[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75RG8Z2FE4XAAYG1BSWDR4N":3,"skill-same:01M75RG8Z2FE4XAAYG1BSWDR4N":48},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M75RG8Z2FE4XAAYG1BSWDR4N","seo",null,"Optimize YouTube titles, descriptions, and tags using competitive research. Analyzes top-performing videos on the topic, identifies keyword patterns and CTR hooks, and generates SEO-optimized titles with scorecards. Optionally generates social media titles. Triggers on: seo optimize, optimize title, youtube seo, optimize description, title ideas, seo this video, improve my title.","jayozer\u002Fjay-marketplace","jayozer","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1474896?v=4","01M75RFSSP3SF9YENHHZ2YNMR8","Jay Ozer","01M75RFST8CQ74PY997ZFPDDKC",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjayozer\u002Fjay-marketplace\u002Fblob\u002Fmain\u002Fyt-automation-kit\u002Fskills\u002Fseo\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: seo\ndescription: \"Optimize YouTube titles, descriptions, and tags using competitive research. Analyzes top-performing videos on the topic, identifies keyword patterns and CTR hooks, and generates SEO-optimized titles with scorecards. Optionally generates social media titles. Triggers on: seo optimize, optimize title, youtube seo, optimize description, title ideas, seo this video, improve my title.\"\nargument-hint: \"[topic or ~\u002Fyoutube\u002F\u003Cslug>\u002F]\"\nallowed-tools: Read, Write, Edit, Glob, Grep, WebSearch, WebFetch, AskUserQuestion\nuser-invocable: true\n---\n\nOptimize YouTube SEO for the video topic or package at $ARGUMENTS.\n\n## Workflow Context\n\n**Step 4 of the weekly content pipeline** (after `\u002Fyt`). Run once per long-form video package. After this, run `\u002Fcontent` to generate the LinkedIn + YT Community text posts for that video.\n\n## Data Location\n\n- If a video package exists at `~\u002Fyoutube\u002F\u003Cslug>\u002F`: updates `titles.md` and `description.md` in place (adds SEO section)\n- Standalone: outputs to `~\u002Fyoutube\u002F\u003Cslug>\u002Fseo.md`\n\n## Flow\n\n### Step 1: Gather Context\n\nDetermine the input:\n\n- **Video package path** (`~\u002Fyoutube\u002F\u003Cslug>\u002F`): Read `titles.md`, `script.md`, `description.md`, `analysis.md`, and `performance.md` if they exist. The `performance.md` file tracks previously tried titles and thumbnails - never suggest a title that's already been tried.\n- **Topic\u002Ftitle string**: Use it directly as the starting point\n- **No argument**: Ask the user for their video topic or title\n\nExtract:\n- The core topic and primary keyword\n- Any existing titles to improve on\n- The video's key points and value proposition (from script if available)\n\nCheck if `--social` flag is present in $ARGUMENTS — if so, also generate social media titles in the output.\n\n### Step 2: Competitive Research (WebSearch)\n\nThis step is NOT optional — always do real research.\n\n**First, check for existing research from `\u002Fyt`:** If a video package exists at `~\u002Fyoutube\u002F\u003Cslug>\u002Fanalysis.md`, read it. The `\u002Fyt` skill already runs 4-6 web searches and saves competitor data, content gaps, and community sentiment. Extract what's already there:\n- Competitor video titles and view counts\n- Keywords and phrases already identified\n- Content gaps already noted\n\n**Then fill in SEO-specific gaps** — only run searches for data NOT already in `analysis.md`. Typically this means 2-3 targeted searches instead of 5-6:\n\n1. **YouTube autocomplete**: Search `\u003Ctopic> youtube autocomplete suggestions` and `\u003Ctopic> how to \u002F vs \u002F best \u002F tutorial` to find what people actually search for\n2. **Title patterns**: Search for variations of the topic to see how different creators title similar content (skip if analysis.md already has 10+ competitor titles)\n3. **Related keywords**: Search for synonyms, related terms, and long-tail variations\n4. **Trending angles**: Search for recent news\u002Fdevelopments about the topic that could inform timely title angles (skip if analysis.md has recent news)\n\n**If no analysis.md exists** (standalone SEO run without `\u002Fyt`), run the full 5-6 searches:\n\n1. **Top videos on this topic**: Search `\"\u003Ctopic>\" site:youtube.com` and `\u003Ctopic> youtube` to find the top-performing videos\n2. **Title patterns**: Search for variations of the topic to see how different creators title similar content\n3. **YouTube autocomplete**: Search `\u003Ctopic> youtube autocomplete suggestions` and `\u003Ctopic> how to \u002F vs \u002F best \u002F tutorial` to find what people actually search for\n4. **Related keywords**: Search for synonyms, related terms, and long-tail variations\n5. **Trending angles**: Search for recent news\u002Fdevelopments about the topic that could inform timely title angles\n6. **Competitor analysis**: Search for the top creators in this niche and analyze their title patterns\n\nFor each search, note:\n- Video titles that appeared\n- View counts where visible\n- Common keywords and phrases\n- Title formulas being used (How to X, X vs Y, I tried X, etc.)\n\nPresent a **research summary** to the user:\n- Top 10-15 competitor titles with view counts\n- Most common keywords (ranked by frequency)\n- Title formulas that appear to perform well\n- Content gaps — angles nobody is using\n\n### Step 3: Generate SEO-Optimized Content\n\n#### Title Options (5 titles)\n\nFor each title:\n- **The title** — Under 70 characters (YouTube truncates after that)\n- **Character count** — Show the exact count\n- **CTR formula used** — Name the technique (curiosity gap, specific number, how-to, comparison, bold claim, etc.)\n- **Primary keyword** — What search term this targets\n- **Why it works** — One sentence on the psychology\u002FSEO reasoning\n\nRules for titles:\n- Front-load the most important keyword in the first 40 characters\n- Never use clickbait the video can't deliver on\n- Include at least one title using a number\u002Fspecific claim\n- Include at least one curiosity-driven title\n- Include at least one direct\u002Fsearch-optimized title\n- Avoid overused words: \"INSANE\", \"CRAZY\", \"YOU WON'T BELIEVE\"\n\n#### Title Scorecard\n\nRate each title on a 1-5 scale:\n\n| Title | Curiosity | Specificity | SEO Strength | Click Factor | Total |\n|-------|-----------|-------------|--------------|--------------|-------|\n\n- **Curiosity (1-5)** — Does it create an information gap the viewer wants to close?\n- **Specificity (1-5)** — Does it promise something concrete vs vague?\n- **SEO Strength (1-5)** — Does it contain high-volume searchable keywords?\n- **Click Factor (1-5)** — Would YOU click this in a sea of other thumbnails?\n\nMark the recommended title with the highest total score.\n\n#### Optimized Description\n\n- **First 2 lines** — These show in search results. Front-load keywords and value proposition. No fluff.\n- **Body** — Natural keyword density (2-3% target keyword occurrence). Include related keywords organically.\n- **Chapters section** — `00:00 - Title` format (use placeholders if timestamps unknown, mark with [UPDATE])\n- **Links section** — Placeholder for relevant links\n- **Tags line** — Keywords at the bottom for additional SEO signal\n\nIf an existing `description.md` exists, add a `## SEO-Optimized Version` section rather than replacing the original.\n\n#### Tags (15-20)\n\nOrganize tags in three tiers:\n1. **Exact match** (3-5) — The exact phrases people search for\n2. **Broad match** (5-7) — Related topics and category terms\n3. **Long-tail** (5-8) — Specific, lower-competition phrases\n\n#### Social Media Titles (if `--social` flag)\n\nGenerate platform-native titles:\n- **LinkedIn headline** — Professional, insight-driven (under 150 chars). Focus on the lesson or takeaway, not the video.\n- **TikTok\u002FReels caption** — Short, punchy, hook-first (under 100 chars). Create urgency or curiosity.\n- **Twitter\u002FX post** — Under 280 chars, curiosity-driven. Make it a standalone insight that happens to link to a video.\n\nRules for social titles:\n- These should NOT just be the YouTube title copy-pasted\n- Each platform has different psychology — LinkedIn = professional growth, TikTok = entertainment\u002Fdiscovery, Twitter = hot takes\u002Finsights\n- The social title should make the content feel native to that platform\n\n### Step 4: Present Results\n\nShow the user:\n1. The research summary (competitor titles + view counts)\n2. All 5 title options with the scorecard\n3. The recommended title (highlighted)\n4. The optimized description (first 3 lines preview)\n5. The tag list\n6. Social media titles (if generated)\n\n### Step 5: Iterate\n\nAsk: **\"Want to go with one of these, or want me to generate more variants of a specific style?\"**\n\nOptions:\n- Pick a title and finalize\n- Generate 5 more in the style of a specific title\n- Mix elements from multiple titles\n- Adjust the description\n- Regenerate with different target keywords\n\n## Output\n\nIf a video package exists at `~\u002Fyoutube\u002F\u003Cslug>\u002F`:\n- **Update `titles.md`**: Add a `## SEO-Optimized Titles` section with the new titles, scorecard, and research data\n- **Update `description.md`**: Add a `## SEO-Optimized Version` section with the new description and tags\n\nIf standalone (no existing package):\n- **Create `~\u002Fyoutube\u002F\u003Cslug>\u002Fseo.md`**: Contains all titles, scorecard, description, tags, research data, and social titles\n\nAlways include the research data (competitor titles with view counts) in the output so the user can see WHY each title works.\n\n## Rules\n\n- ALWAYS do competitive research — never skip Step 2. The research is what makes this valuable.\n- Titles must be under 70 characters — no exceptions\n- Front-load the most important keyword in the first 40 characters\n- Never use clickbait that the video can't deliver on\n- Description first 2 lines are crucial — they show in search results\n- Tags should include exact match, broad match, and long-tail variants\n- Social titles should be platform-native, not just the YouTube title reformatted\n- Always show the research data so the user can see the reasoning\n- Include ALL competitor titles and view counts in the output — transparency builds trust\n- If updating existing files, add new sections rather than overwriting the original content\n","Optimize YouTube SEO for the video topic or package at $ARGUMENTS.\n\n## Workflow Context\n\n**Step 4 of the weekly content pipeline** (after `\u002Fyt`). Run once per long-form video package. After this, run `\u002Fcontent` to generate the LinkedIn + YT Community text posts for that video.\n\n## Data Location\n\n- If a video package exists at `~\u002Fyoutube\u002F\u003Cslug>\u002F`: updates `titles.md` and `description.md` in place (adds SEO section)\n- Standalone: outputs to `~\u002Fyoutube\u002F\u003Cslug>\u002Fseo.md`\n\n## Flow\n\n### Step 1: Gather Context\n\nDetermine the input:\n\n- **Video package path** (`~\u002Fyoutube\u002F\u003Cslug>\u002F`): Read `titles.md`, `script.md`, `description.md`, `analysis.md`, and `performance.md` if they exist. The `performance.md` file tracks previously tried titles and thumbnails - never suggest a title that's already been tried.\n- **Topic\u002Ftitle string**: Use it directly as the starting point\n- **No argument**: Ask the user for their video topic or title\n\nExtract:\n- The core topic and primary keyword\n- Any existing titles to improve on\n- The video's key points and value proposition (from script if available)\n\nCheck if `--social` flag is present in $ARGUMENTS — if so, also generate social media titles in the output.\n\n### Step 2: Competitive Research (WebSearch)\n\nThis step is NOT optional — always do real research.\n\n**First, check for existing research from `\u002Fyt`:** If a video package exists at `~\u002Fyoutube\u002F\u003Cslug>\u002Fanalysis.md`, read it. The `\u002Fyt` skill already runs 4-6 web searches and saves competitor data, content gaps, and community sentiment. Extract what's already there:\n- Competitor video titles and view counts\n- Keywords and phrases already identified\n- Content gaps already noted\n\n**Then fill in SEO-specific gaps** — only run searches for data NOT already in `analysis.md`. Typically this means 2-3 targeted searches instead of 5-6:\n\n1. **YouTube autocomplete**: Search `\u003Ctopic> youtube autocomplete suggestions` and `\u003Ctopic> how to \u002F vs \u002F best \u002F tutorial` to find what people actually search for\n2. **Title patterns**: Search for variations of the topic to see how different creators title similar content (skip if analysis.md already has 10+ competitor titles)\n3. **Related keywords**: Search for synonyms, related terms, and long-tail variations\n4. **Trending angles**: Search for recent news\u002Fdevelopments about the topic that could inform timely title angles (skip if analysis.md has recent news)\n\n**If no analysis.md exists** (standalone SEO run without `\u002Fyt`), run the full 5-6 searches:\n\n1. **Top videos on this topic**: Search `\"\u003Ctopic>\" site:youtube.com` and `\u003Ctopic> youtube` to find the top-performing videos\n2. **Title patterns**: Search for variations of the topic to see how different creators title similar content\n3. **YouTube autocomplete**: Search `\u003Ctopic> youtube autocomplete suggestions` and `\u003Ctopic> how to \u002F vs \u002F best \u002F tutorial` to find what people actually search for\n4. **Related keywords**: Search for synonyms, related terms, and long-tail variations\n5. **Trending angles**: Search for recent news\u002Fdevelopments about the topic that could inform timely title angles\n6. **Competitor analysis**: Search for the top creators in this niche and analyze their title patterns\n\nFor each search, note:\n- Video titles that appeared\n- View counts where visible\n- Common keywords and phrases\n- Title formulas being used (How to X, X vs Y, I tried X, etc.)\n\nPresent a **research summary** to the user:\n- Top 10-15 competitor titles with view counts\n- Most common keywords (ranked by frequency)\n- Title formulas that appear to perform well\n- Content gaps — angles nobody is using\n\n### Step 3: Generate SEO-Optimized Content\n\n#### Title Options (5 titles)\n\nFor each title:\n- **The title** — Under 70 characters (YouTube truncates after that)\n- **Character count** — Show the exact count\n- **CTR formula used** — Name the technique (curiosity gap, specific number, how-to, comparison, bold claim, etc.)\n- **Primary keyword** — What search term this targets\n- **Why it works** — One sentence on the psychology\u002FSEO reasoning\n\nRules for titles:\n- Front-load the most important keyword in the first 40 characters\n- Never use clickbait the video can't deliver on\n- Include at least one title using a number\u002Fspecific claim\n- Include at least one curiosity-driven title\n- Include at least one direct\u002Fsearch-optimized title\n- Avoid overused words: \"INSANE\", \"CRAZY\", \"YOU WON'T BELIEVE\"\n\n#### Title Scorecard\n\nRate each title on a 1-5 scale:\n\n| Title | Curiosity | Specificity | SEO Strength | Click Factor | Total |\n|-------|-----------|-------------|--------------|--------------|-------|\n\n- **Curiosity (1-5)** — Does it create an information gap the viewer wants to close?\n- **Specificity (1-5)** — Does it promise something concrete vs vague?\n- **SEO Strength (1-5)** — Does it contain high-volume searchable keywords?\n- **Click Factor (1-5)** — Would YOU click this in a sea of other thumbnails?\n\nMark the recommended title with the highest total score.\n\n#### Optimized Description\n\n- **First 2 lines** — These show in search results. Front-load keywords and value proposition. No fluff.\n- **Body** — Natural keyword density (2-3% target keyword occurrence). Include related keywords organically.\n- **Chapters section** — `00:00 - Title` format (use placeholders if timestamps unknown, mark with [UPDATE])\n- **Links section** — Placeholder for relevant links\n- **Tags line** — Keywords at the bottom for additional SEO signal\n\nIf an existing `description.md` exists, add a `## SEO-Optimized Version` section rather than replacing the original.\n\n#### Tags (15-20)\n\nOrganize tags in three tiers:\n1. **Exact match** (3-5) — The exact phrases people search for\n2. **Broad match** (5-7) — Related topics and category terms\n3. **Long-tail** (5-8) — Specific, lower-competition phrases\n\n#### Social Media Titles (if `--social` flag)\n\nGenerate platform-native titles:\n- **LinkedIn headline** — Professional, insight-driven (under 150 chars). Focus on the lesson or takeaway, not the video.\n- **TikTok\u002FReels caption** — Short, punchy, hook-first (under 100 chars). Create urgency or curiosity.\n- **Twitter\u002FX post** — Under 280 chars, curiosity-driven. Make it a standalone insight that happens to link to a video.\n\nRules for social titles:\n- These should NOT just be the YouTube title copy-pasted\n- Each platform has different psychology — LinkedIn = professional growth, TikTok = entertainment\u002Fdiscovery, Twitter = hot takes\u002Finsights\n- The social title should make the content feel native to that platform\n\n### Step 4: Present Results\n\nShow the user:\n1. The research summary (competitor titles + view counts)\n2. All 5 title options with the scorecard\n3. The recommended title (highlighted)\n4. The optimized description (first 3 lines preview)\n5. The tag list\n6. Social media titles (if generated)\n\n### Step 5: Iterate\n\nAsk: **\"Want to go with one of these, or want me to generate more variants of a specific style?\"**\n\nOptions:\n- Pick a title and finalize\n- Generate 5 more in the style of a specific title\n- Mix elements from multiple titles\n- Adjust the description\n- Regenerate with different target keywords\n\n## Output\n\nIf a video package exists at `~\u002Fyoutube\u002F\u003Cslug>\u002F`:\n- **Update `titles.md`**: Add a `## SEO-Optimized Titles` section with the new titles, scorecard, and research data\n- **Update `description.md`**: Add a `## SEO-Optimized Version` section with the new description and tags\n\nIf standalone (no existing package):\n- **Create `~\u002Fyoutube\u002F\u003Cslug>\u002Fseo.md`**: Contains all titles, scorecard, description, tags, research data, and social titles\n\nAlways include the research data (competitor titles with view counts) in the output so the user can see WHY each title works.\n\n## Rules\n\n- ALWAYS do competitive research — never skip Step 2. The research is what makes this valuable.\n- Titles must be under 70 characters — no exceptions\n- Front-load the most important keyword in the first 40 characters\n- Never use clickbait that the video can't deliver on\n- Description first 2 lines are crucial — they show in search results\n- Tags should include exact match, broad match, and long-tail variants\n- Social titles should be platform-native, not just the YouTube title reformatted\n- Always show the research data so the user can see the reasoning\n- Include ALL competitor titles and view counts in the output — transparency builds trust\n- If updating existing files, add new sections rather than overwriting the original content\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25,"user-invocable":26},"Read, Write, Edit, Glob, Grep, WebSearch, WebFetch, AskUserQuestion","[topic or ~\u002Fyoutube\u002F\u003Cslug>\u002F]",true,"main","1324adb807d8bb4b91692ddd6cf1f0c353b6637b","yt-automation-kit\u002Fskills\u002Fseo","https:\u002F\u002Fgithub.com\u002Fjayozer\u002Fjay-marketplace","https:\u002F\u002Fgithub.com\u002Fjayozer","www.dataacrobat.com","🪩","2026-10-04 04:22:36",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add jayozer\u002Fjay-marketplace --skill seo",{"tool":41,"command":42},"bunx","bunx skills add jayozer\u002Fjay-marketplace --skill seo",{"tool":44,"command":45},"pnpm","pnpm dlx skills add jayozer\u002Fjay-marketplace --skill seo","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjayozer\u002Fjay-marketplace\u002Fblob\u002Fmain\u002Fyt-automation-kit\u002Fskills\u002Fseo\u002FSKILL.md",[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M75RGN7NXPZQCD17P96Q2J35","yt","Plan a YouTube video from a reference transcript and your own ideas. Analyzes source video structure, researches the topic online, asks for your angle, then generates titles, hooks, description, full script, and a filming guide. Triggers on: youtube video, video script, plan a video, video from transcript, yt plan.","https:\u002F\u002Fgithub.com\u002Fjayozer\u002Fjay-marketplace\u002Fblob\u002Fmain\u002Fyt-automation-kit\u002Fskills\u002Fyt\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M75RGJ122DRMW9MT6S3GXAJ5","yt-search","Search YouTube by keywords using yt-dlp. Finds recent videos, sorts by views, and generates a markdown report with full metadata. Triggers on: youtube search, search youtube, yt search, what's trending on youtube, youtube research.","https:\u002F\u002Fgithub.com\u002Fjayozer\u002Fjay-marketplace\u002Fblob\u002Fmain\u002Fyt-automation-kit\u002Fskills\u002Fyt-search\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M75RGDVYRGVDVPD88EBKS7BA","thumbnail","Generate YouTube thumbnails using Kie.ai image APIs (Nano Banana 2, Nano Banana Pro, or Seedream 4.5). Supports text-to-image and remix (image + text). Creates multiple variants with configurable settings. Triggers on: create thumbnail, generate thumbnail, thumbnail for, make a thumbnail, youtube thumbnail, remix thumbnail.","https:\u002F\u002Fgithub.com\u002Fjayozer\u002Fjay-marketplace\u002Fblob\u002Fmain\u002Fyt-automation-kit\u002Fskills\u002Fthumbnail\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M75RG42XKFZGN3AH41CVRBBM","repurpose","Repurpose a VIDEO transcript or script into short-form VIDEO scripts for YouTube Shorts, TikTok, and Reels — plus matching captions and a community post. Input must be a video transcript, script path, or YouTube URL. Use this for video-first content only. For text posts, LinkedIn posts, carousels, or static visuals, use \u002Fcontent instead. Triggers on: repurpose this video, repurpose transcript, create shorts from, make social posts from, repurpose content, turn this into shorts.","https:\u002F\u002Fgithub.com\u002Fjayozer\u002Fjay-marketplace\u002Fblob\u002Fmain\u002Fyt-automation-kit\u002Fskills\u002Frepurpose\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M75RG0QV4EFGJKJMD1NSFCG1","video-understanding","Analyze local video files with Gemini multimodal models, especially Gemini 3.1 Pro Preview, by uploading supported video formats and answering grounded questions with timestamps. Use when the user asks to analyze, understand, describe, summarize, inspect, or answer questions about videos such as .mp4, .mov, .webm, .avi, .wmv, .mpeg, .mpg, .flv, or .3gp files.","https:\u002F\u002Fgithub.com\u002Fjayozer\u002Fjay-marketplace\u002Fblob\u002Fmain\u002Fvideo-understanding-kit\u002Fskills\u002Fvideo-understanding\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M75RFX89S09DM28XSXWHC7J4","goal-orchestrator","Turn broad requests into an execution-ready brief and a measurable native goal for Codex, Claude Code, or Kimi Code. Use when the user asks to draft, refine, start, or run a goal whose outcome or verification still needs definition. Already precise tasks can use native \u002Fgoal or an ordinary prompt directly.","https:\u002F\u002Fgithub.com\u002Fjayozer\u002Fjay-marketplace\u002Fblob\u002Fmain\u002Fgoal-orchestrator\u002Fskills\u002Fgoal-orchestrator\u002FSKILL.md",[],[]]