[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DFRG32DC8321N4AZ4EECTG":3,"skill-same:01M6DFRG32DC8321N4AZ4EECTG":78},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":6,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":63,"updatedAt":64,"install":65,"resources":77},"01M6DFRG32DC8321N4AZ4EECTG","1password",null,"Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in, and reading\u002Finjecting secrets for commands.","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\u002F51\u002F51bebfc277e0acb8e33e5840a66c179dce641438131e3d81adff5e772a07f08c\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"app","cli","service","token","commands","desktop app","up","use","settings","hermes agent","hermes","secrets","SET","service-accounts","integration","https","desktop","create","security","2026-11-10 10:12:30",false,"---\r\nname: 1password\r\ndescription: Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in, and reading\u002Finjecting secrets for commands.\r\nversion: 1.0.0\r\nauthor: arceus77-7, enhanced by Hermes Agent\r\nlicense: MIT\r\nmetadata:\r\n  hermes:\r\n    tags: [security, secrets, 1password, op, cli]\r\n    category: security\r\nsetup:\r\n  help: \"Create a service account at https:\u002F\u002Fmy.1password.com → Settings → Service Accounts\"\r\n  collect_secrets:\r\n    - env_var: OP_SERVICE_ACCOUNT_TOKEN\r\n      prompt: \"1Password Service Account Token\"\r\n      provider_url: \"https:\u002F\u002Fdeveloper.1password.com\u002Fdocs\u002Fservice-accounts\u002F\"\r\n      secret: true\r\n---\r\n\r\n# 1Password CLI\r\n\r\nUse this skill when the user wants secrets managed through 1Password instead of plaintext env vars or files.\r\n\r\n## Requirements\r\n\r\n- 1Password account\r\n- 1Password CLI (`op`) installed\r\n- One of: desktop app integration, service account token (`OP_SERVICE_ACCOUNT_TOKEN`), or Connect server\r\n- `tmux` available for stable authenticated sessions during Hermes terminal calls (desktop app flow only)\r\n\r\n## When to Use\r\n\r\n- Install or configure 1Password CLI\r\n- Sign in with `op signin`\r\n- Read secret references like `op:\u002F\u002FVault\u002FItem\u002Ffield`\r\n- Inject secrets into config\u002Ftemplates using `op inject`\r\n- Run commands with secret env vars via `op run`\r\n\r\n## Authentication Methods\r\n\r\n### Service Account (recommended for Hermes)\r\n\r\nSet `OP_SERVICE_ACCOUNT_TOKEN` in `~\u002F.hermes\u002F.env` (the skill will prompt for this on first load).\r\nNo desktop app needed. Supports `op read`, `op inject`, `op run`.\r\n\r\n```bash\r\nexport OP_SERVICE_ACCOUNT_TOKEN=\"your-token-here\"\r\nop whoami  # verify — should show Type: SERVICE_ACCOUNT\r\n```\r\n\r\n### Desktop App Integration (interactive)\r\n\r\n1. Enable in 1Password desktop app: Settings → Developer → Integrate with 1Password CLI\r\n2. Ensure app is unlocked\r\n3. Run `op signin` and approve the biometric prompt\r\n\r\n### Connect Server (self-hosted)\r\n\r\n```bash\r\nexport OP_CONNECT_HOST=\"http:\u002F\u002Flocalhost:8080\"\r\nexport OP_CONNECT_TOKEN=\"your-connect-token\"\r\n```\r\n\r\n## Setup\r\n\r\n1. Install CLI:\r\n\r\n```bash\r\n# macOS\r\nbrew install 1password-cli\r\n\r\n# Linux (official package\u002Finstall docs)\r\n# See references\u002Fget-started.md for distro-specific links.\r\n\r\n# Windows (winget)\r\nwinget install AgileBits.1Password.CLI\r\n```\r\n\r\n2. Verify:\r\n\r\n```bash\r\nop --version\r\n```\r\n\r\n3. Choose an auth method above and configure it.\r\n\r\n## Hermes Execution Pattern (desktop app flow)\r\n\r\nHermes terminal commands are non-interactive by default and can lose auth context between calls.\r\nFor reliable `op` use with desktop app integration, run sign-in and secret operations inside a dedicated tmux session.\r\n\r\nNote: This is NOT needed when using `OP_SERVICE_ACCOUNT_TOKEN` — the token persists across terminal calls automatically.\r\n\r\n```bash\r\nSOCKET_DIR=\"${TMPDIR:-\u002Ftmp}\u002Fhermes-tmux-sockets\"\r\nmkdir -p \"$SOCKET_DIR\"\r\nSOCKET=\"$SOCKET_DIR\u002Fhermes-op.sock\"\r\nSESSION=\"op-auth-$(date +%Y%m%d-%H%M%S)\"\r\n\r\ntmux -S \"$SOCKET\" new -d -s \"$SESSION\" -n shell\r\n\r\n# Sign in (approve in desktop app when prompted)\r\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 -- \"eval \\\"\\$(op signin --account my.1password.com)\\\"\" Enter\r\n\r\n# Verify auth\r\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 -- \"op whoami\" Enter\r\n\r\n# Example read\r\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 -- \"op read 'op:\u002F\u002FPrivate\u002FNpmjs\u002Fone-time password?attribute=otp'\" Enter\r\n\r\n# Capture output when needed\r\ntmux -S \"$SOCKET\" capture-pane -p -J -t \"$SESSION\":0.0 -S -200\r\n\r\n# Cleanup\r\ntmux -S \"$SOCKET\" kill-session -t \"$SESSION\"\r\n```\r\n\r\n## Common Operations\r\n\r\n### Read a secret\r\n\r\n```bash\r\nop read \"op:\u002F\u002Fapp-prod\u002Fdb\u002Fpassword\"\r\n```\r\n\r\n### Get OTP\r\n\r\n```bash\r\nop read \"op:\u002F\u002Fapp-prod\u002Fnpm\u002Fone-time password?attribute=otp\"\r\n```\r\n\r\n### Inject into template\r\n\r\n```bash\r\necho \"db_password: {{ op:\u002F\u002Fapp-prod\u002Fdb\u002Fpassword }}\" | op inject\r\n```\r\n\r\n### Run a command with secret env var\r\n\r\n```bash\r\nexport DB_PASSWORD=\"[REDACTED]\"\r\nop run -- sh -c '[ -n \"$DB_PASSWORD\" ] && echo \"DB_PASSWORD is set\" || echo \"DB_PASSWORD missing\"'\r\n```\r\n\r\n## Guardrails\r\n\r\n- Never print raw secrets back to user unless they explicitly request the value.\r\n- Prefer `op run` \u002F `op inject` instead of writing secrets into files.\r\n- If command fails with \"account is not signed in\", run `op signin` again in the same tmux session.\r\n- If desktop app integration is unavailable (headless\u002FCI), use service account token flow.\r\n\r\n## CI \u002F Headless note\r\n\r\nFor non-interactive use, authenticate with `OP_SERVICE_ACCOUNT_TOKEN` and avoid interactive `op signin`.\r\nService accounts require CLI v2.18.0+.\r\n\r\n## References\r\n\r\n- `references\u002Fget-started.md`\r\n- `references\u002Fcli-examples.md`\r\n- https:\u002F\u002Fdeveloper.1password.com\u002Fdocs\u002Fcli\u002F\r\n- https:\u002F\u002Fdeveloper.1password.com\u002Fdocs\u002Fservice-accounts\u002F\r\n","# 1Password CLI\r\n\r\nUse this skill when the user wants secrets managed through 1Password instead of plaintext env vars or files.\r\n\r\n## Requirements\r\n\r\n- 1Password account\r\n- 1Password CLI (`op`) installed\r\n- One of: desktop app integration, service account token (`OP_SERVICE_ACCOUNT_TOKEN`), or Connect server\r\n- `tmux` available for stable authenticated sessions during Hermes terminal calls (desktop app flow only)\r\n\r\n## When to Use\r\n\r\n- Install or configure 1Password CLI\r\n- Sign in with `op signin`\r\n- Read secret references like `op:\u002F\u002FVault\u002FItem\u002Ffield`\r\n- Inject secrets into config\u002Ftemplates using `op inject`\r\n- Run commands with secret env vars via `op run`\r\n\r\n## Authentication Methods\r\n\r\n### Service Account (recommended for Hermes)\r\n\r\nSet `OP_SERVICE_ACCOUNT_TOKEN` in `~\u002F.hermes\u002F.env` (the skill will prompt for this on first load).\r\nNo desktop app needed. Supports `op read`, `op inject`, `op run`.\r\n\r\n```bash\r\nexport OP_SERVICE_ACCOUNT_TOKEN=\"your-token-here\"\r\nop whoami  # verify — should show Type: SERVICE_ACCOUNT\r\n```\r\n\r\n### Desktop App Integration (interactive)\r\n\r\n1. Enable in 1Password desktop app: Settings → Developer → Integrate with 1Password CLI\r\n2. Ensure app is unlocked\r\n3. Run `op signin` and approve the biometric prompt\r\n\r\n### Connect Server (self-hosted)\r\n\r\n```bash\r\nexport OP_CONNECT_HOST=\"http:\u002F\u002Flocalhost:8080\"\r\nexport OP_CONNECT_TOKEN=\"your-connect-token\"\r\n```\r\n\r\n## Setup\r\n\r\n1. Install CLI:\r\n\r\n```bash\r\n# macOS\r\nbrew install 1password-cli\r\n\r\n# Linux (official package\u002Finstall docs)\r\n# See references\u002Fget-started.md for distro-specific links.\r\n\r\n# Windows (winget)\r\nwinget install AgileBits.1Password.CLI\r\n```\r\n\r\n2. Verify:\r\n\r\n```bash\r\nop --version\r\n```\r\n\r\n3. Choose an auth method above and configure it.\r\n\r\n## Hermes Execution Pattern (desktop app flow)\r\n\r\nHermes terminal commands are non-interactive by default and can lose auth context between calls.\r\nFor reliable `op` use with desktop app integration, run sign-in and secret operations inside a dedicated tmux session.\r\n\r\nNote: This is NOT needed when using `OP_SERVICE_ACCOUNT_TOKEN` — the token persists across terminal calls automatically.\r\n\r\n```bash\r\nSOCKET_DIR=\"${TMPDIR:-\u002Ftmp}\u002Fhermes-tmux-sockets\"\r\nmkdir -p \"$SOCKET_DIR\"\r\nSOCKET=\"$SOCKET_DIR\u002Fhermes-op.sock\"\r\nSESSION=\"op-auth-$(date +%Y%m%d-%H%M%S)\"\r\n\r\ntmux -S \"$SOCKET\" new -d -s \"$SESSION\" -n shell\r\n\r\n# Sign in (approve in desktop app when prompted)\r\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 -- \"eval \\\"\\$(op signin --account my.1password.com)\\\"\" Enter\r\n\r\n# Verify auth\r\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 -- \"op whoami\" Enter\r\n\r\n# Example read\r\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 -- \"op read 'op:\u002F\u002FPrivate\u002FNpmjs\u002Fone-time password?attribute=otp'\" Enter\r\n\r\n# Capture output when needed\r\ntmux -S \"$SOCKET\" capture-pane -p -J -t \"$SESSION\":0.0 -S -200\r\n\r\n# Cleanup\r\ntmux -S \"$SOCKET\" kill-session -t \"$SESSION\"\r\n```\r\n\r\n## Common Operations\r\n\r\n### Read a secret\r\n\r\n```bash\r\nop read \"op:\u002F\u002Fapp-prod\u002Fdb\u002Fpassword\"\r\n```\r\n\r\n### Get OTP\r\n\r\n```bash\r\nop read \"op:\u002F\u002Fapp-prod\u002Fnpm\u002Fone-time password?attribute=otp\"\r\n```\r\n\r\n### Inject into template\r\n\r\n```bash\r\necho \"db_password: {{ op:\u002F\u002Fapp-prod\u002Fdb\u002Fpassword }}\" | op inject\r\n```\r\n\r\n### Run a command with secret env var\r\n\r\n```bash\r\nexport DB_PASSWORD=\"[REDACTED]\"\r\nop run -- sh -c '[ -n \"$DB_PASSWORD\" ] && echo \"DB_PASSWORD is set\" || echo \"DB_PASSWORD missing\"'\r\n```\r\n\r\n## Guardrails\r\n\r\n- Never print raw secrets back to user unless they explicitly request the value.\r\n- Prefer `op run` \u002F `op inject` instead of writing secrets into files.\r\n- If command fails with \"account is not signed in\", run `op signin` again in the same tmux session.\r\n- If desktop app integration is unavailable (headless\u002FCI), use service account token flow.\r\n\r\n## CI \u002F Headless note\r\n\r\nFor non-interactive use, authenticate with `OP_SERVICE_ACCOUNT_TOKEN` and avoid interactive `op signin`.\r\nService accounts require CLI v2.18.0+.\r\n\r\n## References\r\n\r\n- `references\u002Fget-started.md`\r\n- `references\u002Fcli-examples.md`\r\n- https:\u002F\u002Fdeveloper.1password.com\u002Fdocs\u002Fcli\u002F\r\n- https:\u002F\u002Fdeveloper.1password.com\u002Fdocs\u002Fservice-accounts\u002F\r\n",{"name":5,"setup":43,"author":51,"license":15,"version":52,"metadata":53,"description":7},{"help":44,"collect_secrets":45},"Create a service account at https:\u002F\u002Fmy.1password.com → Settings → Service Accounts",[46],{"prompt":47,"secret":48,"env_var":49,"provider_url":50},"1Password Service Account Token",true,"OP_SERVICE_ACCOUNT_TOKEN","https:\u002F\u002Fdeveloper.1password.com\u002Fdocs\u002Fservice-accounts\u002F","arceus77-7, enhanced by Hermes Agent","1.0.0",{"hermes":54},{"tags":55,"category":37},[37,30,5,56,20],"op","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F51\u002F51bebfc277e0acb8e33e5840a66c179dce641438131e3d81adff5e772a07f08c",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":66,"prompt":76,"zipAvailable":48},[67,70,73],{"tool":68,"command":69},"npx","npx skills add zapabob\u002FSkills --skill 1password",{"tool":71,"command":72},"bunx","bunx skills add zapabob\u002FSkills --skill 1password",{"tool":74,"command":75},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill 1password","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F51\u002F51bebfc277e0acb8e33e5840a66c179dce641438131e3d81adff5e772a07f08c\u002FSKILL.md",[],[79,113,148,174,201,218],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":98,"publishedAt":38},"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",[85,90,93],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":91,"categoryName":92,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[81,99,100,20,101,102,103,104,105,34,106,107,108,29,28,109,57,110,111,112],"openclaw","macos","github","linux","windows","official","search","social-media","api","Media","twitter","social","via","post",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":130,"publishedAt":38},"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",[119,122,125,126,127],{"categoryNo":120,"categoryName":121,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":123,"categoryName":124,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":91,"categoryName":92,"taxonomyType":88,"taxonomyTypeDesc":89},{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":128,"categoryName":129,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000036","内容创作者",[131,132,133,134,100,135,102,136,103,137,138,139,140,141,142,143,144,145,146,147],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":157,"publishedAt":38},"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",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000016","图像与多媒体",[150,100,102,158,159,160,161,162,163,164,165,166,26,167,168,169,170,171,172,173],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":183,"publishedAt":38},"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",[180],{"categoryNo":181,"categoryName":182,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000013","分析与可视化",[184,100,185,186,103,187,188,189,190,191,192,165,193,194,195,196,197,198,199,200],"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":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":208,"publishedAt":38},"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",[207],{"categoryNo":91,"categoryName":92,"taxonomyType":88,"taxonomyTypeDesc":89},[203,100,209,101,102,210,211,212,213,214,215,29,28,216,217],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":222,"categories":223,"keywords":226,"publishedAt":38},"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",[224,225],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},[227,228,229,102,230,158,231,232,233,161,234,107,235,236,237,238,239,240,241,242],"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"]