[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71BVPPS1X8ZS2MQ3PW4BDCE":3,"skill-same:01M71BVPPS1X8ZS2MQ3PW4BDCE":73},{"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":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M71BVPPS1X8ZS2MQ3PW4BDCE","plan-review",null,"Optional human-in-the-loop (HITL) plan\u002Fdiff review sublane — capture a plan, annotate it, ship structured feedback, and diff plan revisions. Mutually exclusive with the autonomous plan_dispatch_gate. AUTO-BLOCKS the next mutation with a reason until the plan is approved (review mode only, default OFF). Use when a human needs to review or annotate an agent plan before dispatch.","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\u002Fplan-review\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"plan","plan review","review","harness","annotation","ship","my","human","next","workflow","when","loop","mutation","auto","autonomous","only","default","annotate","mode","plan gate","2026-11-10 10:12:30",false,"---\nname: plan-review\ndescription: Optional human-in-the-loop (HITL) plan\u002Fdiff review sublane — capture a plan, annotate it, ship structured feedback, and diff plan revisions. Mutually exclusive with the autonomous plan_dispatch_gate. AUTO-BLOCKS the next mutation with a reason until the plan is approved (review mode only, default OFF). Use when a human needs to review or annotate an agent plan before dispatch.\ntriggers:\n  - \u002Fplan-review\n  - human review plan\n  - plan annotation\n  - HITL plan gate\n  - review my plan before dispatch\n  - diff plan revisions\nscope: harness\ninvocation: workflow\n---\n\n# plan-review — Human-in-the-loop plan\u002Fdiff review sublane\n\nOPTIONAL HITL surface. Capture an agent plan, let a human annotate it, ship structured feedback back, and compute a Plan-Diff across resubmissions. Clean-room re-imagining of the plan-annotation idea (github-adoption 2026-06-13, `human-review-sublane`) — no external code copied.\n\n## Posture (read this first)\n\n- **AUTO-BLOCK (owner decision 2026-06-13, Marcel \"auto block with a reason provided\").** When plan-review mode is ON, the PreToolUse guard DENIES the next post-`ExitPlanMode` mutation, with a reason, until the plan is reviewed and approved (a changes-requested verdict keeps the block). Hard gate; requires `CLAUDE_SESSION_ID` (else degrades to WARN); a long TTL failsafe prevents a forgotten review-mode from wedging the session. Fires ONLY in review mode (default OFF), so autonomous sessions are unaffected.\n- **Mutual exclusion (load-bearing safety invariant).** Plan-review mode and the autonomous `plan_dispatch_gate` NEVER both fire on the same `ExitPlanMode` event. The mode toggle is the single source of truth; the PostToolUse arm site + the two PreToolUse gate-eval sites all exclude off `isPlanReviewMode()`.\n- **Fail-loud toggle.** `on`\u002F`off` MUST fail loud on null\u002Fcorrupt\u002Fmissing session-state (exit nonzero + stderr + read-back verify) — never a silent no-op.\n\n## CLI\n\n```bash\n# Toggle HITL plan-review mode (fail-loud; exits nonzero on bad state)\nnode _SYSTEM\u002FScripts\u002Fplan-review.mjs on\nnode _SYSTEM\u002FScripts\u002Fplan-review.mjs off\nnode _SYSTEM\u002FScripts\u002Fplan-review.mjs status\n\n# Capture a plan revision (auto-increments revision number)\nnode _SYSTEM\u002FScripts\u002Fplan-review.mjs capture \"\u003Cplan-id>\" \"plan text here\"\necho \"plan text\" | node _SYSTEM\u002FScripts\u002Fplan-review.mjs capture \"\u003Cplan-id>\"\n\n# Plan-Diff across two stored revisions (LCS, scale-capped)\nnode _SYSTEM\u002FScripts\u002Fplan-review.mjs diff \"\u003Cplan-id>\" 0 1\n```\n\nProgrammatic: `import { isPlanReviewMode, setPlanReviewMode, capturePlan, annotatePlan, computePlanDiff, buildResultLabel } from '_SYSTEM\u002FScripts\u002Fplan-review.mjs'`.\n\n## When to reach for it\n\n- A human wants to review\u002Fannotate an agent plan before any mutation is dispatched.\n- You want a recorded Plan-Diff showing what actually changed between plan resubmissions.\n- You want to GATE the autonomous dispatch loop with a human checkpoint (blocks the next mutation until you approve) instead of the route-plan auto-dispatch.\n\nDo NOT reach for it for routine autonomous work — leave the mode OFF and the existing `plan_dispatch_gate` flow runs unchanged.\n\n## RESULT_LABEL\n\nEmits a BARE Lane Result Grammar label: `09PR_PLAN_REVIEW_\u003Cverb>_\u003CX|P|F>_\u003CPASS_COMMITTED|BLOCKED>`. X\u002FP use `PASS_COMMITTED`; F uses `BLOCKED`.\n\n## Session Notes\n\n### 2026-06-13\n- session: 24m | peak ctx: 54% | compacts: 0\n- tools: Bash×129, Write×56, Read×56, Edit×39, StructuredOutput×6, Agent×5, TodoWrite×5, TaskUpdate×2, Workflow×1\n- corrections: Base directory for this skill: \u002FUsers\u002Fmarcelspatz\u002F.claude\u002Fskills\u002Fcross-reference-navigation\n\n# Cross-Reference Navigation (XREF)\n\nThe GROUND step of the work loop, made reflexive. One question asked a | Base directory for this skill: \u002FUsers\u002Fmarcelspatz\u002F.claude\u002Fskills\u002Fquantum-hypothesis-simulation\n\n# Quantum Hypothesis Simulation\n\nThe quantum-probability layer for YURI's claim\u002Fpulse machinery. It mode\n- errors: none\n","# plan-review — Human-in-the-loop plan\u002Fdiff review sublane\n\nOPTIONAL HITL surface. Capture an agent plan, let a human annotate it, ship structured feedback back, and compute a Plan-Diff across resubmissions. Clean-room re-imagining of the plan-annotation idea (github-adoption 2026-06-13, `human-review-sublane`) — no external code copied.\n\n## Posture (read this first)\n\n- **AUTO-BLOCK (owner decision 2026-06-13, Marcel \"auto block with a reason provided\").** When plan-review mode is ON, the PreToolUse guard DENIES the next post-`ExitPlanMode` mutation, with a reason, until the plan is reviewed and approved (a changes-requested verdict keeps the block). Hard gate; requires `CLAUDE_SESSION_ID` (else degrades to WARN); a long TTL failsafe prevents a forgotten review-mode from wedging the session. Fires ONLY in review mode (default OFF), so autonomous sessions are unaffected.\n- **Mutual exclusion (load-bearing safety invariant).** Plan-review mode and the autonomous `plan_dispatch_gate` NEVER both fire on the same `ExitPlanMode` event. The mode toggle is the single source of truth; the PostToolUse arm site + the two PreToolUse gate-eval sites all exclude off `isPlanReviewMode()`.\n- **Fail-loud toggle.** `on`\u002F`off` MUST fail loud on null\u002Fcorrupt\u002Fmissing session-state (exit nonzero + stderr + read-back verify) — never a silent no-op.\n\n## CLI\n\n```bash\n# Toggle HITL plan-review mode (fail-loud; exits nonzero on bad state)\nnode _SYSTEM\u002FScripts\u002Fplan-review.mjs on\nnode _SYSTEM\u002FScripts\u002Fplan-review.mjs off\nnode _SYSTEM\u002FScripts\u002Fplan-review.mjs status\n\n# Capture a plan revision (auto-increments revision number)\nnode _SYSTEM\u002FScripts\u002Fplan-review.mjs capture \"\u003Cplan-id>\" \"plan text here\"\necho \"plan text\" | node _SYSTEM\u002FScripts\u002Fplan-review.mjs capture \"\u003Cplan-id>\"\n\n# Plan-Diff across two stored revisions (LCS, scale-capped)\nnode _SYSTEM\u002FScripts\u002Fplan-review.mjs diff \"\u003Cplan-id>\" 0 1\n```\n\nProgrammatic: `import { isPlanReviewMode, setPlanReviewMode, capturePlan, annotatePlan, computePlanDiff, buildResultLabel } from '_SYSTEM\u002FScripts\u002Fplan-review.mjs'`.\n\n## When to reach for it\n\n- A human wants to review\u002Fannotate an agent plan before any mutation is dispatched.\n- You want a recorded Plan-Diff showing what actually changed between plan resubmissions.\n- You want to GATE the autonomous dispatch loop with a human checkpoint (blocks the next mutation until you approve) instead of the route-plan auto-dispatch.\n\nDo NOT reach for it for routine autonomous work — leave the mode OFF and the existing `plan_dispatch_gate` flow runs unchanged.\n\n## RESULT_LABEL\n\nEmits a BARE Lane Result Grammar label: `09PR_PLAN_REVIEW_\u003Cverb>_\u003CX|P|F>_\u003CPASS_COMMITTED|BLOCKED>`. X\u002FP use `PASS_COMMITTED`; F uses `BLOCKED`.\n\n## Session Notes\n\n### 2026-06-13\n- session: 24m | peak ctx: 54% | compacts: 0\n- tools: Bash×129, Write×56, Read×56, Edit×39, StructuredOutput×6, Agent×5, TodoWrite×5, TaskUpdate×2, Workflow×1\n- corrections: Base directory for this skill: \u002FUsers\u002Fmarcelspatz\u002F.claude\u002Fskills\u002Fcross-reference-navigation\n\n# Cross-Reference Navigation (XREF)\n\nThe GROUND step of the work loop, made reflexive. One question asked a | Base directory for this skill: \u002FUsers\u002Fmarcelspatz\u002F.claude\u002Fskills\u002Fquantum-hypothesis-simulation\n\n# Quantum Hypothesis Simulation\n\nThe quantum-probability layer for YURI's claim\u002Fpulse machinery. It mode\n- errors: none\n",{"name":5,"scope":22,"triggers":44,"invocation":28,"description":7},[45,46,47,48,49,50],"\u002Fplan-review","human review plan","plan annotation","HITL plan gate","review my plan before dispatch","diff plan revisions","main","4c6d8d65f3d6096e2fc25b0845e481dda73c2794",".claude\u002Fskills\u002Fplan-review",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":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add nexuslinkproductions\u002Fyuri-os --skill plan-review",{"tool":65,"command":66},"bunx","bunx skills add nexuslinkproductions\u002Fyuri-os --skill plan-review",{"tool":68,"command":69},"pnpm","pnpm dlx skills add nexuslinkproductions\u002Fyuri-os --skill plan-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fplan-review\u002FSKILL.md",true,[],[74,95,117,147,176,194],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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",[],[81,82,83,22,84,85,86,87,88,89,90,29,91,92,93,94],"zoom out","zoom","with","how","section","re","true","understand","use","perspective","you","code","it","context",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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",[],[102,103,22,104,105,106,107,108,109,110,111,89,112,29,28,113,114,21,115,116],"yuri shura","parallel","architecture review","planning","for","deployment","vector","strategic review","decision","strategic","ops","decisions","architecture","perspectives","adversarial",{"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":128,"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",[123],{"categoryNo":124,"categoryName":125,"taxonomyType":126,"taxonomyTypeDesc":127},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",[129,130,131,132,133,134,135,136,137,29,138,139,140,141,142,143,144,106,145,146],"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":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":161,"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",[153,156],{"categoryNo":154,"categoryName":155,"taxonomyType":126,"taxonomyTypeDesc":127},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":157,"categoryName":158,"taxonomyType":159,"taxonomyTypeDesc":160},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[162,92,163,129,22,164,165,166,106,167,168,169,170,171,172,173,174,175,89,29],"yuri code intelligence","code intelligence","reviews","code quality","feature","performance","code review","long","up","issues","clean","techniques","improve","design",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"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",[],[183,184,185,186,187,188,189,30,190,29,191,28,192,193],"yuri adw","run","engineering loop","software factory","software","agentic engineering","factory","invoke","engineering","agentic","user",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":212,"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",[200,203,206,209],{"categoryNo":201,"categoryName":202,"taxonomyType":126,"taxonomyTypeDesc":127},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":204,"categoryName":205,"taxonomyType":126,"taxonomyTypeDesc":127},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":207,"categoryName":208,"taxonomyType":126,"taxonomyTypeDesc":127},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":210,"categoryName":211,"taxonomyType":159,"taxonomyTypeDesc":160},"01JBSEEDCAT000000000000036","内容创作者",[213,214,215,29,28,216,22,217,107,89,218],"writing","writing skills","new","work","editing","Existing"]