[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71BTYVS3WAS18T39AT4MCPF":3,"skill-same:01M71BTYVS3WAS18T39AT4MCPF":74},{"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":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":59,"updatedAt":60,"install":61,"resources":73},"01M71BTYVS3WAS18T39AT4MCPF","organ-formula-foundry",null,"Formula Foundry typing Core A — the legal-move generator that classifies formula input\u002Foutput units into closed-set dimensions and rejects dimensionally-incoherent compositions. Use when composing formulas and needing to verify dimensional compatibility, cataloging formula banks, or checking whether one formula's output can legally feed another's input.","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\u002Forgan-formula-foundry\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"organ formula foundry","formula","foundry","do","when","compositions","true","usage","formulas","generator","move","typing","use","catalog","coverage","system","Composition","SET","harness","core","2026-11-10 10:12:30",false,"---\nname: organ-formula-foundry\ndescription: \"Formula Foundry typing Core A — the legal-move generator that classifies formula input\u002Foutput units into closed-set dimensions and rejects dimensionally-incoherent compositions. Use when composing formulas and needing to verify dimensional compatibility, cataloging formula banks, or checking whether one formula's output can legally feed another's input.\"\ntriggers:\n  - \"organ-formula-foundry\"\n  - \"how do I use formula-foundry\"\n  - \"formula-foundry usage\"\n  - \"formula-foundry guide\"\n  - \"Formula Foundry (typing core: catalog + coverage + composition type-algebra)\"\ngenerated: true\nsource_node: \"formula-foundry\"\nsource_file: \"_SYSTEM\u002FScripts\u002Fmath\u002Fformula-foundry.mjs\"\nscope: harness\ninvocation: ability\n---\n\n\u003C!-- GENERATED from the canonical graph node \"formula-foundry\" (mechanism.guide) by _SYSTEM\u002FScripts\u002Fyuri-guide-project.mjs.\n     DO NOT hand-edit — edit _SYSTEM\u002Forgan-guides.json, then run: node _SYSTEM\u002FScripts\u002Fyuri-guide-seed.mjs && node _SYSTEM\u002FScripts\u002Fyuri-guide-project.mjs -->\n\n# Organ Guide — Formula Foundry (typing core: catalog + coverage + composition type-algebra)\n\n**Module:** `_SYSTEM\u002FScripts\u002Fmath\u002Fformula-foundry.mjs` · **Layer:** Energy & Math · **Invocation:** both · **CLI:** `catalog`, `coverage`, `compose`, `composable`, `sequences`, `synth`, `preflight`\n\n**Purpose.** Formula Foundry typing CORE A — the legal-move generator. Reads the typed formula-bank cards, classifies each card's input\u002Foutput UNITS into a deterministic closed-set dimension, and decides whether one formula's output may legally feed another's input. Rejects dimensionally-incoherent compositions (bits→length, probability into an energy slot) — the silent-garbage hole the engine exists to close.\n\n## Exports\n- `classifyDimension(unitText)`\n  - in: a prose unit string (e.g. 'bits', 'joule', 'meters\u002Fsecond')\n  - out: { dimension, witness } — closed-set dimension + the matched witness token (or null)\n- `dimensionsCompatible(a, b)`\n  - in: two dimension strings (from classifyDimension)\n  - out: { compatible, confidence, reason }\n- `catalogFormulas(opts = {})`\n  - in: optional { bankDir }\n  - out: { cards, count, banks, skipped } — unified read-view over the typed formula-banks; corrupt banks are listed in skipped\n- `async coverageReport()`\n  - in: none (reads banks + math-kernel exports)\n  - out: { boundCount, kernelExportCount, unboundPrimitives, orphanCards, cardCount } — the kernel-fn↔bank-card binding worklist\n- `composeCheck(cardA, cardB)`\n  - in: two catalog card objects\n  - out: { legal, compatibleSlots, reasons, from, to, outputDim } — whether A's output may legally feed B\n- `composableTargets(cardA, catalog = null)`\n  - in: one card + optional pre-loaded catalog\n  - out: array of legal downstream targets { to, slots, outputDim }\n- `composeOperatorSequences(catalog = null, opts = {})`\n  - in: optional catalog + { min\u002Fmax chain length, branching, domain filters }\n  - out: { sequences, count, truncated, truncation, params } — enumerated legal operator chains\n- `synthesizeFormulaCandidates(opts = {})`\n  - in: optional catalog + synthesis constraints\n  - out: { candidates, count, truncated } — research-status candidates\n- `draftFormulaBankCard(candidate)`\n  - in: a synthesized candidate\n  - out: a research-status bank card (promotionStatus:'research', advisoryOnly:true, implementedBy:null)\n- `proofPreflightCandidate(card, opts = {})`\n  - in: a draft card + optional overrides\n  - out: { inert, hasBinding, reason, promotionStatus, advisoryOnly, validationOk, validationErrors }\n\n## Security boundary\nREAD-ONLY over the formula-bank files; mints NO production cards. Synthesis output is INERT — promotionStatus:'research', advisoryOnly:true, no kernel binding — and cannot promote until someone binds a real kernel symbol AND a green worked example clears math-proof-gate (Core B). No protected-path access. Deterministic: no RNG, no clock, sorted iteration, closed-set classification.\n\n## When to use\nAuditing math coverage (which kernel primitives are unbound \u002F which cards are orphaned), checking whether two formulas can legally compose, enumerating legal operator chains, or prototyping new formula candidates by dimensional rules. The upstream typing gate before math-proof-gate validates.\n\n## Gotchas\n- Dimension classification is keyword-based over a CLOSED set; short tokens (≤5 chars) require full word boundaries to avoid collisions with ordinary English (F-1 hardening).\n- UNKNOWN dimensions are treated as compatible-by-default (cannot be disproven) — an UNKNOWN slot is not a rejection.\n- Synthesized candidates are INERT and advisory; they NEVER auto-promote — binding + proof-gate is a separate manual step.\n- Corrupt bank files are silently skipped; the only visibility of lost cards is the `skipped` field of catalogFormulas.\n- Generator (synthesize) and scorer (bakeoff) are deliberately separate modules — this core does not grade its own candidates.\n\n## Session Notes\n\n### 2026-06-13\n- session: 40m | peak ctx: 0% | compacts: 0\n- tools: Bash×824, Read×163, Edit×17, StructuredOutput×16, Write×8, TodoWrite×4, ToolSearch×2, ScheduleWakeup×2, Workflow×1, mcp×1, AskUserQuestion×1\n- corrections: none\n- errors: none\n","\u003C!-- GENERATED from the canonical graph node \"formula-foundry\" (mechanism.guide) by _SYSTEM\u002FScripts\u002Fyuri-guide-project.mjs.\n     DO NOT hand-edit — edit _SYSTEM\u002Forgan-guides.json, then run: node _SYSTEM\u002FScripts\u002Fyuri-guide-seed.mjs && node _SYSTEM\u002FScripts\u002Fyuri-guide-project.mjs -->\n\n# Organ Guide — Formula Foundry (typing core: catalog + coverage + composition type-algebra)\n\n**Module:** `_SYSTEM\u002FScripts\u002Fmath\u002Fformula-foundry.mjs` · **Layer:** Energy & Math · **Invocation:** both · **CLI:** `catalog`, `coverage`, `compose`, `composable`, `sequences`, `synth`, `preflight`\n\n**Purpose.** Formula Foundry typing CORE A — the legal-move generator. Reads the typed formula-bank cards, classifies each card's input\u002Foutput UNITS into a deterministic closed-set dimension, and decides whether one formula's output may legally feed another's input. Rejects dimensionally-incoherent compositions (bits→length, probability into an energy slot) — the silent-garbage hole the engine exists to close.\n\n## Exports\n- `classifyDimension(unitText)`\n  - in: a prose unit string (e.g. 'bits', 'joule', 'meters\u002Fsecond')\n  - out: { dimension, witness } — closed-set dimension + the matched witness token (or null)\n- `dimensionsCompatible(a, b)`\n  - in: two dimension strings (from classifyDimension)\n  - out: { compatible, confidence, reason }\n- `catalogFormulas(opts = {})`\n  - in: optional { bankDir }\n  - out: { cards, count, banks, skipped } — unified read-view over the typed formula-banks; corrupt banks are listed in skipped\n- `async coverageReport()`\n  - in: none (reads banks + math-kernel exports)\n  - out: { boundCount, kernelExportCount, unboundPrimitives, orphanCards, cardCount } — the kernel-fn↔bank-card binding worklist\n- `composeCheck(cardA, cardB)`\n  - in: two catalog card objects\n  - out: { legal, compatibleSlots, reasons, from, to, outputDim } — whether A's output may legally feed B\n- `composableTargets(cardA, catalog = null)`\n  - in: one card + optional pre-loaded catalog\n  - out: array of legal downstream targets { to, slots, outputDim }\n- `composeOperatorSequences(catalog = null, opts = {})`\n  - in: optional catalog + { min\u002Fmax chain length, branching, domain filters }\n  - out: { sequences, count, truncated, truncation, params } — enumerated legal operator chains\n- `synthesizeFormulaCandidates(opts = {})`\n  - in: optional catalog + synthesis constraints\n  - out: { candidates, count, truncated } — research-status candidates\n- `draftFormulaBankCard(candidate)`\n  - in: a synthesized candidate\n  - out: a research-status bank card (promotionStatus:'research', advisoryOnly:true, implementedBy:null)\n- `proofPreflightCandidate(card, opts = {})`\n  - in: a draft card + optional overrides\n  - out: { inert, hasBinding, reason, promotionStatus, advisoryOnly, validationOk, validationErrors }\n\n## Security boundary\nREAD-ONLY over the formula-bank files; mints NO production cards. Synthesis output is INERT — promotionStatus:'research', advisoryOnly:true, no kernel binding — and cannot promote until someone binds a real kernel symbol AND a green worked example clears math-proof-gate (Core B). No protected-path access. Deterministic: no RNG, no clock, sorted iteration, closed-set classification.\n\n## When to use\nAuditing math coverage (which kernel primitives are unbound \u002F which cards are orphaned), checking whether two formulas can legally compose, enumerating legal operator chains, or prototyping new formula candidates by dimensional rules. The upstream typing gate before math-proof-gate validates.\n\n## Gotchas\n- Dimension classification is keyword-based over a CLOSED set; short tokens (≤5 chars) require full word boundaries to avoid collisions with ordinary English (F-1 hardening).\n- UNKNOWN dimensions are treated as compatible-by-default (cannot be disproven) — an UNKNOWN slot is not a rejection.\n- Synthesized candidates are INERT and advisory; they NEVER auto-promote — binding + proof-gate is a separate manual step.\n- Corrupt bank files are silently skipped; the only visibility of lost cards is the `skipped` field of catalogFormulas.\n- Generator (synthesize) and scorer (bakeoff) are deliberately separate modules — this core does not grade its own candidates.\n\n## Session Notes\n\n### 2026-06-13\n- session: 40m | peak ctx: 0% | compacts: 0\n- tools: Bash×824, Read×163, Edit×17, StructuredOutput×16, Write×8, TodoWrite×4, ToolSearch×2, ScheduleWakeup×2, Workflow×1, mcp×1, AskUserQuestion×1\n- corrections: none\n- errors: none\n",{"name":5,"scope":37,"triggers":44,"generated":49,"invocation":50,"description":7,"source_file":51,"source_node":52},[5,45,46,47,48],"how do I use formula-foundry","formula-foundry usage","formula-foundry guide","Formula Foundry (typing core: catalog + coverage + composition type-algebra)",true,"ability","_SYSTEM\u002FScripts\u002Fmath\u002Fformula-foundry.mjs","formula-foundry","main","4c6d8d65f3d6096e2fc25b0845e481dda73c2794",".claude\u002Fskills\u002Forgan-formula-foundry",0,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions","Building deterministic AI governance and continuity systems. Workflow architect + visual storyteller","2026-10-27 02:18:29",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":49},[63,66,69],{"tool":64,"command":65},"npx","npx skills add nexuslinkproductions\u002Fyuri-os --skill organ-formula-foundry",{"tool":67,"command":68},"bunx","bunx skills add nexuslinkproductions\u002Fyuri-os --skill organ-formula-foundry",{"tool":70,"command":71},"pnpm","pnpm dlx skills add nexuslinkproductions\u002Fyuri-os --skill organ-formula-foundry","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Forgan-formula-foundry\u002FSKILL.md",[],[75,94,118,148,177,196],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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",[],[82,83,84,37,85,86,87,25,88,31,89,23,90,91,92,93],"zoom out","zoom","with","how","section","re","understand","perspective","you","code","it","context",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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",[],[101,102,37,103,104,105,106,107,108,109,110,31,111,23,112,113,114,115,116,117],"yuri shura","parallel","architecture review","planning","for","deployment","vector","strategic review","decision","strategic","ops","workflow","decisions","architecture","review","perspectives","adversarial",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":129,"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",[124],{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",[130,131,132,133,134,135,136,137,138,23,139,140,141,142,143,144,145,105,146,147],"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":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":162,"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",[154,157],{"categoryNo":155,"categoryName":156,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":158,"categoryName":159,"taxonomyType":160,"taxonomyTypeDesc":161},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[163,91,164,130,37,165,166,167,105,168,169,170,171,172,173,174,175,176,31,23],"yuri code intelligence","code intelligence","reviews","code quality","feature","performance","code review","long","up","issues","clean","techniques","improve","design",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"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",[],[184,185,186,187,188,189,190,191,192,23,193,112,194,195],"yuri adw","run","engineering loop","software factory","software","agentic engineering","factory","loop","invoke","engineering","agentic","user",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":214,"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",[202,205,208,211],{"categoryNo":203,"categoryName":204,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":206,"categoryName":207,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":209,"categoryName":210,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":212,"categoryName":213,"taxonomyType":160,"taxonomyTypeDesc":161},"01JBSEEDCAT000000000000036","内容创作者",[215,216,217,23,112,218,37,219,106,31,220],"writing","writing skills","new","work","editing","Existing"]