[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A89TXZH06EPC2WWN0QBY8F":3,"skill-same:01M7A89TXZH06EPC2WWN0QBY8F":55},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M7A89TXZH06EPC2WWN0QBY8F","podcast-generation",null,"Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.","Zephyrsz\u002Fdeer-flow","Zephyrsz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F22188415?v=4","01M7A86RT97A5TPK28B3RDTBA0","01M7A86RTZCC4WVXV52676PSHP",0,"MIT","https:\u002F\u002Fgithub.com\u002FZephyrsz\u002Fdeer-flow\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fpodcast-generation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: podcast-generation\ndescription: Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.\n---\n\n# Podcast Generation Skill\n\n## Overview\n\nThis skill generates high-quality podcast audio from text content. The workflow includes creating a structured JSON script (conversational dialogue) and executing audio generation through text-to-speech synthesis.\n\n## Core Capabilities\n\n- Convert any text content (articles, reports, documentation) into podcast scripts\n- Generate natural two-host conversational dialogue (male and female hosts)\n- Synthesize speech audio using text-to-speech\n- Mix audio chunks into a final podcast MP3 file\n- Support both English and Chinese content\n\n## Workflow\n\n### Step 1: Understand Requirements\n\nWhen a user requests podcast generation, identify:\n\n- Source content: The text\u002Farticle\u002Freport to convert into a podcast\n- Language: English or Chinese (based on content)\n- Output location: Where to save the generated podcast\n- You don't need to check the folder under `\u002Fmnt\u002Fuser-data`\n\n### Step 2: Create Structured Script JSON\n\nGenerate a structured JSON script file in `\u002Fmnt\u002Fuser-data\u002Fworkspace\u002F` with naming pattern: `{descriptive-name}-script.json`\n\nThe JSON structure:\n```json\n{\n  \"locale\": \"en\",\n  \"lines\": [\n    {\"speaker\": \"male\", \"paragraph\": \"dialogue text\"},\n    {\"speaker\": \"female\", \"paragraph\": \"dialogue text\"}\n  ]\n}\n```\n\n### Step 3: Execute Generation\n\nCall the Python script:\n```bash\npython \u002Fmnt\u002Fskills\u002Fpublic\u002Fpodcast-generation\u002Fscripts\u002Fgenerate.py \\\n  --script-file \u002Fmnt\u002Fuser-data\u002Fworkspace\u002Fscript-file.json \\\n  --output-file \u002Fmnt\u002Fuser-data\u002Foutputs\u002Fgenerated-podcast.mp3 \\\n  --transcript-file \u002Fmnt\u002Fuser-data\u002Foutputs\u002Fgenerated-podcast-transcript.md\n```\n\nParameters:\n\n- `--script-file`: Absolute path to JSON script file (required)\n- `--output-file`: Absolute path to output MP3 file (required)\n- `--transcript-file`: Absolute path to output transcript markdown file (optional, but recommended)\n\n> [!IMPORTANT]\n> - Execute the script in one complete call. Do NOT split the workflow into separate steps.\n> - The script handles all TTS API calls and audio generation internally.\n> - Do NOT read the Python file, just call it with the parameters.\n> - Always include `--transcript-file` to generate a readable transcript for the user.\n> - The TTS provider and its concurrency are selected automatically from environment variables — you do not choose or tune them.\n\n## Script JSON Format\n\nThe script JSON file must follow this structure:\n\n```json\n{\n  \"title\": \"The History of Artificial Intelligence\",\n  \"locale\": \"en\",\n  \"lines\": [\n    {\"speaker\": \"male\", \"paragraph\": \"Hello Deer! Welcome back to another episode.\"},\n    {\"speaker\": \"female\", \"paragraph\": \"Hey everyone! Today we have an exciting topic to discuss.\"},\n    {\"speaker\": \"male\", \"paragraph\": \"That's right! We're going to talk about...\"}\n  ]\n}\n```\n\nFields:\n- `title`: Title of the podcast episode (optional, used as heading in transcript)\n- `locale`: Language code - \"en\" for English or \"zh\" for Chinese\n- `lines`: Array of dialogue lines\n  - `speaker`: Either \"male\" or \"female\"\n  - `paragraph`: The dialogue text for this speaker\n\n## Script Writing Guidelines\n\nWhen creating the script JSON, follow these guidelines:\n\n### Format Requirements\n- Only two hosts: male and female, alternating naturally\n- Target runtime: approximately 10 minutes of dialogue (around 40-60 lines)\n- Start with the male host saying a greeting that includes \"Hello Deer\"\n\n### Tone & Style\n- Natural, conversational dialogue - like two friends chatting\n- Use casual expressions and conversational transitions\n- Avoid overly formal language or academic tone\n- Include reactions, follow-up questions, and natural interjections\n\n### Content Guidelines\n- Frequent back-and-forth between hosts\n- Keep sentences short and easy to follow when spoken\n- Plain text only - no markdown formatting in the output\n- Translate technical concepts into accessible language\n- No mathematical formulas, code, or complex notation\n- Make content engaging and accessible for audio-only listeners\n- Exclude meta information like dates, author names, or document structure\n\n## Podcast Generation Example\n\nUser request: \"Generate a podcast about the history of artificial intelligence\"\n\nStep 1: Create script file `\u002Fmnt\u002Fuser-data\u002Fworkspace\u002Fai-history-script.json`:\n```json\n{\n  \"title\": \"The History of Artificial Intelligence\",\n  \"locale\": \"en\",\n  \"lines\": [\n    {\"speaker\": \"male\", \"paragraph\": \"Hello Deer! Welcome back to another fascinating episode. Today we're diving into something that's literally shaping our future - the history of artificial intelligence.\"},\n    {\"speaker\": \"female\", \"paragraph\": \"Oh, I love this topic! You know, AI feels so modern, but it actually has roots going back over seventy years.\"},\n    {\"speaker\": \"male\", \"paragraph\": \"Exactly! It all started back in the 1950s. The term artificial intelligence was actually coined by John McCarthy in 1956 at a famous conference at Dartmouth.\"},\n    {\"speaker\": \"female\", \"paragraph\": \"Wait, so they were already thinking about machines that could think back then? That's incredible!\"},\n    {\"speaker\": \"male\", \"paragraph\": \"Right? The early pioneers were so optimistic. They thought we'd have human-level AI within a generation.\"},\n    {\"speaker\": \"female\", \"paragraph\": \"But things didn't quite work out that way, did they?\"},\n    {\"speaker\": \"male\", \"paragraph\": \"No, not at all. The 1970s brought what's called the first AI winter...\"}\n  ]\n}\n```\n\nStep 2: Execute generation:\n```bash\npython \u002Fmnt\u002Fskills\u002Fpublic\u002Fpodcast-generation\u002Fscripts\u002Fgenerate.py \\\n  --script-file \u002Fmnt\u002Fuser-data\u002Fworkspace\u002Fai-history-script.json \\\n  --output-file \u002Fmnt\u002Fuser-data\u002Foutputs\u002Fai-history-podcast.mp3 \\\n  --transcript-file \u002Fmnt\u002Fuser-data\u002Foutputs\u002Fai-history-transcript.md\n```\n\nThis will generate:\n- `ai-history-podcast.mp3`: The audio podcast file\n- `ai-history-transcript.md`: A readable markdown transcript of the podcast\n\n## Specific Templates\n\nRead the following template file only when matching the user request.\n\n- [Tech Explainer](templates\u002Ftech-explainer.md) - For converting technical documentation and tutorials\n\n## Output Format\n\nThe generated podcast follows the \"Hello Deer\" format:\n- Two hosts: one male, one female\n- Natural conversational dialogue\n- Starts with \"Hello Deer\" greeting\n- Target duration: approximately 10 minutes\n- Alternating speakers for engaging flow\n\n## Output Handling\n\nAfter generation:\n\n- Podcasts and transcripts are saved in `\u002Fmnt\u002Fuser-data\u002Foutputs\u002F`\n- Share both the podcast MP3 and transcript MD with user using `present_files` tool\n- Provide brief description of the generation result (topic, duration, hosts)\n- Offer to regenerate if adjustments needed\n\n## Requirements\n\nThe following environment variables must be set:\n- For Volcengine: `VOLCENGINE_TTS_APPID` and `VOLCENGINE_TTS_ACCESS_TOKEN`\n- For MiniMax: `MINIMAX_API_KEY`\n- `VOLCENGINE_TTS_CLUSTER`: Volcengine TTS cluster (optional, defaults to \"volcano_tts\")\n\n## Notes\n\n- **Always execute the full pipeline in one call** - no need to test individual steps or worry about timeouts\n- The script JSON should match the content language (en or zh)\n- Technical content should be simplified for audio accessibility in the script\n- Complex notations (formulas, code) should be translated to plain language in the script\n- Long content may result in longer podcasts\n\n## Providers (Volcengine \u002F MiniMax)\n\nAuto-selected by environment variables:\n\n- `VOLCENGINE_TTS_APPID` + `VOLCENGINE_TTS_ACCESS_TOKEN` set → Volcengine TTS (default).\n- Only `MINIMAX_API_KEY` set → MiniMax TTS (`\u002Fv1\u002Ft2a_v2`).\n- Force with `PODCAST_GENERATION_PROVIDER=volcengine|minimax`.\n\nMiniMax overrides: `MINIMAX_API_HOST` (default `https:\u002F\u002Fapi.minimaxi.com`),\n`MINIMAX_TTS_MODEL` (default `speech-2.6-hd`), `MINIMAX_TTS_VOICE_MALE`\n(default `male-qn-qingse`), `MINIMAX_TTS_VOICE_FEMALE` (default `female-tianmei`).\n\nConcurrency is owned by each provider internally — MiniMax runs single-threaded\nto reduce rate-limit failures, Volcengine uses 4 workers. There is no\ncaller-facing concurrency knob; transient rate limits are handled by automatic\nretry with backoff.\n","# Podcast Generation Skill\n\n## Overview\n\nThis skill generates high-quality podcast audio from text content. The workflow includes creating a structured JSON script (conversational dialogue) and executing audio generation through text-to-speech synthesis.\n\n## Core Capabilities\n\n- Convert any text content (articles, reports, documentation) into podcast scripts\n- Generate natural two-host conversational dialogue (male and female hosts)\n- Synthesize speech audio using text-to-speech\n- Mix audio chunks into a final podcast MP3 file\n- Support both English and Chinese content\n\n## Workflow\n\n### Step 1: Understand Requirements\n\nWhen a user requests podcast generation, identify:\n\n- Source content: The text\u002Farticle\u002Freport to convert into a podcast\n- Language: English or Chinese (based on content)\n- Output location: Where to save the generated podcast\n- You don't need to check the folder under `\u002Fmnt\u002Fuser-data`\n\n### Step 2: Create Structured Script JSON\n\nGenerate a structured JSON script file in `\u002Fmnt\u002Fuser-data\u002Fworkspace\u002F` with naming pattern: `{descriptive-name}-script.json`\n\nThe JSON structure:\n```json\n{\n  \"locale\": \"en\",\n  \"lines\": [\n    {\"speaker\": \"male\", \"paragraph\": \"dialogue text\"},\n    {\"speaker\": \"female\", \"paragraph\": \"dialogue text\"}\n  ]\n}\n```\n\n### Step 3: Execute Generation\n\nCall the Python script:\n```bash\npython \u002Fmnt\u002Fskills\u002Fpublic\u002Fpodcast-generation\u002Fscripts\u002Fgenerate.py \\\n  --script-file \u002Fmnt\u002Fuser-data\u002Fworkspace\u002Fscript-file.json \\\n  --output-file \u002Fmnt\u002Fuser-data\u002Foutputs\u002Fgenerated-podcast.mp3 \\\n  --transcript-file \u002Fmnt\u002Fuser-data\u002Foutputs\u002Fgenerated-podcast-transcript.md\n```\n\nParameters:\n\n- `--script-file`: Absolute path to JSON script file (required)\n- `--output-file`: Absolute path to output MP3 file (required)\n- `--transcript-file`: Absolute path to output transcript markdown file (optional, but recommended)\n\n> [!IMPORTANT]\n> - Execute the script in one complete call. Do NOT split the workflow into separate steps.\n> - The script handles all TTS API calls and audio generation internally.\n> - Do NOT read the Python file, just call it with the parameters.\n> - Always include `--transcript-file` to generate a readable transcript for the user.\n> - The TTS provider and its concurrency are selected automatically from environment variables — you do not choose or tune them.\n\n## Script JSON Format\n\nThe script JSON file must follow this structure:\n\n```json\n{\n  \"title\": \"The History of Artificial Intelligence\",\n  \"locale\": \"en\",\n  \"lines\": [\n    {\"speaker\": \"male\", \"paragraph\": \"Hello Deer! Welcome back to another episode.\"},\n    {\"speaker\": \"female\", \"paragraph\": \"Hey everyone! Today we have an exciting topic to discuss.\"},\n    {\"speaker\": \"male\", \"paragraph\": \"That's right! We're going to talk about...\"}\n  ]\n}\n```\n\nFields:\n- `title`: Title of the podcast episode (optional, used as heading in transcript)\n- `locale`: Language code - \"en\" for English or \"zh\" for Chinese\n- `lines`: Array of dialogue lines\n  - `speaker`: Either \"male\" or \"female\"\n  - `paragraph`: The dialogue text for this speaker\n\n## Script Writing Guidelines\n\nWhen creating the script JSON, follow these guidelines:\n\n### Format Requirements\n- Only two hosts: male and female, alternating naturally\n- Target runtime: approximately 10 minutes of dialogue (around 40-60 lines)\n- Start with the male host saying a greeting that includes \"Hello Deer\"\n\n### Tone & Style\n- Natural, conversational dialogue - like two friends chatting\n- Use casual expressions and conversational transitions\n- Avoid overly formal language or academic tone\n- Include reactions, follow-up questions, and natural interjections\n\n### Content Guidelines\n- Frequent back-and-forth between hosts\n- Keep sentences short and easy to follow when spoken\n- Plain text only - no markdown formatting in the output\n- Translate technical concepts into accessible language\n- No mathematical formulas, code, or complex notation\n- Make content engaging and accessible for audio-only listeners\n- Exclude meta information like dates, author names, or document structure\n\n## Podcast Generation Example\n\nUser request: \"Generate a podcast about the history of artificial intelligence\"\n\nStep 1: Create script file `\u002Fmnt\u002Fuser-data\u002Fworkspace\u002Fai-history-script.json`:\n```json\n{\n  \"title\": \"The History of Artificial Intelligence\",\n  \"locale\": \"en\",\n  \"lines\": [\n    {\"speaker\": \"male\", \"paragraph\": \"Hello Deer! Welcome back to another fascinating episode. Today we're diving into something that's literally shaping our future - the history of artificial intelligence.\"},\n    {\"speaker\": \"female\", \"paragraph\": \"Oh, I love this topic! You know, AI feels so modern, but it actually has roots going back over seventy years.\"},\n    {\"speaker\": \"male\", \"paragraph\": \"Exactly! It all started back in the 1950s. The term artificial intelligence was actually coined by John McCarthy in 1956 at a famous conference at Dartmouth.\"},\n    {\"speaker\": \"female\", \"paragraph\": \"Wait, so they were already thinking about machines that could think back then? That's incredible!\"},\n    {\"speaker\": \"male\", \"paragraph\": \"Right? The early pioneers were so optimistic. They thought we'd have human-level AI within a generation.\"},\n    {\"speaker\": \"female\", \"paragraph\": \"But things didn't quite work out that way, did they?\"},\n    {\"speaker\": \"male\", \"paragraph\": \"No, not at all. The 1970s brought what's called the first AI winter...\"}\n  ]\n}\n```\n\nStep 2: Execute generation:\n```bash\npython \u002Fmnt\u002Fskills\u002Fpublic\u002Fpodcast-generation\u002Fscripts\u002Fgenerate.py \\\n  --script-file \u002Fmnt\u002Fuser-data\u002Fworkspace\u002Fai-history-script.json \\\n  --output-file \u002Fmnt\u002Fuser-data\u002Foutputs\u002Fai-history-podcast.mp3 \\\n  --transcript-file \u002Fmnt\u002Fuser-data\u002Foutputs\u002Fai-history-transcript.md\n```\n\nThis will generate:\n- `ai-history-podcast.mp3`: The audio podcast file\n- `ai-history-transcript.md`: A readable markdown transcript of the podcast\n\n## Specific Templates\n\nRead the following template file only when matching the user request.\n\n- [Tech Explainer](templates\u002Ftech-explainer.md) - For converting technical documentation and tutorials\n\n## Output Format\n\nThe generated podcast follows the \"Hello Deer\" format:\n- Two hosts: one male, one female\n- Natural conversational dialogue\n- Starts with \"Hello Deer\" greeting\n- Target duration: approximately 10 minutes\n- Alternating speakers for engaging flow\n\n## Output Handling\n\nAfter generation:\n\n- Podcasts and transcripts are saved in `\u002Fmnt\u002Fuser-data\u002Foutputs\u002F`\n- Share both the podcast MP3 and transcript MD with user using `present_files` tool\n- Provide brief description of the generation result (topic, duration, hosts)\n- Offer to regenerate if adjustments needed\n\n## Requirements\n\nThe following environment variables must be set:\n- For Volcengine: `VOLCENGINE_TTS_APPID` and `VOLCENGINE_TTS_ACCESS_TOKEN`\n- For MiniMax: `MINIMAX_API_KEY`\n- `VOLCENGINE_TTS_CLUSTER`: Volcengine TTS cluster (optional, defaults to \"volcano_tts\")\n\n## Notes\n\n- **Always execute the full pipeline in one call** - no need to test individual steps or worry about timeouts\n- The script JSON should match the content language (en or zh)\n- Technical content should be simplified for audio accessibility in the script\n- Complex notations (formulas, code) should be translated to plain language in the script\n- Long content may result in longer podcasts\n\n## Providers (Volcengine \u002F MiniMax)\n\nAuto-selected by environment variables:\n\n- `VOLCENGINE_TTS_APPID` + `VOLCENGINE_TTS_ACCESS_TOKEN` set → Volcengine TTS (default).\n- Only `MINIMAX_API_KEY` set → MiniMax TTS (`\u002Fv1\u002Ft2a_v2`).\n- Force with `PODCAST_GENERATION_PROVIDER=volcengine|minimax`.\n\nMiniMax overrides: `MINIMAX_API_HOST` (default `https:\u002F\u002Fapi.minimaxi.com`),\n`MINIMAX_TTS_MODEL` (default `speech-2.6-hd`), `MINIMAX_TTS_VOICE_MALE`\n(default `male-qn-qingse`), `MINIMAX_TTS_VOICE_FEMALE` (default `female-tianmei`).\n\nConcurrency is owned by each provider internally — MiniMax runs single-threaded\nto reduce rate-limit failures, Volcengine uses 4 workers. There is no\ncaller-facing concurrency knob; transient rate limits are handled by automatic\nretry with backoff.\n",{"name":5,"description":7},"main","43f7bd69f890fb21cbec1ffb4828338083a49bbd","skills\u002Fpublic\u002Fpodcast-generation","https:\u002F\u002Fgithub.com\u002FZephyrsz\u002Fdeer-flow","https:\u002F\u002Fgithub.com\u002FZephyrsz","2026-08-06 20:49:50",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add Zephyrsz\u002Fdeer-flow --skill podcast-generation",{"tool":35,"command":36},"bunx","bunx skills add Zephyrsz\u002Fdeer-flow --skill podcast-generation",{"tool":38,"command":39},"pnpm","pnpm dlx skills add Zephyrsz\u002Fdeer-flow --skill podcast-generation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FZephyrsz\u002Fdeer-flow\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fpodcast-generation\u002FSKILL.md",true,[43,49],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"scripts\u002Fgenerate.py","SCRIPT","脚本",14597,"https:\u002F\u002Fgithub.com\u002FZephyrsz\u002Fdeer-flow\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fpodcast-generation\u002Fscripts\u002Fgenerate.py",{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"templates\u002Ftech-explainer.md","REFERENCE","参考文档",1979,"https:\u002F\u002Fgithub.com\u002FZephyrsz\u002Fdeer-flow\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fpodcast-generation\u002Ftemplates\u002Ftech-explainer.md",[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M7A8BAFHVH14H14N967NA8AB","twitter-fetch","Use when a user asks to collect, filter, summarize, score, or archive posts from an authenticated X\u002FTwitter home timeline.","https:\u002F\u002Fgithub.com\u002FZephyrsz\u002Fdeer-flow\u002Fblob\u002Fmain\u002Fuser_test\u002Ftwitter_fetch\u002Fskill\u002Ftwitter-fetch\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M7A8B6JV6ZSTJKZASQCG27QF","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002FZephyrsz\u002Fdeer-flow\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M7A8B3FH8T96QKHDBE1ZK0QW","video-generation","Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.","https:\u002F\u002Fgithub.com\u002FZephyrsz\u002Fdeer-flow\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fvideo-generation\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M7A8B067HY9TASVY4CTPSPK4","vercel-deploy","Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as \"Deploy my app\", \"Deploy this to production\", \"Create a preview deployment\", \"Deploy and give me the link\", or \"Push this live\". No authentication required - returns preview URL and claimable deployment link.","https:\u002F\u002Fgithub.com\u002FZephyrsz\u002Fdeer-flow\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fvercel-deploy-claimable\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M7A8AWGDAK1A005C5V9MZ84T","systematic-literature-review","Use this skill when the user wants a systematic literature review, survey, or synthesis across multiple academic papers on a topic. Also covers annotated bibliographies and cross-paper comparisons. Searches arXiv and outputs reports in APA, IEEE, or BibTeX format. Not for single-paper tasks — use academic-paper-review for reviewing one paper.","https:\u002F\u002Fgithub.com\u002FZephyrsz\u002Fdeer-flow\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fsystematic-literature-review\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":18},"01M7A8AR484E6ACG8BDZR1MKSR","surprise-me","Create a delightful, unexpected \"wow\" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says \"surprise me\" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for \"something interesting\".","https:\u002F\u002Fgithub.com\u002FZephyrsz\u002Fdeer-flow\u002Fblob\u002Fmain\u002Fskills\u002Fpublic\u002Fsurprise-me\u002FSKILL.md",[],[]]