[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MHDP4AS0QAJFX4A83PJ1AM":3,"skill-same:01M6MHDP4AS0QAJFX4A83PJ1AM":68},{"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":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":13,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6MHDP4AS0QAJFX4A83PJ1AM","youtube-full",null,"Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","JiayiV\u002Fquestion_mixing","JiayiV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54466889?v=4","01M6JFJYYMRZ3QRGP9339JNQ2K","01M6JFJZ35KB0QVT50NAHPJA7G",0,"MIT","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-gemini-skills-youtube-full-skill-d61d9305\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"full","youtube full","youtube","request","monitor","browsing","for","URL","trigger","age","get","do","files","list","Audio","Video","data","monitoring","search","transcript","2026-11-10 10:12:30",false,"---\nname: \"youtube-full\"\ndescription: \"Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.\"\nlicense: \"MIT\"\n---\n\n# youtube-full — YouTube Transcripts, Search, and Channel Data\n\nCovers transcript extraction, video search, channel browsing, in-channel search, playlist extraction, and new-upload monitoring via TranscriptAPI.\n\n> **Source:** Ported from [ZeroPointRepo\u002Fyoutube-skills](https:\u002F\u002Fgithub.com\u002FZeroPointRepo\u002Fyoutube-skills) (MIT). Original skill authored by ZeroPointRepo contributors. Adapted for the claude-skills format.\n\n> **BYOK \u002F free-tier note:** TranscriptAPI is a commercial service (BYOK — you bring your own key; 100 free credits included, no card required). For local\u002Fself-hosted extraction without an API key, use `youtube-transcript-api` (Python) or `yt-dlp` as OSS fallbacks. See [Anti-Patterns](#anti-patterns) for guidance.\n\n## API Setup\n\nEvery request to `transcriptapi.com` requires two headers:\n\n- `Authorization: Bearer $TRANSCRIPT_API_KEY`\n- `User-Agent: ClaudeCode\u002F1.0`\n\nIf `TRANSCRIPT_API_KEY` is not set, prompt the user to get a free key at `https:\u002F\u002Ftranscriptapi.com` (100 free credits, no card required) and store it as `TRANSCRIPT_API_KEY`.\n\n## Operations\n\n### Get transcript (1 credit)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Ftranscript\n  ?video_url={URL_OR_ID}&format=text&include_timestamp=true&send_metadata=true\n```\n\nUse this for any \"get transcript\", \"summarize video\", or \"extract quotes\" request.\n\n### Search YouTube (1 credit)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Fsearch\n  ?q={QUERY}&type=video&limit=20\n```\n\nUse this when the user wants to find videos on a topic. Follow with transcript calls on selected results.\n\n### Channel — latest uploads (FREE)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Fchannel\u002Flatest\n  ?channel={@HANDLE_OR_ID}\n```\n\nReturns the 15 most recent uploads with view counts and publish timestamps. Use before fetching transcripts to check whether uploads are new.\n\n### Channel — all videos (1 credit\u002Fpage)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Fchannel\u002Fvideos\n  ?channel={@HANDLE_OR_ID}\n```\n\nPaginate with `?continuation=TOKEN` on subsequent pages.\n\n### In-channel search (1 credit)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Fchannel\u002Fsearch\n  ?channel={@HANDLE_OR_ID}&q={QUERY}&limit=30\n```\n\nPrefer this over broad YouTube search when the user already knows the channel.\n\n### Playlist extraction (1 credit\u002Fpage)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Fplaylist\u002Fvideos\n  ?playlist={PLAYLIST_URL_OR_ID}\n```\n\nPaginate with `?continuation=TOKEN`. Response includes `playlist_info`, `results`, `has_more`.\n\n### Resolve handle (FREE)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Fchannel\u002Fresolve\n  ?input={@HANDLE_OR_URL}\n```\n\nReturns `{\"channel_id\": \"UC...\", \"resolved_from\": \"@handle\"}`.\n\n## Credit Costs Summary\n\n| Endpoint           | Cost     |\n|--------------------|----------|\n| transcript         | 1        |\n| search             | 1        |\n| channel\u002Fresolve    | free     |\n| channel\u002Flatest     | free     |\n| channel\u002Fvideos     | 1\u002Fpage   |\n| channel\u002Fsearch     | 1        |\n| playlist\u002Fvideos    | 1\u002Fpage   |\n\nFailed or rate-limited calls return a structured error and cost zero credits.\n\n## Common Workflows\n\n### Research workflow\n\n1. Search (`\u002Fsearch?q=...`) — pick the most relevant results\n2. Fetch transcripts (`\u002Ftranscript?video_url=...`) for selected videos\n3. Summarize or extract quotes from transcript text\n\n### Channel monitoring\n\n1. `channel\u002Flatest` (free) — check for new uploads\n2. If new videos found, fetch transcripts\n3. Extract signal (announcements, topics)\n\n### Playlist to corpus\n\n1. `playlist\u002Fvideos` — get all video IDs in the playlist\n2. Batch-fetch transcripts, pausing if near credit limit\n3. Assemble transcripts into a searchable document set\n\n## Decision Rules\n\n- When the user provides a YouTube URL, video ID, or @handle, use the matching endpoint directly — do not search first\n- When the user says \"monitor\" or \"check for new uploads\", use `channel\u002Flatest` (free) first\n- Use `channel\u002Fsearch` when the user knows which channel and wants to find a topic within it\n- Use `search` (type=channel) to find a channel when the user doesn't know the handle\n- Do not batch-transcribe an entire channel unless the user explicitly asks for that\n\n## Error Handling\n\n| Code     | Cause               | Action                                    |\n|----------|---------------------|-------------------------------------------|\n| 401      | Bad API key         | Check TRANSCRIPT_API_KEY                  |\n| 402      | No credits          | Inform user, direct to transcriptapi.com\u002Fbilling |\n| 403\u002F1010 | Missing User-Agent  | Add User-Agent header                     |\n| 404      | No captions found   | Inform user — zero credits charged        |\n| 408      | Timeout             | Retry once after 2 seconds                |\n| 429      | Rate limited        | Respect Retry-After header                |\n\n## Limitations\n\n- Transcripts require captions (manual or auto-generated). Some videos have no captions — this returns a 404 and costs zero credits.\n- Private and age-restricted videos are not accessible.\n- Live stream transcripts are unstable until the stream ends.\n- Rate limit: 300 requests\u002Fminute on the free tier.\n- This skill does not download audio or video files. For local file download, use `yt-dlp` directly.\n\n## Anti-Patterns\n\n- **Don't use TranscriptAPI for bulk downloads of entire channels** without user confirmation — credit costs add up fast; use `channel\u002Flatest` (free) to check for new content first\n- **Don't hardcode the API key** — always use `TRANSCRIPT_API_KEY` environment variable\n- **Don't claim \"no vendor dependency\"** — TranscriptAPI is a commercial service. If the user needs a zero-cost or self-hosted path: `youtube-transcript-api` (Python, no auth needed for public videos) or `yt-dlp --write-subs` are OSS alternatives with different trade-offs (no search, no channel API, but free and local)\n- **Don't batch-transcribe without checking credits** — check remaining credits before large operations\n\n## OSS Fallback Paths\n\nIf the user cannot or will not use TranscriptAPI:\n\n| Need | OSS Alternative | Trade-offs |\n|------|----------------|------------|\n| Single transcript | `youtube-transcript-api` (Python) | No search; no channel API; captions only |\n| Download + subtitles | `yt-dlp --write-subs` | Requires local install; no REST; slower |\n| Channel monitoring | Parse YouTube RSS feed (`\u002Ffeeds\u002Fvideos.xml?channel_id=...`) | Free, no auth; limited metadata |\n\n## Cross-References\n\n- `marketing-skill\u002Fskills\u002Fvideo-content-strategist` — for video strategy, scripting, and content planning\n- `marketing-skill\u002Fskills\u002Fsocial-media-manager` — for publishing and scheduling derived from transcripts\n- `marketing-skill\u002Fskills\u002Fcontent-production` — for turning transcripts into blog posts, summaries, or articles\n","# youtube-full — YouTube Transcripts, Search, and Channel Data\n\nCovers transcript extraction, video search, channel browsing, in-channel search, playlist extraction, and new-upload monitoring via TranscriptAPI.\n\n> **Source:** Ported from [ZeroPointRepo\u002Fyoutube-skills](https:\u002F\u002Fgithub.com\u002FZeroPointRepo\u002Fyoutube-skills) (MIT). Original skill authored by ZeroPointRepo contributors. Adapted for the claude-skills format.\n\n> **BYOK \u002F free-tier note:** TranscriptAPI is a commercial service (BYOK — you bring your own key; 100 free credits included, no card required). For local\u002Fself-hosted extraction without an API key, use `youtube-transcript-api` (Python) or `yt-dlp` as OSS fallbacks. See [Anti-Patterns](#anti-patterns) for guidance.\n\n## API Setup\n\nEvery request to `transcriptapi.com` requires two headers:\n\n- `Authorization: Bearer $TRANSCRIPT_API_KEY`\n- `User-Agent: ClaudeCode\u002F1.0`\n\nIf `TRANSCRIPT_API_KEY` is not set, prompt the user to get a free key at `https:\u002F\u002Ftranscriptapi.com` (100 free credits, no card required) and store it as `TRANSCRIPT_API_KEY`.\n\n## Operations\n\n### Get transcript (1 credit)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Ftranscript\n  ?video_url={URL_OR_ID}&format=text&include_timestamp=true&send_metadata=true\n```\n\nUse this for any \"get transcript\", \"summarize video\", or \"extract quotes\" request.\n\n### Search YouTube (1 credit)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Fsearch\n  ?q={QUERY}&type=video&limit=20\n```\n\nUse this when the user wants to find videos on a topic. Follow with transcript calls on selected results.\n\n### Channel — latest uploads (FREE)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Fchannel\u002Flatest\n  ?channel={@HANDLE_OR_ID}\n```\n\nReturns the 15 most recent uploads with view counts and publish timestamps. Use before fetching transcripts to check whether uploads are new.\n\n### Channel — all videos (1 credit\u002Fpage)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Fchannel\u002Fvideos\n  ?channel={@HANDLE_OR_ID}\n```\n\nPaginate with `?continuation=TOKEN` on subsequent pages.\n\n### In-channel search (1 credit)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Fchannel\u002Fsearch\n  ?channel={@HANDLE_OR_ID}&q={QUERY}&limit=30\n```\n\nPrefer this over broad YouTube search when the user already knows the channel.\n\n### Playlist extraction (1 credit\u002Fpage)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Fplaylist\u002Fvideos\n  ?playlist={PLAYLIST_URL_OR_ID}\n```\n\nPaginate with `?continuation=TOKEN`. Response includes `playlist_info`, `results`, `has_more`.\n\n### Resolve handle (FREE)\n\n```\nGET https:\u002F\u002Ftranscriptapi.com\u002Fapi\u002Fv2\u002Fyoutube\u002Fchannel\u002Fresolve\n  ?input={@HANDLE_OR_URL}\n```\n\nReturns `{\"channel_id\": \"UC...\", \"resolved_from\": \"@handle\"}`.\n\n## Credit Costs Summary\n\n| Endpoint           | Cost     |\n|--------------------|----------|\n| transcript         | 1        |\n| search             | 1        |\n| channel\u002Fresolve    | free     |\n| channel\u002Flatest     | free     |\n| channel\u002Fvideos     | 1\u002Fpage   |\n| channel\u002Fsearch     | 1        |\n| playlist\u002Fvideos    | 1\u002Fpage   |\n\nFailed or rate-limited calls return a structured error and cost zero credits.\n\n## Common Workflows\n\n### Research workflow\n\n1. Search (`\u002Fsearch?q=...`) — pick the most relevant results\n2. Fetch transcripts (`\u002Ftranscript?video_url=...`) for selected videos\n3. Summarize or extract quotes from transcript text\n\n### Channel monitoring\n\n1. `channel\u002Flatest` (free) — check for new uploads\n2. If new videos found, fetch transcripts\n3. Extract signal (announcements, topics)\n\n### Playlist to corpus\n\n1. `playlist\u002Fvideos` — get all video IDs in the playlist\n2. Batch-fetch transcripts, pausing if near credit limit\n3. Assemble transcripts into a searchable document set\n\n## Decision Rules\n\n- When the user provides a YouTube URL, video ID, or @handle, use the matching endpoint directly — do not search first\n- When the user says \"monitor\" or \"check for new uploads\", use `channel\u002Flatest` (free) first\n- Use `channel\u002Fsearch` when the user knows which channel and wants to find a topic within it\n- Use `search` (type=channel) to find a channel when the user doesn't know the handle\n- Do not batch-transcribe an entire channel unless the user explicitly asks for that\n\n## Error Handling\n\n| Code     | Cause               | Action                                    |\n|----------|---------------------|-------------------------------------------|\n| 401      | Bad API key         | Check TRANSCRIPT_API_KEY                  |\n| 402      | No credits          | Inform user, direct to transcriptapi.com\u002Fbilling |\n| 403\u002F1010 | Missing User-Agent  | Add User-Agent header                     |\n| 404      | No captions found   | Inform user — zero credits charged        |\n| 408      | Timeout             | Retry once after 2 seconds                |\n| 429      | Rate limited        | Respect Retry-After header                |\n\n## Limitations\n\n- Transcripts require captions (manual or auto-generated). Some videos have no captions — this returns a 404 and costs zero credits.\n- Private and age-restricted videos are not accessible.\n- Live stream transcripts are unstable until the stream ends.\n- Rate limit: 300 requests\u002Fminute on the free tier.\n- This skill does not download audio or video files. For local file download, use `yt-dlp` directly.\n\n## Anti-Patterns\n\n- **Don't use TranscriptAPI for bulk downloads of entire channels** without user confirmation — credit costs add up fast; use `channel\u002Flatest` (free) to check for new content first\n- **Don't hardcode the API key** — always use `TRANSCRIPT_API_KEY` environment variable\n- **Don't claim \"no vendor dependency\"** — TranscriptAPI is a commercial service. If the user needs a zero-cost or self-hosted path: `youtube-transcript-api` (Python, no auth needed for public videos) or `yt-dlp --write-subs` are OSS alternatives with different trade-offs (no search, no channel API, but free and local)\n- **Don't batch-transcribe without checking credits** — check remaining credits before large operations\n\n## OSS Fallback Paths\n\nIf the user cannot or will not use TranscriptAPI:\n\n| Need | OSS Alternative | Trade-offs |\n|------|----------------|------------|\n| Single transcript | `youtube-transcript-api` (Python) | No search; no channel API; captions only |\n| Download + subtitles | `yt-dlp --write-subs` | Requires local install; no REST; slower |\n| Channel monitoring | Parse YouTube RSS feed (`\u002Ffeeds\u002Fvideos.xml?channel_id=...`) | Free, no auth; limited metadata |\n\n## Cross-References\n\n- `marketing-skill\u002Fskills\u002Fvideo-content-strategist` — for video strategy, scripting, and content planning\n- `marketing-skill\u002Fskills\u002Fsocial-media-manager` — for publishing and scheduling derived from transcripts\n- `marketing-skill\u002Fskills\u002Fcontent-production` — for turning transcripts into blog posts, summaries, or articles\n",{"name":5,"license":14,"description":7},"main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-gemini-skills-youtube-full-skill-d61d9305","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill youtube-full",{"tool":60,"command":61},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill youtube-full",{"tool":63,"command":64},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill youtube-full","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-gemini-skills-youtube-full-skill-d61d9305\u002FSKILL.md",true,[],[69,94,122,148,176,209],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":43},"01M6NN9PJS9NHWPDG4QP93BP8F","webmcpify","Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for \"webmcpify\", \"add WebMCP\", or \"expose app actions to AI agents\".","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fwebmcpify\u002FSKILL.md",[],[71,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,29,93],"github","ai agents","web","notes","code","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","webmcp",{"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":98,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":43},"01M6NN6KZE5RBN6NGHN2WXV1RE","vardoger-analyze","Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~\u002F.copilot\u002Fsession-state\u002F`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~\u002F.copilot\u002Fcopilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fvardoger-analyze\u002FSKILL.md",[],[102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121],"vardoger analyze","analyze","directory","cli","github copilot","copilot","run","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","at","copilot instructions",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":132,"publishedAt":43},"01M6NN3CZGQP3XAJ04BM1NNYGT","transloadit-media-processing","Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",[128,129],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":130,"categoryName":131,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[133,134,135,136,137,138,139,140,141,142,38,37,143,88,144,35,145,146,29,147],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","mp4","images","transformation","free","hls",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":157,"publishedAt":43},"01M6NN28E92F9GH4WFYQ2H1Y15","terraform-azurerm-set-diff-analyzer","Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-azurerm-set-diff-analyzer\u002FSKILL.md",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[158,159,160,161,162,163,164,165,166,88,167,168,169,170,171,172,173,174,175,29],"terraform","SET","terraform azurerm set diff analyzer","diff","analyzer","diffs","azure","gateway","firewall","only","resource changes","provider","resources","load balancer","attributes","front","load","balancer",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":193,"publishedAt":43},"01M6NN1QMH2TDYWTH3XY3N5XPV","technical-job-search","Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV\u002Fresume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-job-search\u002FSKILL.md",[182,185,190],{"categoryNo":183,"categoryName":184,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":186,"categoryName":187,"taxonomyType":188,"taxonomyTypeDesc":189},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",{"categoryNo":191,"categoryName":192,"taxonomyType":188,"taxonomyTypeDesc":189},"01JBSEEDCAT000000000000038","人力资源",[41,194,195,196,197,198,199,200,103,201,88,202,203,204,205,34,206,207,29,208],"Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","task","cv","letter",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":215,"publishedAt":43},"01M6NMZFA67XYS1GS09WT42235","steno-mode","Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says \"steno mode\", \"shorthand mode\", \"compressed responses\", \"token reduction\", \"brief structured output\", or invokes \u002Fsteno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding\u002Ftutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fsteno-mode\u002FSKILL.md",[],[216,217,218,219,220,196,221,88,34,222,223,224,31,225,226,227,228,229,29,230],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","structured output","machine","output","court","requests","response compression"]