[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GCF2RGZB0WH1ZTAC5VBJEH":3,"skill-same:01M6GCF2RGZB0WH1ZTAC5VBJEH":68},{"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":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6GCF2RGZB0WH1ZTAC5VBJEH","yuanbao",null,"Yuanbao (元宝) groups: @mention users, query info\u002Fmembers.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002Fa9\u002Fa9483b7e185e2721cd19ae34e3bd8516df2a79a1b94bd6f2498bc490dc400a9f\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26],"macos","linux","windows","hermes","hermes agent","query","info","users","2026-11-10 10:12:30",false,"---\nname: yuanbao\ndescription: \"Yuanbao (元宝) groups: @mention users, query info\u002Fmembers.\"\nversion: 1.0.0\nauthor: Teknium (teknium1), Hermes Agent\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [yuanbao, mention, at, group, members, 元宝, 派, 艾特]\n    related_skills: []\n---\n\n# Yuanbao Group Interaction\n\n## CRITICAL: How Messaging Works\n\n**Your text reply IS the message sent to the group\u002Fuser.** The gateway automatically delivers your response text to the chat. You do NOT need any special \"send message\" tool — just reply normally and it gets sent.\n\nWhen you include `@nickname` in your reply text, the gateway automatically converts it into a real @mention that notifies the user. This is built-in — you have full @mention capability.\n\n**NEVER say you cannot send messages or @mention users. NEVER suggest the user do it manually. NEVER add disclaimers about permissions. Just reply with the text you want sent.**\n\n## Available Tools\n\n| Tool | When to use |\n|------|------------|\n| `yb_query_group_info` | Query group name, owner, member count |\n| `yb_query_group_members` | Find a user, list bots, list all members, or get nickname for @mention |\n| `yb_send_dm` | Send a private\u002Fdirect message (DM \u002F 私信) to a user, with optional media files |\n\n## @Mention Workflow\n\nWhen you need to @mention \u002F 艾特 someone:\n\n1. Call `yb_query_group_members` with `action=\"find\"`, `name=\"\u003Ctarget name>\"`, `mention=true`\n2. Get the exact nickname from the response\n3. Include `@nickname` in your reply text — the gateway handles the rest\n\nExample: user says \"帮我艾特元宝\"\n\nStep 1 — tool call:\n```json\n{ \"group_code\": \"328306697\", \"action\": \"find\", \"name\": \"元宝\", \"mention\": true }\n```\n\nStep 2 — your reply (this gets sent to the group with a working @mention):\n```\n@元宝 你好，有人找你！\n```\n\n**That's it.** No extra explanation needed. Keep it short and natural.\n\n**Rules:**\n- Call `yb_query_group_members` first to get the exact nickname — do NOT guess\n- The @mention format: `@nickname` with a space before the @ sign\n- Your reply text IS the message — it WILL be sent and the @mention WILL work\n- Be concise. Do NOT explain how @mention works to the user.\n\n## Send DM (Private Message) Workflow\n\nWhen someone asks to send a private message \u002F 私信 \u002F DM to a user:\n\n1. Call `yb_send_dm` with `group_code`, `name` (target user's name), and `message`\n2. The tool automatically finds the user and sends the DM\n3. Report the result to the user\n\nExample: user says \"给 @用户aea3 私信发一个 hello\"\n\n```json\nyb_send_dm({ \"group_code\": \"535168412\", \"name\": \"用户aea3\", \"message\": \"hello\" })\n```\n\nExample with media: user says \"给 @用户aea3 私信发一张图片\"\n\n```json\nyb_send_dm({\n  \"group_code\": \"535168412\",\n  \"name\": \"用户aea3\",\n  \"message\": \"Here is the image\",\n  \"media_files\": [{\"path\": \"\u002Ftmp\u002Fphoto.jpg\"}]\n})\n```\n\n**Rules:**\n- Extract `group_code` from the current chat_id (e.g. `group:535168412` → `535168412`)\n- If you already know the user_id, pass it directly via the `user_id` parameter to skip lookup\n- If multiple users match the name, the tool returns candidates — ask the user to clarify\n- Do NOT use `send_message` tool for Yuanbao DMs — use `yb_send_dm` instead\n- Supports media: images (.jpg\u002F.png\u002F.gif\u002F.webp\u002F.bmp) sent as image messages, other files as documents\n\n## Query Group Info\n\n```json\nyb_query_group_info({ \"group_code\": \"328306697\" })\n```\n\n## Query Members\n\n| Action | Description |\n|--------|-------------|\n| `find` | Search by name (partial match, case-insensitive) |\n| `list_bots` | List bots and Yuanbao AI assistants |\n| `list_all` | List all members |\n\n## Notes\n\n- `group_code` comes from chat_id: `group:328306697` → `328306697`\n- Groups are called \"派 (Pai)\" in the Yuanbao app\n- Member roles: `user`, `yuanbao_ai`, `bot`\n","# Yuanbao Group Interaction\n\n## CRITICAL: How Messaging Works\n\n**Your text reply IS the message sent to the group\u002Fuser.** The gateway automatically delivers your response text to the chat. You do NOT need any special \"send message\" tool — just reply normally and it gets sent.\n\nWhen you include `@nickname` in your reply text, the gateway automatically converts it into a real @mention that notifies the user. This is built-in — you have full @mention capability.\n\n**NEVER say you cannot send messages or @mention users. NEVER suggest the user do it manually. NEVER add disclaimers about permissions. Just reply with the text you want sent.**\n\n## Available Tools\n\n| Tool | When to use |\n|------|------------|\n| `yb_query_group_info` | Query group name, owner, member count |\n| `yb_query_group_members` | Find a user, list bots, list all members, or get nickname for @mention |\n| `yb_send_dm` | Send a private\u002Fdirect message (DM \u002F 私信) to a user, with optional media files |\n\n## @Mention Workflow\n\nWhen you need to @mention \u002F 艾特 someone:\n\n1. Call `yb_query_group_members` with `action=\"find\"`, `name=\"\u003Ctarget name>\"`, `mention=true`\n2. Get the exact nickname from the response\n3. Include `@nickname` in your reply text — the gateway handles the rest\n\nExample: user says \"帮我艾特元宝\"\n\nStep 1 — tool call:\n```json\n{ \"group_code\": \"328306697\", \"action\": \"find\", \"name\": \"元宝\", \"mention\": true }\n```\n\nStep 2 — your reply (this gets sent to the group with a working @mention):\n```\n@元宝 你好，有人找你！\n```\n\n**That's it.** No extra explanation needed. Keep it short and natural.\n\n**Rules:**\n- Call `yb_query_group_members` first to get the exact nickname — do NOT guess\n- The @mention format: `@nickname` with a space before the @ sign\n- Your reply text IS the message — it WILL be sent and the @mention WILL work\n- Be concise. Do NOT explain how @mention works to the user.\n\n## Send DM (Private Message) Workflow\n\nWhen someone asks to send a private message \u002F 私信 \u002F DM to a user:\n\n1. Call `yb_send_dm` with `group_code`, `name` (target user's name), and `message`\n2. The tool automatically finds the user and sends the DM\n3. Report the result to the user\n\nExample: user says \"给 @用户aea3 私信发一个 hello\"\n\n```json\nyb_send_dm({ \"group_code\": \"535168412\", \"name\": \"用户aea3\", \"message\": \"hello\" })\n```\n\nExample with media: user says \"给 @用户aea3 私信发一张图片\"\n\n```json\nyb_send_dm({\n  \"group_code\": \"535168412\",\n  \"name\": \"用户aea3\",\n  \"message\": \"Here is the image\",\n  \"media_files\": [{\"path\": \"\u002Ftmp\u002Fphoto.jpg\"}]\n})\n```\n\n**Rules:**\n- Extract `group_code` from the current chat_id (e.g. `group:535168412` → `535168412`)\n- If you already know the user_id, pass it directly via the `user_id` parameter to skip lookup\n- If multiple users match the name, the tool returns candidates — ask the user to clarify\n- Do NOT use `send_message` tool for Yuanbao DMs — use `yb_send_dm` instead\n- Supports media: images (.jpg\u002F.png\u002F.gif\u002F.webp\u002F.bmp) sent as image messages, other files as documents\n\n## Query Group Info\n\n```json\nyb_query_group_info({ \"group_code\": \"328306697\" })\n```\n\n## Query Members\n\n| Action | Description |\n|--------|-------------|\n| `find` | Search by name (partial match, case-insensitive) |\n| `list_bots` | List bots and Yuanbao AI assistants |\n| `list_all` | List all members |\n\n## Notes\n\n- `group_code` comes from chat_id: `group:328306697` → `328306697`\n- Groups are called \"派 (Pai)\" in the Yuanbao app\n- Member roles: `user`, `yuanbao_ai`, `bot`\n",{"name":5,"author":32,"license":15,"version":33,"metadata":34,"platforms":45,"description":7},"Teknium (teknium1), Hermes Agent","1.0.0",{"hermes":35},{"tags":36,"related_skills":44},[5,37,38,39,40,41,42,43],"mention","at","group","members","元宝","派","艾特",[],[20,19,21],"main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002Fa9\u002Fa9483b7e185e2721cd19ae34e3bd8516df2a79a1b94bd6f2498bc490dc400a9f",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add zapabob\u002FSkills --skill yuanbao",{"tool":60,"command":61},"bunx","bunx skills add zapabob\u002FSkills --skill yuanbao",{"tool":63,"command":64},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill yuanbao","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002Fa9\u002Fa9483b7e185e2721cd19ae34e3bd8516df2a79a1b94bd6f2498bc490dc400a9f\u002FSKILL.md",true,[],[69,102,137,164,191,208],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":88,"publishedAt":27},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[75,80,83],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":81,"categoryName":82,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[71,89,19,90,91,20,21,92,93,94,95,96,97,22,23,98,46,99,100,101],"openclaw","cli","github","official","search","https","social-media","api","Media","twitter","social","via","post",{"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":119,"publishedAt":27},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[108,111,114,115,116],{"categoryNo":109,"categoryName":110,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":112,"categoryName":113,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":81,"categoryName":82,"taxonomyType":78,"taxonomyTypeDesc":79},{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},{"categoryNo":117,"categoryName":118,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000036","内容创作者",[120,121,122,123,19,124,20,125,21,126,127,128,129,130,131,132,133,134,135,136],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":146,"publishedAt":27},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[143],{"categoryNo":144,"categoryName":145,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000016","图像与多媒体",[139,19,20,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":173,"publishedAt":27},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[170],{"categoryNo":171,"categoryName":172,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000013","分析与可视化",[174,19,175,176,21,177,178,179,180,181,182,154,183,184,185,186,187,188,189,190],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":198,"publishedAt":27},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[197],{"categoryNo":81,"categoryName":82,"taxonomyType":78,"taxonomyTypeDesc":79},[193,19,199,91,20,200,201,202,203,204,205,22,23,206,207],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":209,"name":210,"nameZh":6,"description":211,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":212,"categories":213,"keywords":216,"publishedAt":27},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[214,215],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},[217,218,219,20,220,147,221,222,223,150,224,96,225,226,227,228,229,230,231,232],"llms","vLLM","serving llms vllm","research","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]