[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C3876M43TAMHYAGMFZ3KB3":3,"skill-same:01M6C3876M43TAMHYAGMFZ3KB3":64},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M6C3876M43TAMHYAGMFZ3KB3","multi-teacher-distill-lite",null,"LinkedIn\u002FInfoQ multi-teacher offline distillation with per-shard cache, stability switch, prune+compress (docs\u002FMULTI_TEACHER_DISTILL.md).","IgorGanapolsky\u002FRandom-Timer","IgorGanapolsky","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F201209?v=4","01M6C2WB7720K13ERYVB3AJ0SQ","Igor Ganapolsky","01M6C2WBBF0NWVQV4A89FS00Q5",1,"MIT","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fmulti-teacher-distill-lite\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"distill","multi teacher distill lite","docs","stability","shard","offline","cache","prune","compress","linkedin","2026-11-10 10:12:30",false,"---\nname: multi-teacher-distill-lite\ndescription: LinkedIn\u002FInfoQ multi-teacher offline distillation with per-shard cache, stability switch, prune+compress (docs\u002FMULTI_TEACHER_DISTILL.md).\n---\n\n# Skill: multi-teacher-distill-lite\n\nFollow `docs\u002FMULTI_TEACHER_DISTILL.md`.\n\n- Primary: https:\u002F\u002Fwww.linkedin.com\u002Fblog\u002Fengineering\u002Finfrastructure\u002Fthe-training-infrastructure-behind-ai-powered-job-search-eight-x-faster-multi-teacher-distillation\n- Digest: https:\u002F\u002Fwww.infoq.com\u002Fnews\u002F2026\u002F09\u002Flinkedin-ai-multi-teacher\u002F\n\n```bash\npython3 scripts\u002Fmulti_teacher_distill_gate.py --json\n```\n\nRules:\n1. **Offline first** — cache teacher soft labels\u002Fembeddings; iterate the student without re-running teachers.\n2. **Per-shard invalidation** — never all-or-nothing teacher cache clears.\n3. **Pluggable teachers** — relevance | engagement | embedding | policy | click | critic.\n4. **Compact student for serving** — distill into skills\u002Fgates\u002Ffixtures; do not serve teacher fleets live.\n5. **Stream, don’t full-stage** the corpus each run.\n6. **Online while exploring** teachers; **offline when stable** (InfoQ).\n7. **Compound gains** — stack moderate local wins; do not default FP8 on small models.\n8. **Prune + compress** student serving; demand **NDCG** (or peer) before quality claims.\n9. No GPU multi-node training SaaS under the hard monthly cap.\n","# Skill: multi-teacher-distill-lite\n\nFollow `docs\u002FMULTI_TEACHER_DISTILL.md`.\n\n- Primary: https:\u002F\u002Fwww.linkedin.com\u002Fblog\u002Fengineering\u002Finfrastructure\u002Fthe-training-infrastructure-behind-ai-powered-job-search-eight-x-faster-multi-teacher-distillation\n- Digest: https:\u002F\u002Fwww.infoq.com\u002Fnews\u002F2026\u002F09\u002Flinkedin-ai-multi-teacher\u002F\n\n```bash\npython3 scripts\u002Fmulti_teacher_distill_gate.py --json\n```\n\nRules:\n1. **Offline first** — cache teacher soft labels\u002Fembeddings; iterate the student without re-running teachers.\n2. **Per-shard invalidation** — never all-or-nothing teacher cache clears.\n3. **Pluggable teachers** — relevance | engagement | embedding | policy | click | critic.\n4. **Compact student for serving** — distill into skills\u002Fgates\u002Ffixtures; do not serve teacher fleets live.\n5. **Stream, don’t full-stage** the corpus each run.\n6. **Online while exploring** teachers; **offline when stable** (InfoQ).\n7. **Compound gains** — stack moderate local wins; do not default FP8 on small models.\n8. **Prune + compress** student serving; demand **NDCG** (or peer) before quality claims.\n9. No GPU multi-node training SaaS under the hard monthly cap.\n",{"name":5,"description":7},"develop","4af946ac9a2b3cfbbe9b2e8696cc436f1d16e2e2",".cursor\u002Fskills\u002Fmulti-teacher-distill-lite",0,"https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer","https:\u002F\u002Fapps.apple.com\u002Fus\u002Fapp\u002Frandom-tactical-timer\u002Fid6758355312","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky","https:\u002F\u002Fwww.igorganapolsky.com","Forward Deploy AI Engineer. Automation specialist.\r\n","2026-11-09 23:14:20",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add IgorGanapolsky\u002FRandom-Timer --skill multi-teacher-distill-lite",{"tool":50,"command":51},"bunx","bunx skills add IgorGanapolsky\u002FRandom-Timer --skill multi-teacher-distill-lite",{"tool":53,"command":54},"pnpm","pnpm dlx skills add IgorGanapolsky\u002FRandom-Timer --skill multi-teacher-distill-lite","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fmulti-teacher-distill-lite\u002FSKILL.md",true,[58],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"agents\u002Fopenai.yaml","REFERENCE","参考文档",299,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-macos-menubar-tuist-app\u002Fagents\u002Fopenai.yaml",[65,87,106,117,129,140],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":81,"publishedAt":29},"01M6C3CEGAENG02BPG636N9WG6","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[71,76],{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":77,"categoryName":78,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[82,83,84,85,86],"writing plans","writing","spec","code","use",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":96,"publishedAt":29},"01M6C3CC40GJBTJQHQ5BF7CQN9","workflow-economics-lite","Escape AI pilot purgatory: require completion-loop workflows with one owner, baseline, economic metric, system-of-record integration, and audit trail. Block orphan chatbots and interest-as-ROI claims.","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fworkflow-economics-lite\u002FSKILL.md",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000023","Skill与智能体开发",[97,98,99,100,101,102,103,104,105],"workflow economics lite","workflow","loop","roi","workflows","audit","integration","baseline","system",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":29},"01M6C3C9ESBW612NMMMBQDWSWR","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[113,114,86,115,116],"verification before completion","verification","evidence","work",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":29},"01M6C3C71DNQHJ6PGV0TN1R99N","value-center-lite","Apply InfoQ Rohrer value-center \u002F VSM five questions (agency + coherence). Use when planning work, shipping releases, or auditing agent autonomy claims. Fail closed on product-only slogans without WQTU\u002Fpaywall value.","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fvalue-center-lite\u002FSKILL.md",[],[124,125,86,116,126,127,128],"value center lite","only","product","shipping","planning",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":29},"01M6C3C41Q0R2J49F3Q4CQ004J","using-superpowers","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fusing-superpowers\u002FSKILL.md",[],[136,137,86,138,139],"superpowers","using superpowers","find","how",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":29},"01M6C3C1EBYXRVMNHZZE9N49PN","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fusing-git-worktrees\u002FSKILL.md",[],[147,148,149,150,151,152,153,116,86],"git","using git worktrees","git worktrees","git worktree","Tools","worktree","workspace"]