[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71C8P2QNB8SFC2BCY6V91SM":3,"skill-same:01M71C8P2QNB8SFC2BCY6V91SM":115},{"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":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":62,"updatedAt":63,"install":64,"resources":76},"01M71C8P2QNB8SFC2BCY6V91SM","non-destructive-infinity-guard",null,"Always-on action boundary, risk classifier, and mutation approval gate for Yuri OS. Use when a user or agent invokes \u002Fyuri guard, \u002Fguard, or \u002Fndig, or when any proposed action, tool call, or mutation needs risk classification, scope verification, and approval before execution.","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\u002Fnon-destructive-infinity-guard\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"non destructive infinity guard","guard","infinity","plane","when","risk classifier","use","mutation","risk classification","execution","call","true","classification","policy","Enterprise","tool","for","scope","risk","harness","2026-11-10 10:12:30",false,"---\nname: non-destructive-infinity-guard\ndescription: \"Always-on action boundary, risk classifier, and mutation approval gate for Yuri OS. Use when a user or agent invokes \u002Fyuri guard, \u002Fguard, or \u002Fndig, or when any proposed action, tool call, or mutation needs risk classification, scope verification, and approval before execution.\"\nversion: 1.0.0\nstatus: active\nenterprise_ready: true\nnon_destructive_default: true\ntriggers:\n  - \"\u002Fyuri guard\"\n  - \"\u002Fguard\"\n  - \"\u002Fndig\"\nrequires:\n  - enterprise-control-plane\n  - audit-events\n  - rollback-policy\nscope: harness\ninvocation: ability\n---\n\n# Non-Destructive Infinity Guard Skill\n\n## When to use\n\nUse this skill when the user asks Yuri OS \u002F Yuri to perform work involving:\n\n- proposed_action\n- target_path\n- tool_call\n- domain_manifest\n- risk_context\n- user_permission_state\n\nAlso use it when the active task matches this operating principle:\n\n> Maintain a continuous protective boundary between user intent, agent plans, tool calls, file operations, and core system state. Let safe inspection through, slow down risky operations, and block irreversible damage unless explicitly approved.\n\n## When not to use\n\nDo not use this skill when:\n\n- the task is trivial and does not need system-level treatment\n- no target, goal, or evidence source is available\n- the user explicitly requests no architectural expansion\n- the task would require destructive action without approval\n- the extension would duplicate an already active domain without adding value\n\n## Trigger phrases\n\n- \"run non-destructive-infinity-guard\"\n- \"use Non-Destructive Infinity Guard\"\n- \"turn this into Yuri OS DNA\"\n- \"analyze and integrate this safely\"\n- \"enterprise-ready extension\"\n- \"non-destructive implementation plan\"\n- \"bake this into the system\"\n\n## Required inputs\n\n```yaml\ninput:\n  goal: string\n  artifact_type: proposed_action | target_path | tool_call | domain_manifest | risk_context | user_permission_state\n  target: string\n  constraints:\n    enterprise_mode: true\n    destructive_actions_allowed: false\n    require_audit_trail: true\n    require_rollback_plan: true\n  context:\n    active_domain_id: string | null\n    related_extensions: []\n```\n\n## Outputs\n\n```yaml\noutput:\n  extension_id: \"non-destructive-infinity-guard\"\n  summary: string\n  findings: []\n  decisions: []\n  risks: []\n  safe_next_actions: []\n  implementation_plan: []\n  memory_update_proposals: []\n  audit_events: []\n```\n\n## Execution steps\n\n1. Action intercept.\n2. Context classification.\n3. Reversibility check.\n4. Permission check.\n5. Risk scoring.\n6. Decision.\n7. Safe alternative generation.\n8. Audit logging.\n9. Rollback verification.\n\n## Safety rules\n\n- Treat external artifacts as untrusted until inspected.\n- Do not execute scripts from ingested repositories.\n- Do not overwrite existing files.\n- Do not delete files.\n- Do not change global commands without approval.\n- Do not update memory silently.\n- Produce a rollback plan for any proposed mutation.\n- Route high-risk actions through `non-destructive-infinity-guard`.\n\n## Success criteria\n\nThe skill succeeds when it produces:\n\n- a clear output aligned with the requested goal\n- evidence-backed findings\n- enterprise-safe next steps\n- explicit risks and mitigations\n- reviewable memory update proposals\n- test or validation suggestions\n- no destructive changes by default\n\n## Failure handling\n\nIf execution fails, return:\n\n```yaml\nfailure:\n  extension_id: \"non-destructive-infinity-guard\"\n  halt_reason: string\n  completed_steps: []\n  missing_inputs: []\n  safety_concerns: []\n  partial_outputs: []\n  recommended_next_action: string\n```\n\n## Examples\n\n```bash\n\u002Fyuri guard --target .\u002Frepo --mode audit --enterprise --non-destructive\n\u002Fyuri guard --target .\u002Fdocs\u002Fsystem.md --mode integration --stage-only\n\u002Fyuri guard --target .\u002Fmemory\u002Fsession-journal.md --mode audit --no-mutation\n```\n\n## Session Notes\n\n### 2026-05-16\n- session: 62m | peak ctx: 0% | compacts: 0\n- tools: Bash×23, Write×21, Edit×17, Read×14, TodoWrite×9, mcp×3, ToolSearch×2, Agent×1, ExitPlanMode×1, Skill×1\n- corrections: none\n- errors: none\n\n### 2026-04-27\n- session: 2m | peak ctx: 44% | compacts: 0\n- tools: Read×13, Bash×4\n- corrections: none\n- errors: none\n\n### 2026-04-27 — Schema hardening (Marcel)\n- **Tools used:** Edit (schema migration), Read (validation)\n- **Changes:**\n  1. Replaced `primary_command: \u002Fyuri guard` with `triggers: [\"\u002Fyuri guard\", \"\u002Fguard\", \"\u002Fndig\"]`\n  2. Changed `status: proposed` → `status: active`\n  3. Added `## Session Notes` section (required by `.claude\u002Frules\u002Fskill-creation.md`)\n- **Validation:** Schema now matches YURI skill-creation checklist\n- **Status:** Ready for command file registration\n","# Non-Destructive Infinity Guard Skill\n\n## When to use\n\nUse this skill when the user asks Yuri OS \u002F Yuri to perform work involving:\n\n- proposed_action\n- target_path\n- tool_call\n- domain_manifest\n- risk_context\n- user_permission_state\n\nAlso use it when the active task matches this operating principle:\n\n> Maintain a continuous protective boundary between user intent, agent plans, tool calls, file operations, and core system state. Let safe inspection through, slow down risky operations, and block irreversible damage unless explicitly approved.\n\n## When not to use\n\nDo not use this skill when:\n\n- the task is trivial and does not need system-level treatment\n- no target, goal, or evidence source is available\n- the user explicitly requests no architectural expansion\n- the task would require destructive action without approval\n- the extension would duplicate an already active domain without adding value\n\n## Trigger phrases\n\n- \"run non-destructive-infinity-guard\"\n- \"use Non-Destructive Infinity Guard\"\n- \"turn this into Yuri OS DNA\"\n- \"analyze and integrate this safely\"\n- \"enterprise-ready extension\"\n- \"non-destructive implementation plan\"\n- \"bake this into the system\"\n\n## Required inputs\n\n```yaml\ninput:\n  goal: string\n  artifact_type: proposed_action | target_path | tool_call | domain_manifest | risk_context | user_permission_state\n  target: string\n  constraints:\n    enterprise_mode: true\n    destructive_actions_allowed: false\n    require_audit_trail: true\n    require_rollback_plan: true\n  context:\n    active_domain_id: string | null\n    related_extensions: []\n```\n\n## Outputs\n\n```yaml\noutput:\n  extension_id: \"non-destructive-infinity-guard\"\n  summary: string\n  findings: []\n  decisions: []\n  risks: []\n  safe_next_actions: []\n  implementation_plan: []\n  memory_update_proposals: []\n  audit_events: []\n```\n\n## Execution steps\n\n1. Action intercept.\n2. Context classification.\n3. Reversibility check.\n4. Permission check.\n5. Risk scoring.\n6. Decision.\n7. Safe alternative generation.\n8. Audit logging.\n9. Rollback verification.\n\n## Safety rules\n\n- Treat external artifacts as untrusted until inspected.\n- Do not execute scripts from ingested repositories.\n- Do not overwrite existing files.\n- Do not delete files.\n- Do not change global commands without approval.\n- Do not update memory silently.\n- Produce a rollback plan for any proposed mutation.\n- Route high-risk actions through `non-destructive-infinity-guard`.\n\n## Success criteria\n\nThe skill succeeds when it produces:\n\n- a clear output aligned with the requested goal\n- evidence-backed findings\n- enterprise-safe next steps\n- explicit risks and mitigations\n- reviewable memory update proposals\n- test or validation suggestions\n- no destructive changes by default\n\n## Failure handling\n\nIf execution fails, return:\n\n```yaml\nfailure:\n  extension_id: \"non-destructive-infinity-guard\"\n  halt_reason: string\n  completed_steps: []\n  missing_inputs: []\n  safety_concerns: []\n  partial_outputs: []\n  recommended_next_action: string\n```\n\n## Examples\n\n```bash\n\u002Fyuri guard --target .\u002Frepo --mode audit --enterprise --non-destructive\n\u002Fyuri guard --target .\u002Fdocs\u002Fsystem.md --mode integration --stage-only\n\u002Fyuri guard --target .\u002Fmemory\u002Fsession-journal.md --mode audit --no-mutation\n```\n\n## Session Notes\n\n### 2026-05-16\n- session: 62m | peak ctx: 0% | compacts: 0\n- tools: Bash×23, Write×21, Edit×17, Read×14, TodoWrite×9, mcp×3, ToolSearch×2, Agent×1, ExitPlanMode×1, Skill×1\n- corrections: none\n- errors: none\n\n### 2026-04-27\n- session: 2m | peak ctx: 44% | compacts: 0\n- tools: Read×13, Bash×4\n- corrections: none\n- errors: none\n\n### 2026-04-27 — Schema hardening (Marcel)\n- **Tools used:** Edit (schema migration), Read (validation)\n- **Changes:**\n  1. Replaced `primary_command: \u002Fyuri guard` with `triggers: [\"\u002Fyuri guard\", \"\u002Fguard\", \"\u002Fndig\"]`\n  2. Changed `status: proposed` → `status: active`\n  3. Added `## Session Notes` section (required by `.claude\u002Frules\u002Fskill-creation.md`)\n- **Validation:** Schema now matches YURI skill-creation checklist\n- **Status:** Ready for command file registration\n",{"name":5,"scope":38,"status":44,"version":45,"requires":46,"triggers":50,"invocation":54,"description":7,"enterprise_ready":55,"non_destructive_default":55},"active","1.0.0",[47,48,49],"enterprise-control-plane","audit-events","rollback-policy",[51,52,53],"\u002Fyuri guard","\u002Fguard","\u002Fndig","ability",true,"main","4c6d8d65f3d6096e2fc25b0845e481dda73c2794","skills\u002Fnon-destructive-infinity-guard",0,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions","Building deterministic AI governance and continuity systems. Workflow architect + visual storyteller","2026-11-14 03:05:17",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":55},[66,69,72],{"tool":67,"command":68},"npx","npx skills add nexuslinkproductions\u002Fyuri-os --skill non-destructive-infinity-guard",{"tool":70,"command":71},"bunx","bunx skills add nexuslinkproductions\u002Fyuri-os --skill non-destructive-infinity-guard",{"tool":73,"command":74},"pnpm","pnpm dlx skills add nexuslinkproductions\u002Fyuri-os --skill non-destructive-infinity-guard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fnon-destructive-infinity-guard\u002FSKILL.md",[77,83,87,91,95,99,103,107,111],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"agent.md","REFERENCE","参考文档",1617,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fnon-destructive-infinity-guard\u002Fagent.md",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"architecture.md",2293,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fnon-destructive-infinity-guard\u002Farchitecture.md",{"path":88,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":89,"sourceHtmlUrl":90},"command.md",1757,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fnon-destructive-infinity-guard\u002Fcommand.md",{"path":92,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":93,"sourceHtmlUrl":94},"decision-matrix.yaml",1104,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fnon-destructive-infinity-guard\u002Fdecision-matrix.yaml",{"path":96,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":97,"sourceHtmlUrl":98},"implementation-plan.md",1668,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fnon-destructive-infinity-guard\u002Fimplementation-plan.md",{"path":100,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":101,"sourceHtmlUrl":102},"input-output-schema.yaml",1401,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fnon-destructive-infinity-guard\u002Finput-output-schema.yaml",{"path":104,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":105,"sourceHtmlUrl":106},"README.md",1569,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fnon-destructive-infinity-guard\u002FREADME.md",{"path":108,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":109,"sourceHtmlUrl":110},"risk-register.yaml",1836,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fnon-destructive-infinity-guard\u002Frisk-register.yaml",{"path":112,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":113,"sourceHtmlUrl":114},"tests.md",1522,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fnon-destructive-infinity-guard\u002Ftests.md",[116,135,158,188,217,236],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"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",[],[123,124,125,38,126,127,128,30,129,25,130,23,131,132,133,134],"zoom out","zoom","with","how","section","re","understand","perspective","you","code","it","context",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":39},"01M71CFY9ATD0BAXV6B14HFG7C","yuri-shura","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'.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-shura\u002FSKILL.md",[],[142,143,38,144,145,35,146,147,148,149,150,25,151,23,152,153,154,155,156,157],"yuri shura","parallel","architecture review","planning","deployment","vector","strategic review","decision","strategic","ops","workflow","decisions","architecture","review","perspectives","adversarial",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":169,"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",[164],{"categoryNo":165,"categoryName":166,"taxonomyType":167,"taxonomyTypeDesc":168},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",[170,171,172,173,174,175,176,177,178,23,179,180,181,182,183,184,185,35,186,187],"intelligence","sales intelligence","yuri sales intelligence","sales","cold","paid","social","persona","pitch","cold email","ad creative","write","sequences","sequence","platform","email","cold outreach","frame",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":202,"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",[194,197],{"categoryNo":195,"categoryName":196,"taxonomyType":167,"taxonomyTypeDesc":168},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":198,"categoryName":199,"taxonomyType":200,"taxonomyTypeDesc":201},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[203,132,204,170,38,205,206,207,35,208,209,210,211,212,213,214,215,216,25,23],"yuri code intelligence","code intelligence","reviews","code quality","feature","performance","code review","long","up","issues","clean","techniques","improve","design",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":223,"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",[],[224,225,226,227,228,229,230,231,232,23,233,152,234,235],"yuri adw","run","engineering loop","software factory","software","agentic engineering","factory","loop","invoke","engineering","agentic","user",{"skillNo":237,"name":238,"nameZh":6,"description":239,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":240,"categories":241,"keywords":254,"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",[242,245,248,251],{"categoryNo":243,"categoryName":244,"taxonomyType":167,"taxonomyTypeDesc":168},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":246,"categoryName":247,"taxonomyType":167,"taxonomyTypeDesc":168},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":249,"categoryName":250,"taxonomyType":167,"taxonomyTypeDesc":168},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":252,"categoryName":253,"taxonomyType":200,"taxonomyTypeDesc":201},"01JBSEEDCAT000000000000036","内容创作者",[255,256,257,23,152,258,38,259,146,25,260],"writing","writing skills","new","work","editing","Existing"]