[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71CFY9ATD0BAXV6B14HFG7C":3,"skill-same:01M71CFY9ATD0BAXV6B14HFG7C":68},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M71CFY9ATD0BAXV6B14HFG7C","yuri-shura",null,"6-perspective adversarial review for high-stakes turns (architecture decisions, refactor planning, deployment review) — fans out architect, adversary (7-vector attack), maintainer, ops, product, and security perspectives in parallel, then consolidates. Use when user says 'review this decision', '\u002Fshura', 'adversarial review', 'what could go wrong', 'architecture review', or 'deployment review'.","nexuslinkproductions\u002Fyuri-os","nexuslinkproductions","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F273246263?v=4","01M718YX9NZRCW50B59B8ZVDKN","Marcel Spatz","01M718YXAQ7530F4B1VKN6SFQV",2,"MIT","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-shura\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"yuri shura","perspectives","when","adversarial","for","strategic","strategic review","use","ops","decisions","review","decision","parallel","vector","harness","planning","deployment","architecture review","architecture","workflow","2026-11-10 10:12:30",false,"---\nname: yuri-shura\ndescription: \"6-perspective adversarial review for high-stakes turns (architecture decisions, refactor planning, deployment review) — fans out architect, adversary (7-vector attack), maintainer, ops, product, and security perspectives in parallel, then consolidates. Use when user says 'review this decision', '\u002Fshura', 'adversarial review', 'what could go wrong', 'architecture review', or 'deployment review'.\"\ntriggers:\n  - \"\u002Fshura\"\n  - \"strategic review\"\n  - \"architecture review\"\n  - \"yuri-shura\"\nscope: harness\ninvocation: workflow\n---\n\n# Yuri Shura -- 6-Perspective Review\n\nInspired by Istishraf (MIT-licensed Claude plugin). Original implementation adapted to Yuri OS's pulse-cortex.\n\n## When to invoke\n\nModel-invocable for high-stakes strategic review (architecture, refactor planning, deployment); or `\u002Fshura \u003Ctopic>`. Advisory only — never holds implementation authority.\n\n## 6 Perspectives (native Workflow fan-out)\n\nRun via the **Workflow tool**: 6 parallel agents, each adopting one perspective lens (Opus\u002FSonnet, self-selected per depth). Each returns a bounded structured finding; the main thread consolidates. No external model lanes.\n\n| Perspective | Lens |\n|---|---|\n| Architect | soundness of design |\n| Adversary | 7-vector attack protocol (see below) |\n| Maintainer | long-term cost |\n| Ops | production readiness |\n| Product | user impact |\n| Security | risk surface |\n\n## Output format\n\nSix bounded sections (50 lines each) consolidated by main thread. Each perspective answers: assessment, risks, recommendation.\n\n## Adversary Protocol — 7-Vector Attack Checklist\n\nThe `@ds-pro` adversary lane runs this checklist against every artifact. Derived from Anderson's security framework + Ibn Khaldun's resilience\u002Fdecay model + SOUL.md reversibility principle. Source: strategic-thinker MIT brief (2026-05-16).\n\n| # | Vector | Question |\n|---|--------|----------|\n| 1 | **Policy** | Does this violate an explicit rule, boundary, or operating constraint? |\n| 2 | **Mechanism** | How could the implementation fail, hang, corrupt state, or be exploited? |\n| 3 | **Assurance** | What cannot be monitored, audited, or verified after the fact? |\n| 4 | **Incentives** | What system or actor benefits from this failing silently? |\n| 5 | **Fragility** | Where are the single points of failure, tight coupling, or cascade paths? |\n| 6 | **Scope creep** | What silent expansion or unapproved scope increase does this permit? |\n| 7 | **Irreversibility** | How hard is rollback if this is wrong? Is there a tested recovery path? |\n\nAdversary prompt injection: for each vector, deliver one finding or \"clean\" — no filler. Total output ≤ 35 lines.\n\n## Quarantine rules\n\nAdvisory output only — no implementation authority. Findings are consolidated for the owner; any resulting change goes through the normal owner-gated commit path.\n\n## Trigger phrases (auto-classify)\n\n- \"architecture review\"\n- \"should we refactor\"\n- \"deployment plan\"\n- \"high stakes\"\n- \"before we ship\"\n\n## Session Notes\n\n### 2026-05-17\n- session: 113m | peak ctx: 0% | compacts: 0\n- tools: Bash×168, Edit×41, Read×33, mcp×33, Write×11, ToolSearch×2, Skill×1, AskUserQuestion×1, ExitPlanMode×1\n- corrections: none\n- errors: none\n\n### 2026-05-16\n- session: 61m | peak ctx: 0% | compacts: 0\n- tools: Bash×50, Edit×28, Write×13, Read×12\n- corrections: none\n- errors: none\n","# Yuri Shura -- 6-Perspective Review\n\nInspired by Istishraf (MIT-licensed Claude plugin). Original implementation adapted to Yuri OS's pulse-cortex.\n\n## When to invoke\n\nModel-invocable for high-stakes strategic review (architecture, refactor planning, deployment); or `\u002Fshura \u003Ctopic>`. Advisory only — never holds implementation authority.\n\n## 6 Perspectives (native Workflow fan-out)\n\nRun via the **Workflow tool**: 6 parallel agents, each adopting one perspective lens (Opus\u002FSonnet, self-selected per depth). Each returns a bounded structured finding; the main thread consolidates. No external model lanes.\n\n| Perspective | Lens |\n|---|---|\n| Architect | soundness of design |\n| Adversary | 7-vector attack protocol (see below) |\n| Maintainer | long-term cost |\n| Ops | production readiness |\n| Product | user impact |\n| Security | risk surface |\n\n## Output format\n\nSix bounded sections (50 lines each) consolidated by main thread. Each perspective answers: assessment, risks, recommendation.\n\n## Adversary Protocol — 7-Vector Attack Checklist\n\nThe `@ds-pro` adversary lane runs this checklist against every artifact. Derived from Anderson's security framework + Ibn Khaldun's resilience\u002Fdecay model + SOUL.md reversibility principle. Source: strategic-thinker MIT brief (2026-05-16).\n\n| # | Vector | Question |\n|---|--------|----------|\n| 1 | **Policy** | Does this violate an explicit rule, boundary, or operating constraint? |\n| 2 | **Mechanism** | How could the implementation fail, hang, corrupt state, or be exploited? |\n| 3 | **Assurance** | What cannot be monitored, audited, or verified after the fact? |\n| 4 | **Incentives** | What system or actor benefits from this failing silently? |\n| 5 | **Fragility** | Where are the single points of failure, tight coupling, or cascade paths? |\n| 6 | **Scope creep** | What silent expansion or unapproved scope increase does this permit? |\n| 7 | **Irreversibility** | How hard is rollback if this is wrong? Is there a tested recovery path? |\n\nAdversary prompt injection: for each vector, deliver one finding or \"clean\" — no filler. Total output ≤ 35 lines.\n\n## Quarantine rules\n\nAdvisory output only — no implementation authority. Findings are consolidated for the owner; any resulting change goes through the normal owner-gated commit path.\n\n## Trigger phrases (auto-classify)\n\n- \"architecture review\"\n- \"should we refactor\"\n- \"deployment plan\"\n- \"high stakes\"\n- \"before we ship\"\n\n## Session Notes\n\n### 2026-05-17\n- session: 113m | peak ctx: 0% | compacts: 0\n- tools: Bash×168, Edit×41, Read×33, mcp×33, Write×11, ToolSearch×2, Skill×1, AskUserQuestion×1, ExitPlanMode×1\n- corrections: none\n- errors: none\n\n### 2026-05-16\n- session: 61m | peak ctx: 0% | compacts: 0\n- tools: Bash×50, Edit×28, Write×13, Read×12\n- corrections: none\n- errors: none\n",{"name":5,"scope":33,"triggers":44,"invocation":38,"description":7},[45,25,36,5],"\u002Fshura","main","4c6d8d65f3d6096e2fc25b0845e481dda73c2794","skills\u002Fyuri-shura",0,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions","Building deterministic AI governance and continuity systems. Workflow architect + visual storyteller","2026-11-11 16:42:59",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add nexuslinkproductions\u002Fyuri-os --skill yuri-shura",{"tool":60,"command":61},"bunx","bunx skills add nexuslinkproductions\u002Fyuri-os --skill yuri-shura",{"tool":63,"command":64},"pnpm","pnpm dlx skills add nexuslinkproductions\u002Fyuri-os --skill yuri-shura","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-shura\u002FSKILL.md",true,[],[69,89,119,148,167,192],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":39},"01M71CG1AME5WC0A79AE65WT0X","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-out\u002FSKILL.md",[],[76,77,78,21,79,80,81,82,83,84,33,85,86,87,88,26],"zoom out","zoom","perspective","you","code","it","context","section","re","with","true","understand","how",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":100,"publishedAt":39},"01M71CFTTYW1HA2MNX38EV1GJ5","yuri-sales-intelligence","Unified sales and outreach skill generating cold outreach openers, social selling sequences, objection rebuttals, and ad creative for any paid platform — multi-persona aware, adapting tone and offer frame to buyer type. Use when user says 'write a cold email', 'outreach sequence', 'objection handling', 'ad copy', or 'sales pitch'.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-sales-intelligence\u002FSKILL.md",[95],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",[101,102,103,104,105,106,107,108,109,110,111,112,23,113,114,115,116,117,118,21],"intelligence","sales intelligence","yuri sales intelligence","sales","persona","pitch","social","paid","cold","email","frame","cold outreach","platform","sequence","sequences","write","ad creative","cold email",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":133,"publishedAt":39},"01M71CFQMBFTFADJNGP0Z2WCYK","yuri-code-intelligence","Unified code quality intelligence layer that diagnoses code smells (Long Method, Feature Envy, design pattern issues), prescribes targeted Fowler refactoring techniques, and reviews code for security, performance, and clarity. Use when user says 'review this code', 'refactor this', 'what's wrong with this method', 'code smells', or 'clean this up'.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-code-intelligence\u002FSKILL.md",[125,128],{"categoryNo":126,"categoryName":127,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":129,"categoryName":130,"taxonomyType":131,"taxonomyTypeDesc":132},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[101,134,80,135,21,26,136,137,138,139,140,141,142,143,23,144,145,146,33,147],"code intelligence","yuri code intelligence","design","improve","techniques","clean","issues","long","code review","performance","feature","code quality","reviews","up",{"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":154,"publishedAt":39},"01M71CFP32RT6GD3GKNHCJP8VP","yuri-adw","Invoke when user asks to run the ADW loop \u002F agentic engineering loop \u002F software factory workflow.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-adw\u002FSKILL.md",[],[155,156,38,157,158,159,21,160,161,162,163,164,165,166],"yuri adw","run","user","agentic","engineering","invoke","loop","factory","agentic engineering","software","software factory","engineering loop",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":185,"publishedAt":39},"01M71CFK4VPEKY6A73237P7RSN","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[173,176,179,182],{"categoryNo":174,"categoryName":175,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":177,"categoryName":178,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":180,"categoryName":181,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":183,"categoryName":184,"taxonomyType":131,"taxonomyTypeDesc":132},"01JBSEEDCAT000000000000036","内容创作者",[186,187,188,26,35,189,33,190,38,21,191],"writing skills","writing","Existing","editing","work","new",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":200,"publishedAt":39},"01M71CFGS93M91C0J7SSPXM1NS","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[198,199],{"categoryNo":177,"categoryName":178,"taxonomyType":98,"taxonomyTypeDesc":99},{"categoryNo":183,"categoryName":184,"taxonomyType":131,"taxonomyTypeDesc":132},[187,201,202,203,204,205,206,80,207,79,38,21,26,23,33],"writing plans","plans","spec","multi-step task","multi","task","requirements"]