[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DCBJF2BRZHEDGDKA8G4SJG":3,"skill-same:01M6DCBJF2BRZHEDGDKA8G4SJG":83},{"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":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":61,"commitSha":62,"skillDirectory":63,"forksCount":64,"repositoryHtmlUrl":65,"repositoryHomepageUrl":6,"ownerHtmlUrl":66,"ownerBlogUrl":6,"ownerDescription":67,"updatedAt":68,"install":69,"resources":82},"01M6DCBJF2BRZHEDGDKA8G4SJG","blackbox",null,"Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.","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\u002F10\u002F108b4224b39689a8a494d065ef6fcdc829d30304c1c34527321be778800a2f27\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"multi-agent","ai api","claude-code","multi-model","Coding-Agent","delegate","hermes agent","hermes","coding","cli","model","api","code","tasks","windows","research","codex","linux","llms","2026-11-10 10:12:30",false,"---\r\nname: blackbox\r\ndescription: Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.\r\nversion: 1.0.0\r\nauthor: Hermes Agent (Nous Research)\r\nlicense: MIT\r\nplatforms: [linux, macos, windows]\r\nmetadata:\r\n  hermes:\r\n    tags: [Coding-Agent, Blackbox, Multi-Agent, Judge, Multi-Model]\r\n    related_skills: [claude-code, codex, hermes-agent]\r\n---\r\n\r\n# Blackbox CLI\r\n\r\nDelegate coding tasks to [Blackbox AI](https:\u002F\u002Fwww.blackbox.ai\u002F) via the Hermes terminal. Blackbox is a multi-model coding agent CLI that dispatches tasks to multiple LLMs (Claude, Codex, Gemini, Blackbox Pro) and uses a judge to select the best implementation.\r\n\r\nThe CLI is [open-source](https:\u002F\u002Fgithub.com\u002Fblackboxaicode\u002Fcli) (GPL-3.0, TypeScript, forked from Gemini CLI) and supports interactive sessions, non-interactive one-shots, checkpointing, MCP, and vision model switching.\r\n\r\n## Prerequisites\r\n\r\n- Node.js 20+ installed\r\n- Blackbox CLI installed: `npm install -g @blackboxai\u002Fcli`\r\n- Or install from source:\r\n  ```\r\n  git clone https:\u002F\u002Fgithub.com\u002Fblackboxaicode\u002Fcli.git\r\n  cd cli && npm install && npm install -g .\r\n  ```\r\n- API key from [app.blackbox.ai\u002Fdashboard](https:\u002F\u002Fapp.blackbox.ai\u002Fdashboard)\r\n- Configured: run `blackbox configure` and enter your API key\r\n- Use `pty=true` in terminal calls — Blackbox CLI is an interactive terminal app\r\n\r\n## One-Shot Tasks\r\n\r\n```\r\nterminal(command=\"blackbox --prompt 'Add JWT authentication with refresh tokens to the Express API'\", workdir=\"\u002Fpath\u002Fto\u002Fproject\", pty=true)\r\n```\r\n\r\nFor quick scratch work:\r\n```\r\nterminal(command=\"cd $(mktemp -d) && git init && blackbox --prompt 'Build a REST API for todos with SQLite'\", pty=true)\r\n```\r\n\r\n## Background Mode (Long Tasks)\r\n\r\nFor tasks that take minutes, use background mode so you can monitor progress:\r\n\r\n```\r\n# Start in background with PTY\r\nterminal(command=\"blackbox --prompt 'Refactor the auth module to use OAuth 2.0'\", workdir=\"~\u002Fproject\", background=true, pty=true)\r\n# Returns session_id\r\n\r\n# Monitor progress\r\nprocess(action=\"poll\", session_id=\"\u003Cid>\")\r\nprocess(action=\"log\", session_id=\"\u003Cid>\")\r\n\r\n# Send input if Blackbox asks a question\r\nprocess(action=\"submit\", session_id=\"\u003Cid>\", data=\"yes\")\r\n\r\n# Kill if needed\r\nprocess(action=\"kill\", session_id=\"\u003Cid>\")\r\n```\r\n\r\n## Checkpoints & Resume\r\n\r\nBlackbox CLI has built-in checkpoint support for pausing and resuming tasks:\r\n\r\n```\r\n# After a task completes, Blackbox shows a checkpoint tag\r\n# Resume with a follow-up task:\r\nterminal(command=\"blackbox --resume-checkpoint 'task-abc123-2026-03-06' --prompt 'Now add rate limiting to the endpoints'\", workdir=\"~\u002Fproject\", pty=true)\r\n```\r\n\r\n## Session Commands\r\n\r\nDuring an interactive session, use these commands:\r\n\r\n| Command | Effect |\r\n|---------|--------|\r\n| `\u002Fcompress` | Shrink conversation history to save tokens |\r\n| `\u002Fclear` | Wipe history and start fresh |\r\n| `\u002Fstats` | View current token usage |\r\n| `Ctrl+C` | Cancel current operation |\r\n\r\n## PR Reviews\r\n\r\nClone to a temp directory to avoid modifying the working tree:\r\n\r\n```\r\nterminal(command=\"REVIEW=$(mktemp -d) && git clone https:\u002F\u002Fgithub.com\u002Fuser\u002Frepo.git $REVIEW && cd $REVIEW && gh pr checkout 42 && blackbox --prompt 'Review this PR against main. Check for bugs, security issues, and code quality.'\", pty=true)\r\n```\r\n\r\n## Parallel Work\r\n\r\nSpawn multiple Blackbox instances for independent tasks:\r\n\r\n```\r\nterminal(command=\"blackbox --prompt 'Fix the login bug'\", workdir=\"\u002Ftmp\u002Fissue-1\", background=true, pty=true)\r\nterminal(command=\"blackbox --prompt 'Add unit tests for auth'\", workdir=\"\u002Ftmp\u002Fissue-2\", background=true, pty=true)\r\n\r\n# Monitor all\r\nprocess(action=\"list\")\r\n```\r\n\r\n## Multi-Model Mode\r\n\r\nBlackbox's unique feature is running the same task through multiple models and judging the results. Configure which models to use via `blackbox configure` — select multiple providers to enable the Chairman\u002Fjudge workflow where the CLI evaluates outputs from different models and picks the best one.\r\n\r\n## Key Flags\r\n\r\n| Flag | Effect |\r\n|------|--------|\r\n| `--prompt \"task\"` | Non-interactive one-shot execution |\r\n| `--resume-checkpoint \"tag\"` | Resume from a saved checkpoint |\r\n| `--yolo` | Auto-approve all actions and model switches |\r\n| `blackbox session` | Start interactive chat session |\r\n| `blackbox configure` | Change settings, providers, models |\r\n| `blackbox info` | Display system information |\r\n\r\n## Vision Support\r\n\r\nBlackbox automatically detects images in input and can switch to multimodal analysis. VLM modes:\r\n- `\"once\"` — Switch model for current query only\r\n- `\"session\"` — Switch for entire session\r\n- `\"persist\"` — Stay on current model (no switch)\r\n\r\n## Token Limits\r\n\r\nControl token usage via `.blackboxcli\u002Fsettings.json`:\r\n```json\r\n{\r\n  \"sessionTokenLimit\": 32000\r\n}\r\n```\r\n\r\n## Rules\r\n\r\n1. **Always use `pty=true`** — Blackbox CLI is an interactive terminal app and will hang without a PTY\r\n2. **Use `workdir`** — keep the agent focused on the right directory\r\n3. **Background for long tasks** — use `background=true` and monitor with `process` tool\r\n4. **Don't interfere** — monitor with `poll`\u002F`log`, don't kill sessions because they're slow\r\n5. **Report results** — after completion, check what changed and summarize for the user\r\n6. **Credits cost money** — Blackbox uses a credit-based system; multi-model mode consumes credits faster\r\n7. **Check prerequisites** — verify `blackbox` CLI is installed before attempting delegation\r\n","# Blackbox CLI\r\n\r\nDelegate coding tasks to [Blackbox AI](https:\u002F\u002Fwww.blackbox.ai\u002F) via the Hermes terminal. Blackbox is a multi-model coding agent CLI that dispatches tasks to multiple LLMs (Claude, Codex, Gemini, Blackbox Pro) and uses a judge to select the best implementation.\r\n\r\nThe CLI is [open-source](https:\u002F\u002Fgithub.com\u002Fblackboxaicode\u002Fcli) (GPL-3.0, TypeScript, forked from Gemini CLI) and supports interactive sessions, non-interactive one-shots, checkpointing, MCP, and vision model switching.\r\n\r\n## Prerequisites\r\n\r\n- Node.js 20+ installed\r\n- Blackbox CLI installed: `npm install -g @blackboxai\u002Fcli`\r\n- Or install from source:\r\n  ```\r\n  git clone https:\u002F\u002Fgithub.com\u002Fblackboxaicode\u002Fcli.git\r\n  cd cli && npm install && npm install -g .\r\n  ```\r\n- API key from [app.blackbox.ai\u002Fdashboard](https:\u002F\u002Fapp.blackbox.ai\u002Fdashboard)\r\n- Configured: run `blackbox configure` and enter your API key\r\n- Use `pty=true` in terminal calls — Blackbox CLI is an interactive terminal app\r\n\r\n## One-Shot Tasks\r\n\r\n```\r\nterminal(command=\"blackbox --prompt 'Add JWT authentication with refresh tokens to the Express API'\", workdir=\"\u002Fpath\u002Fto\u002Fproject\", pty=true)\r\n```\r\n\r\nFor quick scratch work:\r\n```\r\nterminal(command=\"cd $(mktemp -d) && git init && blackbox --prompt 'Build a REST API for todos with SQLite'\", pty=true)\r\n```\r\n\r\n## Background Mode (Long Tasks)\r\n\r\nFor tasks that take minutes, use background mode so you can monitor progress:\r\n\r\n```\r\n# Start in background with PTY\r\nterminal(command=\"blackbox --prompt 'Refactor the auth module to use OAuth 2.0'\", workdir=\"~\u002Fproject\", background=true, pty=true)\r\n# Returns session_id\r\n\r\n# Monitor progress\r\nprocess(action=\"poll\", session_id=\"\u003Cid>\")\r\nprocess(action=\"log\", session_id=\"\u003Cid>\")\r\n\r\n# Send input if Blackbox asks a question\r\nprocess(action=\"submit\", session_id=\"\u003Cid>\", data=\"yes\")\r\n\r\n# Kill if needed\r\nprocess(action=\"kill\", session_id=\"\u003Cid>\")\r\n```\r\n\r\n## Checkpoints & Resume\r\n\r\nBlackbox CLI has built-in checkpoint support for pausing and resuming tasks:\r\n\r\n```\r\n# After a task completes, Blackbox shows a checkpoint tag\r\n# Resume with a follow-up task:\r\nterminal(command=\"blackbox --resume-checkpoint 'task-abc123-2026-03-06' --prompt 'Now add rate limiting to the endpoints'\", workdir=\"~\u002Fproject\", pty=true)\r\n```\r\n\r\n## Session Commands\r\n\r\nDuring an interactive session, use these commands:\r\n\r\n| Command | Effect |\r\n|---------|--------|\r\n| `\u002Fcompress` | Shrink conversation history to save tokens |\r\n| `\u002Fclear` | Wipe history and start fresh |\r\n| `\u002Fstats` | View current token usage |\r\n| `Ctrl+C` | Cancel current operation |\r\n\r\n## PR Reviews\r\n\r\nClone to a temp directory to avoid modifying the working tree:\r\n\r\n```\r\nterminal(command=\"REVIEW=$(mktemp -d) && git clone https:\u002F\u002Fgithub.com\u002Fuser\u002Frepo.git $REVIEW && cd $REVIEW && gh pr checkout 42 && blackbox --prompt 'Review this PR against main. Check for bugs, security issues, and code quality.'\", pty=true)\r\n```\r\n\r\n## Parallel Work\r\n\r\nSpawn multiple Blackbox instances for independent tasks:\r\n\r\n```\r\nterminal(command=\"blackbox --prompt 'Fix the login bug'\", workdir=\"\u002Ftmp\u002Fissue-1\", background=true, pty=true)\r\nterminal(command=\"blackbox --prompt 'Add unit tests for auth'\", workdir=\"\u002Ftmp\u002Fissue-2\", background=true, pty=true)\r\n\r\n# Monitor all\r\nprocess(action=\"list\")\r\n```\r\n\r\n## Multi-Model Mode\r\n\r\nBlackbox's unique feature is running the same task through multiple models and judging the results. Configure which models to use via `blackbox configure` — select multiple providers to enable the Chairman\u002Fjudge workflow where the CLI evaluates outputs from different models and picks the best one.\r\n\r\n## Key Flags\r\n\r\n| Flag | Effect |\r\n|------|--------|\r\n| `--prompt \"task\"` | Non-interactive one-shot execution |\r\n| `--resume-checkpoint \"tag\"` | Resume from a saved checkpoint |\r\n| `--yolo` | Auto-approve all actions and model switches |\r\n| `blackbox session` | Start interactive chat session |\r\n| `blackbox configure` | Change settings, providers, models |\r\n| `blackbox info` | Display system information |\r\n\r\n## Vision Support\r\n\r\nBlackbox automatically detects images in input and can switch to multimodal analysis. VLM modes:\r\n- `\"once\"` — Switch model for current query only\r\n- `\"session\"` — Switch for entire session\r\n- `\"persist\"` — Stay on current model (no switch)\r\n\r\n## Token Limits\r\n\r\nControl token usage via `.blackboxcli\u002Fsettings.json`:\r\n```json\r\n{\r\n  \"sessionTokenLimit\": 32000\r\n}\r\n```\r\n\r\n## Rules\r\n\r\n1. **Always use `pty=true`** — Blackbox CLI is an interactive terminal app and will hang without a PTY\r\n2. **Use `workdir`** — keep the agent focused on the right directory\r\n3. **Background for long tasks** — use `background=true` and monitor with `process` tool\r\n4. **Don't interfere** — monitor with `poll`\u002F`log`, don't kill sessions because they're slow\r\n5. **Report results** — after completion, check what changed and summarize for the user\r\n6. **Credits cost money** — Blackbox uses a credit-based system; multi-model mode consumes credits faster\r\n7. **Check prerequisites** — verify `blackbox` CLI is installed before attempting delegation\r\n",{"name":5,"author":48,"license":15,"version":49,"metadata":50,"platforms":59,"description":7},"Hermes Agent (Nous Research)","1.0.0",{"hermes":51},{"tags":52,"related_skills":57},[28,53,54,55,56],"Blackbox","Multi-Agent","Judge","Multi-Model",[26,40,58],"hermes-agent",[41,60,38],"macos","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F10\u002F108b4224b39689a8a494d065ef6fcdc829d30304c1c34527321be778800a2f27",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":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add zapabob\u002FSkills --skill blackbox",{"tool":75,"command":76},"bunx","bunx skills add zapabob\u002FSkills --skill blackbox",{"tool":78,"command":79},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill blackbox","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F10\u002F108b4224b39689a8a494d065ef6fcdc829d30304c1c34527321be778800a2f27\u002FSKILL.md",true,[],[84,111,144,170,197,214],{"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":99,"publishedAt":43},"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",[90,93,94],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[86,100,60,33,101,41,38,102,103,104,105,35,106,31,30,107,61,108,109,110],"openclaw","github","official","search","https","social-media","Media","twitter","social","via","post",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":128,"publishedAt":43},"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",[117,120,123,124,125],{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},{"categoryNo":126,"categoryName":127,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000036","内容创作者",[129,130,131,132,60,133,41,134,38,135,37,136,36,137,138,139,140,141,142,143],"writing","writing plans","plans","design","review","workflow","documentation","development","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":153,"publishedAt":43},"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",[150],{"categoryNo":151,"categoryName":152,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[146,60,41,154,155,156,157,158,159,160,34,161,162,163,164,165,166,167,168,169],"openai","speech","multimodal","Transformers","ASR","Audio","text","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":179,"publishedAt":43},"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",[176],{"categoryNo":177,"categoryName":178,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[180,60,181,182,38,183,184,185,186,187,188,34,189,190,191,192,193,194,195,196],"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":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":204,"publishedAt":43},"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",[203],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[199,60,205,101,41,206,207,208,209,210,211,31,30,212,213],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":222,"publishedAt":43},"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",[220,221],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},[42,223,224,41,39,154,225,226,227,157,228,35,229,230,231,232,233,234,235,236],"vLLM","serving llms vllm","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]