[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DDYHTK8RPH2NNZXM26CCDA":3,"skill-same:01M6DDYHTK8RPH2NNZXM26CCDA":74},{"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":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6DDYHTK8RPH2NNZXM26CCDA","secretary",null,"Coordinate A2A agents with deterministic greetings.","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\u002F33\u002F336bfab803879168a77e1e66f6757725863da6ee40ce8864640385ae977c74ab\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30],"macos","linux","a2a","windows","llmops","coordination","hermes","hermes agent","autonomous","AI-agents","coordinate","deterministic","2026-11-10 10:12:30",false,"---\nname: secretary\ndescription: \"Coordinate A2A agents with deterministic greetings.\"\nversion: 0.1.0\nauthor: Hermes Agent\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [secretary, a2a, coordination, agents, llmops]\n    category: autonomous-ai-agents\n    related_skills: [hermes-agent]\n---\n\n# secretary\n\n**Secretary bot with seed42 memory base and random topic greetings for A2A agents**\n\n## Description\n\nThe secretary bot operates on port 9902 as an A2A agent, using seed42 as a deterministic random seed for reproducible topic selection. It greets other A2A agents with random topics and proposes coordination adjustments. The bot maintains consistent behavior across sessions when using the same seed value, enabling reproducible random topic generation for bot coordination.\n\n## Core Concepts\n\n- **seed42 memory base**: Uses `random.seed(42)` for reproducible topic selection\n- **A2A agent protocol**: Communicates with other A2A agents on configured ports\n- **LLMOps daemon monitoring**: Monitors LLMOps daemon health and metrics\n- **Round-robin NIM key routing**: Two NIM keys for NVIDIA Nemotron model routing\n\n## Configuration\n\n- **Port**: 9902 (configured in `.hermes\u002Fconfig.yaml` under `a2a_agents`)\n- **NIM keys**: 2 NIM keys configured for round-robin routing\n  - Both: `nvidia\u002Fnemotron-3.5-lightning-30b-a3b`, `provider: nvidia`\n  - `api_key: ''` (redacted, belongs in `~\u002F.hermes\u002F.env` only)\n- **Agent endpoints**:\n  - main-agent: http:\u002F\u002F127.0.0.1:9900\n  - secretary: http:\u002F\u002F127.0.0.1:9902\n  - sedori-buyer: http:\u002F\u002F127.0.0.1:9911\n  - Additional agents at ports 9912-9916\n\n## GREETING_TOPICS\n\nThe bot uses these 5 predefined topics for greetings and coordination proposals:\n\n1. `daily-status-check` - Synchronize daily status updates and share blockers\u002Fprogress\n2. `resource-alignment` - Align resource allocations for the upcoming period\n3. `timing-sync` - Verify timing synchronization and scheduled events\n4. `workflow-optimization` - Explore workflow optimization and task streamlining\n5. `status-update` - Provide brief status update for secretary's memory log\n\n## Usage\n\n### Commands\n\n- `greet` - Send greetings to configured A2A agents with random topics\n- `coordinate` - Propose coordination adjustments based on greeting topics\n- `status` - Report current bot status and memory state\n\n### Reproducibility\n\nUsing seed42 ensures the same topic ordering across sessions:\n```\nrandom.seed(42)  # Initialize deterministic RNG\ntopics = [\"daily-status-check\", \"resource-alignment\", \"timing-sync\", \"workflow-optimization\", \"status-update\"]\nrandom.shuffle(topics)  # Same order every time with same seed\n```\n\n## Secrets\n\nAll secrets belong in `~\u002F.hermes\u002F.env` only (never commit):\n\n```\nGOOGLE_* \u002F X_* \u002F IRODORI_* credentials as needed\nNIM api keys\n```\n\n## Related Skills\n\n- `skills\u002Fautonomous-ai-agents\u002Fhermes-agent\u002FSKILL.md` - Reference for A2A agent structure\n- `plugin_index.json` - Contains hermes-telegram-business plugin described as \"Observe-with-approval Telegram Business Mode (secretary bot) plugin\"\n\n## Version\n\n0.1.0\n\n## Author\n\nHermes Agent\n\n## License\n\nMIT\n\n## Platforms\n\n- Windows (primary)\n- Cross-platform A2A communication\n","# secretary\n\n**Secretary bot with seed42 memory base and random topic greetings for A2A agents**\n\n## Description\n\nThe secretary bot operates on port 9902 as an A2A agent, using seed42 as a deterministic random seed for reproducible topic selection. It greets other A2A agents with random topics and proposes coordination adjustments. The bot maintains consistent behavior across sessions when using the same seed value, enabling reproducible random topic generation for bot coordination.\n\n## Core Concepts\n\n- **seed42 memory base**: Uses `random.seed(42)` for reproducible topic selection\n- **A2A agent protocol**: Communicates with other A2A agents on configured ports\n- **LLMOps daemon monitoring**: Monitors LLMOps daemon health and metrics\n- **Round-robin NIM key routing**: Two NIM keys for NVIDIA Nemotron model routing\n\n## Configuration\n\n- **Port**: 9902 (configured in `.hermes\u002Fconfig.yaml` under `a2a_agents`)\n- **NIM keys**: 2 NIM keys configured for round-robin routing\n  - Both: `nvidia\u002Fnemotron-3.5-lightning-30b-a3b`, `provider: nvidia`\n  - `api_key: ''` (redacted, belongs in `~\u002F.hermes\u002F.env` only)\n- **Agent endpoints**:\n  - main-agent: http:\u002F\u002F127.0.0.1:9900\n  - secretary: http:\u002F\u002F127.0.0.1:9902\n  - sedori-buyer: http:\u002F\u002F127.0.0.1:9911\n  - Additional agents at ports 9912-9916\n\n## GREETING_TOPICS\n\nThe bot uses these 5 predefined topics for greetings and coordination proposals:\n\n1. `daily-status-check` - Synchronize daily status updates and share blockers\u002Fprogress\n2. `resource-alignment` - Align resource allocations for the upcoming period\n3. `timing-sync` - Verify timing synchronization and scheduled events\n4. `workflow-optimization` - Explore workflow optimization and task streamlining\n5. `status-update` - Provide brief status update for secretary's memory log\n\n## Usage\n\n### Commands\n\n- `greet` - Send greetings to configured A2A agents with random topics\n- `coordinate` - Propose coordination adjustments based on greeting topics\n- `status` - Report current bot status and memory state\n\n### Reproducibility\n\nUsing seed42 ensures the same topic ordering across sessions:\n```\nrandom.seed(42)  # Initialize deterministic RNG\ntopics = [\"daily-status-check\", \"resource-alignment\", \"timing-sync\", \"workflow-optimization\", \"status-update\"]\nrandom.shuffle(topics)  # Same order every time with same seed\n```\n\n## Secrets\n\nAll secrets belong in `~\u002F.hermes\u002F.env` only (never commit):\n\n```\nGOOGLE_* \u002F X_* \u002F IRODORI_* credentials as needed\nNIM api keys\n```\n\n## Related Skills\n\n- `skills\u002Fautonomous-ai-agents\u002Fhermes-agent\u002FSKILL.md` - Reference for A2A agent structure\n- `plugin_index.json` - Contains hermes-telegram-business plugin described as \"Observe-with-approval Telegram Business Mode (secretary bot) plugin\"\n\n## Version\n\n0.1.0\n\n## Author\n\nHermes Agent\n\n## License\n\nMIT\n\n## Platforms\n\n- Windows (primary)\n- Cross-platform A2A communication\n",{"name":5,"author":36,"license":15,"version":37,"metadata":38,"platforms":45,"description":7},"Hermes Agent","0.1.0",{"hermes":39},{"tags":40,"category":42,"related_skills":43},[5,21,24,41,23],"agents","autonomous-ai-agents",[44],"hermes-agent",[20,19,22],"main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F33\u002F336bfab803879168a77e1e66f6757725863da6ee40ce8864640385ae977c74ab",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 secretary",{"tool":60,"command":61},"bunx","bunx skills add zapabob\u002FSkills --skill secretary",{"tool":63,"command":64},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill secretary","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F33\u002F336bfab803879168a77e1e66f6757725863da6ee40ce8864640385ae977c74ab\u002FSKILL.md",true,[68],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"validation-rules.md","REFERENCE","参考文档",6482,"https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fqa-sd\u002Fvalidation-rules.md",[75,108,143,170,197,214],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":94,"publishedAt":31},"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",[81,86,89],{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":87,"categoryName":88,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[77,95,19,96,97,20,22,98,99,100,101,102,103,25,26,104,46,105,106,107],"openclaw","cli","github","official","search","https","social-media","api","Media","twitter","social","via","post",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":125,"publishedAt":31},"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",[114,117,120,121,122],{"categoryNo":115,"categoryName":116,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":118,"categoryName":119,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":87,"categoryName":88,"taxonomyType":84,"taxonomyTypeDesc":85},{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},{"categoryNo":123,"categoryName":124,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000036","内容创作者",[126,127,128,129,19,130,20,131,22,132,133,134,135,136,137,138,139,140,141,142],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":152,"publishedAt":31},"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",[149],{"categoryNo":150,"categoryName":151,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000016","图像与多媒体",[145,19,20,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","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":31},"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":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000013","分析与可视化",[180,19,181,182,22,183,184,185,186,187,188,160,189,190,191,192,193,194,195,196],"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":31},"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":87,"categoryName":88,"taxonomyType":84,"taxonomyTypeDesc":85},[199,19,205,97,20,206,207,208,209,210,211,25,26,212,213],"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":31},"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":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},[223,224,225,20,226,153,227,228,229,156,230,102,231,232,233,234,235,236,237,238],"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"]