[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71AC0N5ZJCEQ17NQWTC179R":3,"skill-same:01M71AC0N5ZJCEQ17NQWTC179R":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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M71AC0N5ZJCEQ17NQWTC179R","adversarial-verification",null,"Use when verifying completed work, reviewing Claude or Codex output, wiring routes or adapters, relaunching lanes, committing, pushing, or avoiding first-run confidence.","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\u002F.claude\u002Fskills\u002Fadversarial-verification\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"verification","adversarial verification","adversarial","harness","work","first","codex","verify","run","Adapters","use","when","workflow","wiring","output","2026-11-10 10:12:30",false,"---\nname: adversarial-verification\ndescription: Use when verifying completed work, reviewing Claude or Codex output, wiring routes or adapters, relaunching lanes, committing, pushing, or avoiding first-run confidence.\ntriggers: [\"adversarial verification\", \"attack your own output\", \"verify completed work\"]\nscope: harness\ninvocation: workflow\n---\n\n# Adversarial Verification\n\nFirst-run success is a hypothesis, not proof. The job is not done until the work survives a skeptical pass.\n\n## Use When\n\n- about to claim work is complete, fixed, wired, safe, or ready\n- reviewing Claude, Codex, DeepSeek, or other agent output\n- changing skills, routing, registries, permissions, launch packets, adapters, or parsers\n- preparing a commit, push, relaunch, demo, or handoff\n- the user asks to attack, stress test, double-check, verify, or stop trusting first output\n\n## Attack Loop\n\n1. State the claim being tested and the blast radius.\n2. List likely failure modes: cosmetic-only change, wrong path, stale lane, missing registry entry, bad permissions, protected-path leak, live-service risk, unrelated staged changes, false-positive test.\n3. Run positive checks that prove the intended path works.\n4. Run negative or mismatch checks when the change has routing, parsing, permission, adapter, or policy behavior.\n5. Independently verify collaborator output from local evidence; agent success reports are proposals.\n6. Inspect changed\u002Fstaged scope and protected surfaces before commit, push, or relaunch.\n7. Report what failed first, what was fixed, the exact checks run, and residual risk.\n\n## Minimum Evidence\n\n- code\u002Fconfig change: syntax or targeted test plus diff scope\n- route\u002Fskill\u002Fregistry change: validation plus recommender\u002Factivation check\n- permission\u002Foutput-lane change: one accepted packet and one rejected mismatch\n- moved\u002Fimported tree: source absence, destination presence, file count, protected-surface scan\n- Claude output: local file\u002Fdiff\u002Ftest evidence, not Claude's wording\n- commit\u002Fpush: staged scope, protected-path scan, GitNexus change detection when applicable\n\n## Stop Conditions\n\nStop and say so when no deterministic check exists, when the negative case unexpectedly passes, when staged scope includes unrelated work, or when a required check needs credentials\u002Flive services that are out of scope.\n\nNo \"looks good\" shortcut. Evidence first, then the claim.\n\n## Session Notes\n\n### 2026-07-05\n- session: 117m | peak ctx: 0% | compacts: 0\n- tools: TaskCreate×505, Bash×119, Read×109, TaskUpdate×8, WebSearch×8, TaskOutput×6, StructuredOutput×4, Write×4, Agent×3, Workflow×2, AskUserQuestion×1\n- corrections: none\n- errors: none\n\n### 2026-06-02\n- session: 196m | peak ctx: 0% | compacts: 0\n- tools: Bash×101, WebSearch×68, WebFetch×67, Read×45, StructuredOutput×18, ToolSearch×13, Write×11, Edit×7, TodoWrite×5, mcp×4, Workflow×3\n- corrections: none\n- errors: none\n\n### 2026-05-29\n- session: 349m | peak ctx: 71% | compacts: 4\n- tools: Bash×268, Read×133, Edit×104, TodoWrite×12, Write×8, StructuredOutput×8, Workflow×2, ToolSearch×1, AskUserQuestion×1\n- corrections: none\n- errors: none\n","# Adversarial Verification\n\nFirst-run success is a hypothesis, not proof. The job is not done until the work survives a skeptical pass.\n\n## Use When\n\n- about to claim work is complete, fixed, wired, safe, or ready\n- reviewing Claude, Codex, DeepSeek, or other agent output\n- changing skills, routing, registries, permissions, launch packets, adapters, or parsers\n- preparing a commit, push, relaunch, demo, or handoff\n- the user asks to attack, stress test, double-check, verify, or stop trusting first output\n\n## Attack Loop\n\n1. State the claim being tested and the blast radius.\n2. List likely failure modes: cosmetic-only change, wrong path, stale lane, missing registry entry, bad permissions, protected-path leak, live-service risk, unrelated staged changes, false-positive test.\n3. Run positive checks that prove the intended path works.\n4. Run negative or mismatch checks when the change has routing, parsing, permission, adapter, or policy behavior.\n5. Independently verify collaborator output from local evidence; agent success reports are proposals.\n6. Inspect changed\u002Fstaged scope and protected surfaces before commit, push, or relaunch.\n7. Report what failed first, what was fixed, the exact checks run, and residual risk.\n\n## Minimum Evidence\n\n- code\u002Fconfig change: syntax or targeted test plus diff scope\n- route\u002Fskill\u002Fregistry change: validation plus recommender\u002Factivation check\n- permission\u002Foutput-lane change: one accepted packet and one rejected mismatch\n- moved\u002Fimported tree: source absence, destination presence, file count, protected-surface scan\n- Claude output: local file\u002Fdiff\u002Ftest evidence, not Claude's wording\n- commit\u002Fpush: staged scope, protected-path scan, GitNexus change detection when applicable\n\n## Stop Conditions\n\nStop and say so when no deterministic check exists, when the negative case unexpectedly passes, when staged scope includes unrelated work, or when a required check needs credentials\u002Flive services that are out of scope.\n\nNo \"looks good\" shortcut. Evidence first, then the claim.\n\n## Session Notes\n\n### 2026-07-05\n- session: 117m | peak ctx: 0% | compacts: 0\n- tools: TaskCreate×505, Bash×119, Read×109, TaskUpdate×8, WebSearch×8, TaskOutput×6, StructuredOutput×4, Write×4, Agent×3, Workflow×2, AskUserQuestion×1\n- corrections: none\n- errors: none\n\n### 2026-06-02\n- session: 196m | peak ctx: 0% | compacts: 0\n- tools: Bash×101, WebSearch×68, WebFetch×67, Read×45, StructuredOutput×18, ToolSearch×13, Write×11, Edit×7, TodoWrite×5, mcp×4, Workflow×3\n- corrections: none\n- errors: none\n\n### 2026-05-29\n- session: 349m | peak ctx: 71% | compacts: 4\n- tools: Bash×268, Read×133, Edit×104, TodoWrite×12, Write×8, StructuredOutput×8, Workflow×2, ToolSearch×1, AskUserQuestion×1\n- corrections: none\n- errors: none\n",{"name":5,"scope":22,"triggers":39,"invocation":31,"description":7},[20,40,41],"attack your own output","verify completed work","main","4c6d8d65f3d6096e2fc25b0845e481dda73c2794",".claude\u002Fskills\u002Fadversarial-verification",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":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add nexuslinkproductions\u002Fyuri-os --skill adversarial-verification",{"tool":56,"command":57},"bunx","bunx skills add nexuslinkproductions\u002Fyuri-os --skill adversarial-verification",{"tool":59,"command":60},"pnpm","pnpm dlx skills add nexuslinkproductions\u002Fyuri-os --skill adversarial-verification","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fadversarial-verification\u002FSKILL.md",true,[],[65,85,107,137,166,184],{"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":71,"publishedAt":34},"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",[],[72,73,74,22,75,76,77,78,79,29,80,30,81,82,83,84],"zoom out","zoom","with","how","section","re","true","understand","perspective","you","code","it","context",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":34},"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",[],[92,93,22,94,95,96,97,98,99,100,101,29,102,30,31,103,104,105,106,21],"yuri shura","parallel","architecture review","planning","for","deployment","vector","strategic review","decision","strategic","ops","decisions","architecture","review","perspectives",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":118,"publishedAt":34},"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",[113],{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",[119,120,121,122,123,124,125,126,127,30,128,129,130,131,132,133,134,96,135,136],"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":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":151,"publishedAt":34},"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",[143,146],{"categoryNo":144,"categoryName":145,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":147,"categoryName":148,"taxonomyType":149,"taxonomyTypeDesc":150},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[152,82,153,119,22,154,155,156,96,157,158,159,160,161,162,163,164,165,29,30],"yuri code intelligence","code intelligence","reviews","code quality","feature","performance","code review","long","up","issues","clean","techniques","improve","design",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":34},"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",[],[173,27,174,175,176,177,178,179,180,30,181,31,182,183],"yuri adw","engineering loop","software factory","software","agentic engineering","factory","loop","invoke","engineering","agentic","user",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":202,"publishedAt":34},"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",[190,193,196,199],{"categoryNo":191,"categoryName":192,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":194,"categoryName":195,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":197,"categoryName":198,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":200,"categoryName":201,"taxonomyType":149,"taxonomyTypeDesc":150},"01JBSEEDCAT000000000000036","内容创作者",[203,204,205,30,31,23,22,206,97,29,207],"writing","writing skills","new","editing","Existing"]