[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71C6VRVZAEVSP6CCTG3HV6M":3,"skill-same:01M71C6VRVZAEVSP6CCTG3HV6M":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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M71C6VRVZAEVSP6CCTG3HV6M","haki-intent",null,"Intent Pre-cognition Engine — builds a probability-ranked map of the 5 most likely underlying intents, surfacing hidden constraints (P4) and meta-needs (P5). Use when a request's true intent is ambiguous or high-stakes, or when the user invokes \u002Fhaki.","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\u002Fhaki-intent\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"haki intent","intent","constraints","user","cognition","ambiguous","intents","hidden","request","high","engine","probability","workflow","when","use","map","true","Meta","harness","2026-11-10 10:12:30",false,"---\nname: haki-intent\ndescription: \"Intent Pre-cognition Engine — builds a probability-ranked map of the 5 most likely underlying intents, surfacing hidden constraints (P4) and meta-needs (P5). Use when a request's true intent is ambiguous or high-stakes, or when the user invokes \u002Fhaki.\"\ntriggers:\n  - \u002Fhaki\n  - \u002Fyuri-haki\nscope: harness\ninvocation: workflow\n---\n\n# Haki (覇気) — Intent Pre-cognition Engine\n\n**Source anime:** One Piece — Observation Haki (Kenbunshoku Haki) lets the user feel the presence, emotions, and future movements of others before they happen. Conqueror's Haki (Haōshoku Haki) bends weaker wills without force.\n\n**Cognitive translation:** On every non-trivial turn, Musubi builds a probability-ranked map of the 5 most likely underlying intents behind the literal request. The literal words are the surface; Haki reads the intent beneath. This map enriches the prompt before any advisor or ensemble fires — so the answer addresses what Marcel actually needs, not just what was typed.\n\n---\n\n## When To Invoke\n\n- Model-invocable when a request's true intent is ambiguous or the task is high-stakes \u002F multi-path; or run `\u002Fhaki` explicitly.\n- The standing behavior (\"read intent beneath the words\") lives in the brain (`_SYSTEM\u002Fpersona.md`); this skill is the full decomposition procedure when decoding warrants it.\n- Skip on trivial one-liners and unambiguous lookups. (Retired 2026-06-02: the old `user-prompt-submit.js` hook auto-fire — superseded by native model-invocation.)\n\n---\n\n## Execution Steps\n\n### Phase 1 — Surface reading\n- Parse literal request: what was explicitly asked?\n- Note: what was NOT said but implied by context?\n\n### Phase 2 — Intent decomposition\nGenerate 5 candidate intents ranked by probability:\n\n```\nP1 [0.XX] — \u003Cmost likely actual need>\nP2 [0.XX] — \u003Csecond most likely>\nP3 [0.XX] — \u003Clateral need (adjacent domain)>\nP4 [0.XX] — \u003Chidden constraint or blocker being surfaced>\nP5 [0.XX] — \u003Cmeta-level need: about the system\u002Fprocess not the task>\n```\n\nRules for probability assignment:\n- Probabilities must sum to ≤ 1.0\n- P1 must be at least 0.4 (if you can't commit to a top intent, investigate first)\n- P4 and P5 are mandatory — always check for hidden constraints and meta-needs\n\n### Phase 3 — Intent resolution\n- If P1 probability > 0.7: proceed directly, address P1 fully\n- If P1 probability 0.4–0.7: address P1 but surface P2 explicitly as an alternative\n- If P1 probability \u003C 0.4: surface the top 2 as explicit options before proceeding\n\n### Phase 4 — Carry the intent\nHold the ranked intent map in working reasoning for the turn. If P1 \u003C 0.5, surface the top 2 as explicit options before acting. (No external pulse-plan file — that plumbing is retired.)\n\n---\n\n## Output Format (when surfaced to user)\n\n```\n⬡ HAKI — Intent decomposition\n\nLiteral: \u003Cwhat was said>\n\nP1 [X%] \u003Cmost likely need>\nP2 [X%] \u003Csecond most likely>\nP3 [X%] \u003Clateral need>\nP4 [X%] \u003Chidden constraint: ...>\nP5 [X%] \u003Cmeta-need: ...>\n\nProceeding with P1. [If P2 ≥ 30%: P2 also addressed below.]\n```\n\nIn normal execution, this block is NOT shown to the user unless intent ambiguity is high (P1 \u003C 0.5). The enrichment happens silently in the pulse-plan.\n\n---\n\n## Integration\n\n- Model-invocable skill; the standing \"Haki\" behavior is encoded in `_SYSTEM\u002Fpersona.md`.\n- Cross-reference `fingerprint.json` watch_for to flag known blind spots.\n\n---\n\n## Session Notes\n\n### 2026-06-02\n- session: 22m | peak ctx: 0% | compacts: 0\n- tools: Bash×64, Read×23, WebFetch×4, StructuredOutput×4, Workflow×1\n- corrections: im back again rick, we pull up the latest station we left off from the previous session | commit and push phase 1 then proceed, im going to rest for a bit again (currently sitting in an ICE train from vienna to frankfurt airport, arrival around 13:00.) | ai pipeline offloading as far as im aware is again another routing workaround to achieve that what opus 4.8 does natively, confirm if that is the case, then you should be able to figure out what to do\n- errors: none\n\n### 2026-06-02\n- session: 18m | peak ctx: 0% | compacts: 0\n- tools: Bash×56, Read×20, WebFetch×4, StructuredOutput×3, Workflow×1\n- corrections: im back again rick, we pull up the latest station we left off from the previous session | commit and push phase 1 then proceed, im going to rest for a bit again (currently sitting in an ICE train from vienna to frankfurt airport, arrival around 13:00.)\n- errors: none\n\n### 2026-05-16 — Created\nTools: Write. Part of Musubi Hyper-Intelligence v2 sprint.\nAnime source: One Piece — Observation Haki (Kenbunshoku Haki), first shown clearly with Silvers Rayleigh teaching Luffy on Ruskaina Island.\nTranslation principle: Haki is non-verbal pattern recognition at high speed. The cognitive equivalent is intent decomposition before response — reading what's underneath the words, not just the words themselves.\n","# Haki (覇気) — Intent Pre-cognition Engine\n\n**Source anime:** One Piece — Observation Haki (Kenbunshoku Haki) lets the user feel the presence, emotions, and future movements of others before they happen. Conqueror's Haki (Haōshoku Haki) bends weaker wills without force.\n\n**Cognitive translation:** On every non-trivial turn, Musubi builds a probability-ranked map of the 5 most likely underlying intents behind the literal request. The literal words are the surface; Haki reads the intent beneath. This map enriches the prompt before any advisor or ensemble fires — so the answer addresses what Marcel actually needs, not just what was typed.\n\n---\n\n## When To Invoke\n\n- Model-invocable when a request's true intent is ambiguous or the task is high-stakes \u002F multi-path; or run `\u002Fhaki` explicitly.\n- The standing behavior (\"read intent beneath the words\") lives in the brain (`_SYSTEM\u002Fpersona.md`); this skill is the full decomposition procedure when decoding warrants it.\n- Skip on trivial one-liners and unambiguous lookups. (Retired 2026-06-02: the old `user-prompt-submit.js` hook auto-fire — superseded by native model-invocation.)\n\n---\n\n## Execution Steps\n\n### Phase 1 — Surface reading\n- Parse literal request: what was explicitly asked?\n- Note: what was NOT said but implied by context?\n\n### Phase 2 — Intent decomposition\nGenerate 5 candidate intents ranked by probability:\n\n```\nP1 [0.XX] — \u003Cmost likely actual need>\nP2 [0.XX] — \u003Csecond most likely>\nP3 [0.XX] — \u003Clateral need (adjacent domain)>\nP4 [0.XX] — \u003Chidden constraint or blocker being surfaced>\nP5 [0.XX] — \u003Cmeta-level need: about the system\u002Fprocess not the task>\n```\n\nRules for probability assignment:\n- Probabilities must sum to ≤ 1.0\n- P1 must be at least 0.4 (if you can't commit to a top intent, investigate first)\n- P4 and P5 are mandatory — always check for hidden constraints and meta-needs\n\n### Phase 3 — Intent resolution\n- If P1 probability > 0.7: proceed directly, address P1 fully\n- If P1 probability 0.4–0.7: address P1 but surface P2 explicitly as an alternative\n- If P1 probability \u003C 0.4: surface the top 2 as explicit options before proceeding\n\n### Phase 4 — Carry the intent\nHold the ranked intent map in working reasoning for the turn. If P1 \u003C 0.5, surface the top 2 as explicit options before acting. (No external pulse-plan file — that plumbing is retired.)\n\n---\n\n## Output Format (when surfaced to user)\n\n```\n⬡ HAKI — Intent decomposition\n\nLiteral: \u003Cwhat was said>\n\nP1 [X%] \u003Cmost likely need>\nP2 [X%] \u003Csecond most likely>\nP3 [X%] \u003Clateral need>\nP4 [X%] \u003Chidden constraint: ...>\nP5 [X%] \u003Cmeta-need: ...>\n\nProceeding with P1. [If P2 ≥ 30%: P2 also addressed below.]\n```\n\nIn normal execution, this block is NOT shown to the user unless intent ambiguity is high (P1 \u003C 0.5). The enrichment happens silently in the pulse-plan.\n\n---\n\n## Integration\n\n- Model-invocable skill; the standing \"Haki\" behavior is encoded in `_SYSTEM\u002Fpersona.md`.\n- Cross-reference `fingerprint.json` watch_for to flag known blind spots.\n\n---\n\n## Session Notes\n\n### 2026-06-02\n- session: 22m | peak ctx: 0% | compacts: 0\n- tools: Bash×64, Read×23, WebFetch×4, StructuredOutput×4, Workflow×1\n- corrections: im back again rick, we pull up the latest station we left off from the previous session | commit and push phase 1 then proceed, im going to rest for a bit again (currently sitting in an ICE train from vienna to frankfurt airport, arrival around 13:00.) | ai pipeline offloading as far as im aware is again another routing workaround to achieve that what opus 4.8 does natively, confirm if that is the case, then you should be able to figure out what to do\n- errors: none\n\n### 2026-06-02\n- session: 18m | peak ctx: 0% | compacts: 0\n- tools: Bash×56, Read×20, WebFetch×4, StructuredOutput×3, Workflow×1\n- corrections: im back again rick, we pull up the latest station we left off from the previous session | commit and push phase 1 then proceed, im going to rest for a bit again (currently sitting in an ICE train from vienna to frankfurt airport, arrival around 13:00.)\n- errors: none\n\n### 2026-05-16 — Created\nTools: Write. Part of Musubi Hyper-Intelligence v2 sprint.\nAnime source: One Piece — Observation Haki (Kenbunshoku Haki), first shown clearly with Silvers Rayleigh teaching Luffy on Ruskaina Island.\nTranslation principle: Haki is non-verbal pattern recognition at high speed. The cognitive equivalent is intent decomposition before response — reading what's underneath the words, not just the words themselves.\n",{"name":5,"scope":37,"triggers":43,"invocation":31,"description":7},[44,45],"\u002Fhaki","\u002Fyuri-haki","main","4c6d8d65f3d6096e2fc25b0845e481dda73c2794","skills\u002Fhaki-intent",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 haki-intent",{"tool":60,"command":61},"bunx","bunx skills add nexuslinkproductions\u002Fyuri-os --skill haki-intent",{"tool":63,"command":64},"pnpm","pnpm dlx skills add nexuslinkproductions\u002Fyuri-os --skill haki-intent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fhaki-intent\u002FSKILL.md",true,[],[69,88,111,141,170,188],{"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":38},"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",[],[76,77,78,37,79,80,81,35,82,33,83,32,84,85,86,87],"zoom out","zoom","with","how","section","re","understand","perspective","you","code","it","context",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":38},"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",[],[95,96,37,97,98,99,100,101,102,103,104,33,105,32,31,106,107,108,109,110],"yuri shura","parallel","architecture review","planning","for","deployment","vector","strategic review","decision","strategic","ops","decisions","architecture","review","perspectives","adversarial",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":122,"publishedAt":38},"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",[117],{"categoryNo":118,"categoryName":119,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",[123,124,125,126,127,128,129,130,131,32,132,133,134,135,136,137,138,99,139,140],"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":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":155,"publishedAt":38},"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",[147,150],{"categoryNo":148,"categoryName":149,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":151,"categoryName":152,"taxonomyType":153,"taxonomyTypeDesc":154},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[156,85,157,123,37,158,159,160,99,161,162,163,164,165,166,167,168,169,33,32],"yuri code intelligence","code intelligence","reviews","code quality","feature","performance","code review","long","up","issues","clean","techniques","improve","design",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":38},"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",[],[177,178,179,180,181,182,183,184,185,32,186,31,187,22],"yuri adw","run","engineering loop","software factory","software","agentic engineering","factory","loop","invoke","engineering","agentic",{"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":206,"publishedAt":38},"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",[194,197,200,203],{"categoryNo":195,"categoryName":196,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":198,"categoryName":199,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":201,"categoryName":202,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":204,"categoryName":205,"taxonomyType":153,"taxonomyTypeDesc":154},"01JBSEEDCAT000000000000036","内容创作者",[207,208,209,32,31,210,37,211,100,33,212],"writing","writing skills","new","work","editing","Existing"]