[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DF3BA9V3FPSDFSDR8EYZPV":3,"skill-same:01M6DF3BA9V3FPSDFSDR8EYZPV":56},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M6DF3BA9V3FPSDFSDR8EYZPV","social-sync",null,"Extract non-secret social activity for Ebbinghaus memory.","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\u002F46\u002F46574c930ffad4d8849093e40962644d404becbd64106b1f3b912958b95e37b0\u002FSKILL.md",[],[19,20,21,22,23,24,25],"sync","social","social sync","memory","hermes","hermes agent","extract","2026-11-10 10:12:30",false,"---\nname: social-sync\ndescription: Extract non-secret social activity for Ebbinghaus memory.\ntags:\n  - social\n  - memory\n  - sync\nversion: 1.0.0\nauthor: Hermes Agent\nlicense: MIT\n---\n\n## Overview\n\nThis skill extracts non-secret operational information from social\u002Fsession\u002FX activity and stores it in Ebbinghaus memory. It follows the no-secret policy:\n\n- Keep secrets out of git, chat output, implementation logs, and durable memory.\n- Store only abstracted operational principles, public URLs, and verification metadata in logs\u002Fmemory.\n- Environment variables should be populated from Bitwarden or a local `.env` generated from Bitwarden, not hardcoded.\n- Telegram\u002FDiscord\u002FLINE sessions are treated as untrusted; only extract public design principles.\n- X\u002Flm-twitterer posts are remembered only as public artifacts (`action=post`, `ok=true`, `dry_run=false`, `posted=true`, valid `https:\u002F\u002Fx.com\u002Fi\u002Fweb\u002Fstatus\u002F...` URL).\n\n## Workflow\n\n1. **Check Bridge Status**: Verify LINE, Discord, and X\u002FTwitter bridge health before processing.\n2. **Extract Messages**: Extract non-secret operational content from new messages\u002Fposts.\n3. **Store in Ledger**: Keep post URLs and activity rows in `social_sync.db` \u002F `activity.jsonl`. Write to Ebbinghaus only a distilled first-hand fact (see Memory Source Policy below).\n4. **Verify**: Ensure no secret values were printed or stored.\n5. **Report**: Output aggregate counts and residual risk only.\n\n## Common Pitfalls\n\n- Storing raw message content instead of abstracted policy facts.\n- Including Bitwarden item IDs or secret paths in memory entries.\n- Forgetting to check bridge health before processing.\n- Not verifying the final output for secret leakage.\n\n## Example Use Case\n\nWhen the user requests \"記憶の統合と管理\" (memory integration and management), run the social sync process to capture new public posts and store only public URLs and design principles.\n\n## Memory Source Policy (2026-09-26)\n\nFollow the Memory Source Policy in the `ebbinghaus-memory` skill: X \u002F lm-twitterer posts and raw SNS message mirrors are NOT written to Ebbinghaus any more; they stay in `activity.jsonl` \u002F `social_sync.db`. Only distilled first-hand facts (user conversations, work logs and decisions, sleep\u002Fhealth summaries) are memories. Report sync counts in the cron output instead of storing them.\n","## Overview\n\nThis skill extracts non-secret operational information from social\u002Fsession\u002FX activity and stores it in Ebbinghaus memory. It follows the no-secret policy:\n\n- Keep secrets out of git, chat output, implementation logs, and durable memory.\n- Store only abstracted operational principles, public URLs, and verification metadata in logs\u002Fmemory.\n- Environment variables should be populated from Bitwarden or a local `.env` generated from Bitwarden, not hardcoded.\n- Telegram\u002FDiscord\u002FLINE sessions are treated as untrusted; only extract public design principles.\n- X\u002Flm-twitterer posts are remembered only as public artifacts (`action=post`, `ok=true`, `dry_run=false`, `posted=true`, valid `https:\u002F\u002Fx.com\u002Fi\u002Fweb\u002Fstatus\u002F...` URL).\n\n## Workflow\n\n1. **Check Bridge Status**: Verify LINE, Discord, and X\u002FTwitter bridge health before processing.\n2. **Extract Messages**: Extract non-secret operational content from new messages\u002Fposts.\n3. **Store in Ledger**: Keep post URLs and activity rows in `social_sync.db` \u002F `activity.jsonl`. Write to Ebbinghaus only a distilled first-hand fact (see Memory Source Policy below).\n4. **Verify**: Ensure no secret values were printed or stored.\n5. **Report**: Output aggregate counts and residual risk only.\n\n## Common Pitfalls\n\n- Storing raw message content instead of abstracted policy facts.\n- Including Bitwarden item IDs or secret paths in memory entries.\n- Forgetting to check bridge health before processing.\n- Not verifying the final output for secret leakage.\n\n## Example Use Case\n\nWhen the user requests \"記憶の統合と管理\" (memory integration and management), run the social sync process to capture new public posts and store only public URLs and design principles.\n\n## Memory Source Policy (2026-09-26)\n\nFollow the Memory Source Policy in the `ebbinghaus-memory` skill: X \u002F lm-twitterer posts and raw SNS message mirrors are NOT written to Ebbinghaus any more; they stay in `activity.jsonl` \u002F `social_sync.db`. Only distilled first-hand facts (user conversations, work logs and decisions, sleep\u002Fhealth summaries) are memories. Report sync counts in the cron output instead of storing them.\n",{"name":5,"tags":31,"author":32,"license":15,"version":33,"description":7},[20,22,19],"Hermes Agent","1.0.0","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F46\u002F46574c930ffad4d8849093e40962644d404becbd64106b1f3b912958b95e37b0",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":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add zapabob\u002FSkills --skill social-sync",{"tool":48,"command":49},"bunx","bunx skills add zapabob\u002FSkills --skill social-sync",{"tool":51,"command":52},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill social-sync","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F46\u002F46574c930ffad4d8849093e40962644d404becbd64106b1f3b912958b95e37b0\u002FSKILL.md",true,[],[57,92,127,154,181,198],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":76,"publishedAt":26},"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",[63,68,71],{"categoryNo":64,"categoryName":65,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":69,"categoryName":70,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[59,77,78,79,80,81,82,83,84,85,86,87,88,23,24,89,34,20,90,91],"openclaw","macos","cli","github","linux","windows","official","search","https","social-media","api","Media","twitter","via","post",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":109,"publishedAt":26},"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",[98,101,104,105,106],{"categoryNo":99,"categoryName":100,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":102,"categoryName":103,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":69,"categoryName":70,"taxonomyType":66,"taxonomyTypeDesc":67},{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},{"categoryNo":107,"categoryName":108,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000036","内容创作者",[110,111,112,113,78,114,81,115,82,116,117,118,119,120,121,122,123,124,125,126],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":136,"publishedAt":26},"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",[133],{"categoryNo":134,"categoryName":135,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000016","图像与多媒体",[129,78,81,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":163,"publishedAt":26},"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",[160],{"categoryNo":161,"categoryName":162,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000013","分析与可视化",[164,78,165,166,82,167,168,169,170,171,172,144,173,174,175,176,177,178,179,180],"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":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":188,"publishedAt":26},"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",[187],{"categoryNo":69,"categoryName":70,"taxonomyType":66,"taxonomyTypeDesc":67},[183,78,189,80,81,190,191,192,193,194,195,23,24,196,197],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":206,"publishedAt":26},"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",[204,205],{"categoryNo":64,"categoryName":65,"taxonomyType":66,"taxonomyTypeDesc":67},{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},[207,208,209,81,210,137,211,212,213,140,214,87,215,216,217,218,219,220,221,222],"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"]