[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71CFBH48ZX96GDV6PS4KGTG":3,"skill-same:01M71CFBH48ZX96GDV6PS4KGTG":78},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M71CFBH48ZX96GDV6PS4KGTG","viz-lab",null,"Build best-in-class, real-data-grounded visualizations of YURI's own systems — energy\u002FΔU surfaces, quantum Q-spheres, circuitry graphs (2D edge-bundling + 3D die), telemetry cockpits, embedding atlases. Use when the task is to visualize, depict, render, or make interactive any YURI math \u002F quantum \u002F graph \u002F telemetry data, build a 3D \u002F WebGL \u002F three.js \u002F react-three-fiber or D3 visualization, turn a flat view into 3D, or prototype a viz before wiring it into the app. Triggers: visualize, viz, visualization, 3D, WebGL, three.js, D3, surface, graph, chart, dashboard, Q-sphere, edge bundling, make this 3D.","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\u002Fviz-lab\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"lab","viz lab","visualizations","make","graph","react-three-fiber","data","surfaces","math","energy","dashboard","react","wiring","when","chart","render","embedding","3D","visualization","app","2026-11-10 10:12:30",false,"---\nname: viz-lab\ndescription: \"Build best-in-class, real-data-grounded visualizations of YURI's own systems — energy\u002FΔU surfaces, quantum Q-spheres, circuitry graphs (2D edge-bundling + 3D die), telemetry cockpits, embedding atlases. Use when the task is to visualize, depict, render, or make interactive any YURI math \u002F quantum \u002F graph \u002F telemetry data, build a 3D \u002F WebGL \u002F three.js \u002F react-three-fiber or D3 visualization, turn a flat view into 3D, or prototype a viz before wiring it into the app. Triggers: visualize, viz, visualization, 3D, WebGL, three.js, D3, surface, graph, chart, dashboard, Q-sphere, edge bundling, make this 3D.\"\nscope: harness\ninvocation: ability\n---\n\n# YURI Viz-Lab\n\nBest-tool-per-depiction visualization of YURI's own math, quantum, graph, and telemetry layers. **Quality over friction**: pick the genuinely strongest tool for each depiction (Python \u002F Rust \u002F JS — whatever wins), and ground every visual in YURI's **real** code\u002Fdata, never a lookalike.\n\n## Method (the loop that produced the `demos\u002F`)\n\n1. **Ground in real data** — never synthesize a stand-in. Write a generator under `demos\u002Fbuild\u002F*.mjs` that imports the real YURI module (e.g. `computeU` from `_SYSTEM\u002FScripts\u002Fmath\u002Fyuri-energy.mjs`, the exports of `_SYSTEM\u002FScripts\u002Fquantum-hypothesis-tracker.mjs`) or reads the real artifact (e.g. `02_RESOURCES\u002FRESEARCH\u002Fyuri-die-graph.json`), and emit `demos\u002Fdata\u002F\u003Cx>.js` as a `window.\u003CGLOBAL> = …` script. The visual then provably reflects the live system.\n2. **Best tool per depiction** — map the depiction to its strongest tool (table below); do not default to the readiest one. Stack-agnostic.\n3. **Standalone-first, `file:\u002F\u002F`-safe** — one self-contained `.html` that opens by double-click. CDN module imports (CORS-enabled) + local data loaded as a `\u003Cscript src>` global. NEVER a relative ES-module import or `fetch()` — both are blocked on `file:\u002F\u002F`.\n4. **Adversarially verify** — `node --check` the extracted script; confirm every `getElementById` id resolves; prove **fidelity** (recompute a data cell against the real function; confirm a real invariant, e.g. the quantum order-effect P(A→B) ≠ P(B→A) with qq ≈ 0); then an independent render-review before claiming it works. First-run success is a hypothesis.\n5. **Port, don't rewrite** — the standalone renderer ports into the Vite + react-three-fiber app (`_SYSTEM\u002Fsrc\u002Fscenes\u002F`); the generator re-points from snapshot to live stream.\n\n## Depiction → best tool\n\n| YURI object | Depiction | Best tool |\n|---|---|---|\n| energy gate ΔU \u002F U | 3D surface · isosurface · ridgeline · particle field | three.js (+ bloom) \u002F VTK.js |\n| quantum hypothesis sim | Q-sphere · Wigner · Hinton (coupling) | three.js (embed the real tracker) \u002F Qiskit ref |\n| circuitry \u002F code graph | hierarchical edge bundling · 3D layered die · GPU force | D3 (HEB) · three.js (strata) · cosmos.gl (scale) |\n| alpha factors | correlation clustermap · embedding atlas | seaborn \u002F ECharts · regl-scatterplot + UMAP |\n| prediction ledger \u002F decision-sim | calibration diagram · quantile dotplot · fan cone | D3 \u002F Vega · ArviZ |\n| lane telemetry \u002F tokens | uPlot + LTTB · horizon · streaming pivot | uPlot · FINOS Perspective |\n\nDefault JS stack (drops into the existing three.js@0.173 + R3F + Vite): **three.js \u002F R3F** for 3D, **D3** for graphs\u002Fbundling, **uPlot** for time-series, **ECharts-GL \u002F regl \u002F Sigma** at scale.\n\n## Reference assets (read first)\n\n- Landscape survey — 12 families, every technique mapped to a YURI domain, with sources: `02_RESOURCES\u002FRESEARCH\u002Fvisualization-landscape-2026-06-16.md` (`ai search \"visualization\"`).\n- Proven demos: `demos\u002Fvol-surface.html`, `demos\u002Fenergy-surface.html`, `demos\u002Fqsphere.html`, `demos\u002Fcircuitry-heb.html`, `demos\u002Fcircuitry-die-3d.html`; generators `demos\u002Fbuild\u002Fgen-*.mjs`.\n\n## Rules (failure-anchored)\n\n- **`file:\u002F\u002F`-safe loading only**: CDN module imports + local-data globals; no relative module imports \u002F `fetch()`. \u003C!-- @anchor: v1 | failure: file:\u002F\u002F CORS blocks relative ES-module imports + fetch (demos session 2026-06-16) | regression: the node --check + open-in-browser step of this skill -->\n- **Real data, not lookalikes; quality over friction**: pick the BEST tool and the MOST COMPLETE real source, not the readiest. \u003C!-- @anchor: v1 | failure: grabbed the 126-node projected graph (least-friction) when the owner wanted the 242-node die\u002Fmerge — \"best results, not least friction\" (Marcel 2026-06-16) | regression: the ground-in-real-data + completeness check in this skill -->\n- **Verify fidelity, not just syntax**: recompute a real value, confirm a real invariant, independent render-review before \"it works\".\n- **No HUD\u002FKagami design tokens** — style with self-contained purpose-built CSS (standing owner preference).\n\n## Session Notes\n\n### 2026-06-16\n- session: 155m | peak ctx: 0% | compacts: 0\n- tools: Bash×338, Read×113, Edit×60, Write×21, Agent×14, TodoWrite×5, AskUserQuestion×3, ToolSearch×2, WebSearch×2\n- corrections: none\n- errors: none\n","# YURI Viz-Lab\n\nBest-tool-per-depiction visualization of YURI's own math, quantum, graph, and telemetry layers. **Quality over friction**: pick the genuinely strongest tool for each depiction (Python \u002F Rust \u002F JS — whatever wins), and ground every visual in YURI's **real** code\u002Fdata, never a lookalike.\n\n## Method (the loop that produced the `demos\u002F`)\n\n1. **Ground in real data** — never synthesize a stand-in. Write a generator under `demos\u002Fbuild\u002F*.mjs` that imports the real YURI module (e.g. `computeU` from `_SYSTEM\u002FScripts\u002Fmath\u002Fyuri-energy.mjs`, the exports of `_SYSTEM\u002FScripts\u002Fquantum-hypothesis-tracker.mjs`) or reads the real artifact (e.g. `02_RESOURCES\u002FRESEARCH\u002Fyuri-die-graph.json`), and emit `demos\u002Fdata\u002F\u003Cx>.js` as a `window.\u003CGLOBAL> = …` script. The visual then provably reflects the live system.\n2. **Best tool per depiction** — map the depiction to its strongest tool (table below); do not default to the readiest one. Stack-agnostic.\n3. **Standalone-first, `file:\u002F\u002F`-safe** — one self-contained `.html` that opens by double-click. CDN module imports (CORS-enabled) + local data loaded as a `\u003Cscript src>` global. NEVER a relative ES-module import or `fetch()` — both are blocked on `file:\u002F\u002F`.\n4. **Adversarially verify** — `node --check` the extracted script; confirm every `getElementById` id resolves; prove **fidelity** (recompute a data cell against the real function; confirm a real invariant, e.g. the quantum order-effect P(A→B) ≠ P(B→A) with qq ≈ 0); then an independent render-review before claiming it works. First-run success is a hypothesis.\n5. **Port, don't rewrite** — the standalone renderer ports into the Vite + react-three-fiber app (`_SYSTEM\u002Fsrc\u002Fscenes\u002F`); the generator re-points from snapshot to live stream.\n\n## Depiction → best tool\n\n| YURI object | Depiction | Best tool |\n|---|---|---|\n| energy gate ΔU \u002F U | 3D surface · isosurface · ridgeline · particle field | three.js (+ bloom) \u002F VTK.js |\n| quantum hypothesis sim | Q-sphere · Wigner · Hinton (coupling) | three.js (embed the real tracker) \u002F Qiskit ref |\n| circuitry \u002F code graph | hierarchical edge bundling · 3D layered die · GPU force | D3 (HEB) · three.js (strata) · cosmos.gl (scale) |\n| alpha factors | correlation clustermap · embedding atlas | seaborn \u002F ECharts · regl-scatterplot + UMAP |\n| prediction ledger \u002F decision-sim | calibration diagram · quantile dotplot · fan cone | D3 \u002F Vega · ArviZ |\n| lane telemetry \u002F tokens | uPlot + LTTB · horizon · streaming pivot | uPlot · FINOS Perspective |\n\nDefault JS stack (drops into the existing three.js@0.173 + R3F + Vite): **three.js \u002F R3F** for 3D, **D3** for graphs\u002Fbundling, **uPlot** for time-series, **ECharts-GL \u002F regl \u002F Sigma** at scale.\n\n## Reference assets (read first)\n\n- Landscape survey — 12 families, every technique mapped to a YURI domain, with sources: `02_RESOURCES\u002FRESEARCH\u002Fvisualization-landscape-2026-06-16.md` (`ai search \"visualization\"`).\n- Proven demos: `demos\u002Fvol-surface.html`, `demos\u002Fenergy-surface.html`, `demos\u002Fqsphere.html`, `demos\u002Fcircuitry-heb.html`, `demos\u002Fcircuitry-die-3d.html`; generators `demos\u002Fbuild\u002Fgen-*.mjs`.\n\n## Rules (failure-anchored)\n\n- **`file:\u002F\u002F`-safe loading only**: CDN module imports + local-data globals; no relative module imports \u002F `fetch()`. \u003C!-- @anchor: v1 | failure: file:\u002F\u002F CORS blocks relative ES-module imports + fetch (demos session 2026-06-16) | regression: the node --check + open-in-browser step of this skill -->\n- **Real data, not lookalikes; quality over friction**: pick the BEST tool and the MOST COMPLETE real source, not the readiest. \u003C!-- @anchor: v1 | failure: grabbed the 126-node projected graph (least-friction) when the owner wanted the 242-node die\u002Fmerge — \"best results, not least friction\" (Marcel 2026-06-16) | regression: the ground-in-real-data + completeness check in this skill -->\n- **Verify fidelity, not just syntax**: recompute a real value, confirm a real invariant, independent render-review before \"it works\".\n- **No HUD\u002FKagami design tokens** — style with self-contained purpose-built CSS (standing owner preference).\n\n## Session Notes\n\n### 2026-06-16\n- session: 155m | peak ctx: 0% | compacts: 0\n- tools: Bash×338, Read×113, Edit×60, Write×21, Agent×14, TodoWrite×5, AskUserQuestion×3, ToolSearch×2, WebSearch×2\n- corrections: none\n- errors: none\n",{"name":5,"scope":54,"invocation":55,"description":7},"harness","ability","main","4c6d8d65f3d6096e2fc25b0845e481dda73c2794","skills\u002Fviz-lab",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":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add nexuslinkproductions\u002Fyuri-os --skill viz-lab",{"tool":70,"command":71},"bunx","bunx skills add nexuslinkproductions\u002Fyuri-os --skill viz-lab",{"tool":73,"command":74},"pnpm","pnpm dlx skills add nexuslinkproductions\u002Fyuri-os --skill viz-lab","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fviz-lab\u002FSKILL.md",true,[],[79,100,124,152,179,198],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":49},"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",[],[86,87,88,54,89,90,91,92,93,94,95,42,96,97,98,99],"zoom out","zoom","with","how","section","re","true","understand","use","perspective","you","code","it","context",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":49},"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",[],[107,108,54,109,110,111,112,113,114,115,116,94,117,42,118,119,120,121,122,123],"yuri shura","parallel","architecture review","planning","for","deployment","vector","strategic review","decision","strategic","ops","workflow","decisions","architecture","review","perspectives","adversarial",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":133,"publishedAt":49},"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",[130],{"categoryNo":131,"categoryName":132,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000005","邮件与沟通",[134,135,136,137,138,139,140,141,142,42,143,144,145,146,147,148,149,111,150,151],"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":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":164,"publishedAt":49},"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",[158,161],{"categoryNo":159,"categoryName":160,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":162,"categoryName":163,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师",[165,97,166,134,54,167,168,169,111,170,171,172,173,174,175,176,177,178,94,42],"yuri code intelligence","code intelligence","reviews","code quality","feature","performance","code review","long","up","issues","clean","techniques","improve","design",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":185,"publishedAt":49},"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",[],[186,187,188,189,190,191,192,193,194,42,195,118,196,197],"yuri adw","run","engineering loop","software factory","software","agentic engineering","factory","loop","invoke","engineering","agentic","user",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":216,"publishedAt":49},"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",[204,207,210,213],{"categoryNo":205,"categoryName":206,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":208,"categoryName":209,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":211,"categoryName":212,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":214,"categoryName":215,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者",[217,218,219,42,118,220,54,221,112,94,222],"writing","writing skills","new","work","editing","Existing"]