LongLeo287\u002FSEOSONA-OS --skill meta-ad-builder",{"tool":39,"command":40},"bunx","bunx skills add LongLeo287\u002FSEOSONA-OS --skill meta-ad-builder",{"tool":42,"command":43},"pnpm","pnpm dlx skills add LongLeo287\u002FSEOSONA-OS --skill meta-ad-builder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fmarketing_creative\u002Fmeta-ad-builder\u002FSKILL.md",true,[47,53,57,61,67,71,75,79,83],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"prompting\u002Fcopy-guide.md","REFERENCE","参考文档",4002,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fmarketing_creative\u002Fmeta-ad-builder\u002Fprompting\u002Fcopy-guide.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"reference\u002Fdeploy-patterns.md",4687,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fmarketing_creative\u002Fmeta-ad-builder\u002Freference\u002Fdeploy-patterns.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"reference\u002Fmeta-api-cheatsheet.md",40736,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fmarketing_creative\u002Fmeta-ad-builder\u002Freference\u002Fmeta-api-cheatsheet.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck-meta-env.sh","SCRIPT","脚本",2107,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fmarketing_creative\u002Fmeta-ad-builder\u002Fscripts\u002Fcheck-meta-env.sh",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fdeploy-ad.py",10050,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fmarketing_creative\u002Fmeta-ad-builder\u002Fscripts\u002Fdeploy-ad.py",{"path":72,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Flib\u002Fmeta_api.py",6326,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fmarketing_creative\u002Fmeta-ad-builder\u002Fscripts\u002Flib\u002Fmeta_api.py",{"path":76,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fpull-competitor-ads.py",7441,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fmarketing_creative\u002Fmeta-ad-builder\u002Fscripts\u002Fpull-competitor-ads.py",{"path":80,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Fpull-top-ads.py",7203,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fmarketing_creative\u002Fmeta-ad-builder\u002Fscripts\u002Fpull-top-ads.py",{"path":84,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002Frequirements.txt",146,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fmarketing_creative\u002Fmeta-ad-builder\u002Fscripts\u002Frequirements.txt",[88,95,102,109,116,123],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M75F0T3V3W7JQQ05X26NNN2T","web_crawler_katana","High-speed web crawling using Katana patterns for deep site mapping, URL discovery, and content extraction.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fweb_crawler_katana\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M75F0Q2QJXDGAFKC7D84GT88","server_log_analyzer","Analyzes Nginx\u002FApache server logs to identify Googlebot crawl patterns, errors, and performance bottlenecks.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fserver_log_analyzer\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M75F0KZP6D8R8XPN2YT35BAJ","schema_markup_generator","Auto-generates JSON-LD structured data for any page type (Article, Product, FAQ, LocalBusiness, etc.).","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fschema_markup_generator\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M75F0G3KX4Y86AXJXTKXVEVA","internal_linking_optimizer","Analyzes and optimizes the internal link graph of a website for SEO authority distribution.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Finternal_linking_optimizer\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":19},"01M75F0CS1RYX4YPJC7N6RAAQJ","google_trends_analyzer","Detects trending topics and seasonal patterns using Google Trends data for content planning and keyword strategy.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fgoogle_trends_analyzer\u002FSKILL.md",[],[],{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":19},"01M75F0ASMQ1GKPFX82D19SRTN","brand_context_analyzer","Tracks brand mentions, sentiment, and online reputation across web sources.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fbrand_context_analyzer\u002FSKILL.md",[],[]]