[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HC3BVX9G5VMS91QESS9X9":3,"skill-same:01M71HC3BVX9G5VMS91QESS9X9":114},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":27,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":63,"ownerHtmlUrl":64,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":65,"install":66,"resources":79},"01M71HC3BVX9G5VMS91QESS9X9","linkedin-analytics",null,"Use when someone wants to understand their own LinkedIn numbers — which posts worked, why reach dropped, whether a pattern is real, or how to test a hypothesis. Triggers on \"why did my reach drop\", \"what's working on my LinkedIn\", \"analyze my posts\", \"do carousels do better for me\", \"should I test this\", \"LinkedIn analytics\". Reads your own exported post data, reports medians and outlier bands, tests candidate patterns against a permutation null, and sizes a real experiment — refusing to conclude anything below 10 posts.","marshadgani\u002FArshad.AI","marshadgani","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F275367399?v=4","01M71G2BP4YMZ4AX5YY0QBHAZH","01M71G2BPPHHFRMHQAKJTZPGK4",1,"MIT","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-analytics\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"analytics","linkedin","linkedin analytics","when","test","candidate","for","which","posts","post","how to","triggers","tests","drop","me","do","reports","use","analyze","how","2026-11-10 10:12:30",false,"---\nname: linkedin-analytics\ndescription: Use when someone wants to understand their own LinkedIn numbers — which posts worked, why reach dropped, whether a pattern is real, or how to test a hypothesis. Triggers on \"why did my reach drop\", \"what's working on my LinkedIn\", \"analyze my posts\", \"do carousels do better for me\", \"should I test this\", \"LinkedIn analytics\". Reads your own exported post data, reports medians and outlier bands, tests candidate patterns against a permutation null, and sizes a real experiment — refusing to conclude anything below 10 posts.\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: Alireza Rezvani\n  category: marketing\n  updated: 2026-08-25\n---\n\n# LinkedIn Analytics — describe honestly, then refuse to over-conclude\n\nThe characteristic sentence of LinkedIn analytics is \"carousels do 3x better for me\", built\non four posts. With engagement as heavy-tailed as it is, four posts will show a 3x difference\nbetween almost any two groups you care to define. These three scripts stop that sentence\nbecoming a strategy.\n\n**Your own data only.** Nothing is fetched; scraping post or profile data is prohibited by\nUser Agreement §8.2 and none of this analysis needs it.\n\n## Workflow\n\n**1. Get the export.** LinkedIn Analytics → Post impressions → Export, or Settings → Data\nprivacy → Get a copy of your data. CSV and JSON both work.\n\n**2. Describe it.** Exit 0 analysed \u002F 2 below the 10-post floor, descriptive only \u002F 3\nunusable. Reports median and MAD rather than mean and standard deviation — one breakout post\nmakes a mean describe a distribution none of your posts belong to — plus Tukey percentile\nbands and a 1.5×IQR breakout threshold, so \"this did well\" has a number behind it.\n\n```bash\npython3 scripts\u002Fpost_performance_analyzer.py --input posts.csv --csv --output human\n```\n\n**3. Test the pattern they think they see.**\n\n```bash\npython3 scripts\u002Fpattern_miner.py --input posts.json --output human\n```\n\nExit 0 something survived \u002F 2 nothing survived \u002F 3 under 10 posts. Four gates: 5 posts in and\n5 out; a 15% relative difference in medians; beating 90% of 2,000 seeded label shuffles; and\na multiple-comparisons accounting of how many candidates would pass on noise alone.\n\n**\"Nothing survived\" is the most common honest answer and it is a real finding.** Report it\nas one. Do not soften it into a hedge that reads like a conclusion.\n\n**4. Turn a survivor into a test.**\n\n```bash\npython3 scripts\u002Fexperiment_planner.py --hypothesis \"...\" --variable \"...\" \\\n  --cv 0.45 --effect 0.30 --posts-per-week 2 --max-weeks 12 --output human\n```\n\nCV comes from step 2: `1.4826 * MAD \u002F median`. Exit 0 feasible \u002F 2 too long, with the minimum\ndetectable effect in their window \u002F 3 refused. It will frequently say the test needs more\nposts than a quarter allows — **that is the honest answer**, and more useful than a confident\nconclusion from retrospective data.\n\n## Rules\n\n- **Under 10 posts, describe; do not conclude.** Say so plainly.\n- **A pattern in past posts is a hypothesis.** Retrospective data is confounded — you made\n  carousels when you had structured material, on topics you knew best, in weeks you had time.\n  No statistics on the same data removes that.\n- **Never benchmark against someone else's numbers.** Different denominator, different\n  audience, usually a vendor's sample.\n- **Follower count is not a success metric.** Track inbound conversations, specific\n  references, invitations — the Tier 1 metrics you count by hand.\n- **Report the confidence level.** LinkedIn-official 🟢, third-party study 🟡, folklore 🔴.\n- **One good post is not evidence.** It is the most common cause of a strategy change and the\n  least informative event available.\n\n## Scripts\n\n| Script | Role |\n|---|---|\n| [`scripts\u002Fpost_performance_analyzer.py`](scripts\u002Fpost_performance_analyzer.py) | Median\u002FMAD, percentile bands, IQR outlier fence, per-post BREAKOUT→DUD classification; refuses conclusions below 10 posts. |\n| [`scripts\u002Fpattern_miner.py`](scripts\u002Fpattern_miner.py) | Four-gate permutation test with multiple-comparisons accounting; reports why every rejected candidate failed. |\n| [`scripts\u002Fexperiment_planner.py`](scripts\u002Fexperiment_planner.py) | Sizes a two-arm posting experiment, names the confounds to hold constant, and writes the falsification condition before the first post. |\n\n## References and assets\n\n- [`references\u002Flinkedin_metrics_canon.md`](references\u002Flinkedin_metrics_canon.md) — what each number is, what it is not, and which three tiers to track (7 sources)\n- [`references\u002Fevidence_thresholds.md`](references\u002Fevidence_thresholds.md) — the four gates, forking paths, and the uncomfortable arithmetic of LinkedIn A\u002FB tests (7 sources)\n\n- [`assets\u002Fexample_post_export.csv`](assets\u002Fexample_post_export.csv) — a 12-post export in the expected shape\n- [`assets\u002Fmeasurement_log_template.md`](assets\u002Fmeasurement_log_template.md) — the Tier 1 outcome log you keep by hand\n\n## Distinct from\n\n- **`marketing-skill\u002Fsocial-media-analyzer`** — cross-platform brand campaign reporting. This\n  is one person's own LinkedIn export, with refusals attached.\n- **`linkedin-strategy`** — decides what to do next. This says what happened.\n- **`product-team\u002Fexperiment-designer`** — product A\u002FB tests with real traffic; here n is\n  posts, and usually too small.\n\n---\n**Version:** 1.0.0\n","# LinkedIn Analytics — describe honestly, then refuse to over-conclude\n\nThe characteristic sentence of LinkedIn analytics is \"carousels do 3x better for me\", built\non four posts. With engagement as heavy-tailed as it is, four posts will show a 3x difference\nbetween almost any two groups you care to define. These three scripts stop that sentence\nbecoming a strategy.\n\n**Your own data only.** Nothing is fetched; scraping post or profile data is prohibited by\nUser Agreement §8.2 and none of this analysis needs it.\n\n## Workflow\n\n**1. Get the export.** LinkedIn Analytics → Post impressions → Export, or Settings → Data\nprivacy → Get a copy of your data. CSV and JSON both work.\n\n**2. Describe it.** Exit 0 analysed \u002F 2 below the 10-post floor, descriptive only \u002F 3\nunusable. Reports median and MAD rather than mean and standard deviation — one breakout post\nmakes a mean describe a distribution none of your posts belong to — plus Tukey percentile\nbands and a 1.5×IQR breakout threshold, so \"this did well\" has a number behind it.\n\n```bash\npython3 scripts\u002Fpost_performance_analyzer.py --input posts.csv --csv --output human\n```\n\n**3. Test the pattern they think they see.**\n\n```bash\npython3 scripts\u002Fpattern_miner.py --input posts.json --output human\n```\n\nExit 0 something survived \u002F 2 nothing survived \u002F 3 under 10 posts. Four gates: 5 posts in and\n5 out; a 15% relative difference in medians; beating 90% of 2,000 seeded label shuffles; and\na multiple-comparisons accounting of how many candidates would pass on noise alone.\n\n**\"Nothing survived\" is the most common honest answer and it is a real finding.** Report it\nas one. Do not soften it into a hedge that reads like a conclusion.\n\n**4. Turn a survivor into a test.**\n\n```bash\npython3 scripts\u002Fexperiment_planner.py --hypothesis \"...\" --variable \"...\" \\\n  --cv 0.45 --effect 0.30 --posts-per-week 2 --max-weeks 12 --output human\n```\n\nCV comes from step 2: `1.4826 * MAD \u002F median`. Exit 0 feasible \u002F 2 too long, with the minimum\ndetectable effect in their window \u002F 3 refused. It will frequently say the test needs more\nposts than a quarter allows — **that is the honest answer**, and more useful than a confident\nconclusion from retrospective data.\n\n## Rules\n\n- **Under 10 posts, describe; do not conclude.** Say so plainly.\n- **A pattern in past posts is a hypothesis.** Retrospective data is confounded — you made\n  carousels when you had structured material, on topics you knew best, in weeks you had time.\n  No statistics on the same data removes that.\n- **Never benchmark against someone else's numbers.** Different denominator, different\n  audience, usually a vendor's sample.\n- **Follower count is not a success metric.** Track inbound conversations, specific\n  references, invitations — the Tier 1 metrics you count by hand.\n- **Report the confidence level.** LinkedIn-official 🟢, third-party study 🟡, folklore 🔴.\n- **One good post is not evidence.** It is the most common cause of a strategy change and the\n  least informative event available.\n\n## Scripts\n\n| Script | Role |\n|---|---|\n| [`scripts\u002Fpost_performance_analyzer.py`](scripts\u002Fpost_performance_analyzer.py) | Median\u002FMAD, percentile bands, IQR outlier fence, per-post BREAKOUT→DUD classification; refuses conclusions below 10 posts. |\n| [`scripts\u002Fpattern_miner.py`](scripts\u002Fpattern_miner.py) | Four-gate permutation test with multiple-comparisons accounting; reports why every rejected candidate failed. |\n| [`scripts\u002Fexperiment_planner.py`](scripts\u002Fexperiment_planner.py) | Sizes a two-arm posting experiment, names the confounds to hold constant, and writes the falsification condition before the first post. |\n\n## References and assets\n\n- [`references\u002Flinkedin_metrics_canon.md`](references\u002Flinkedin_metrics_canon.md) — what each number is, what it is not, and which three tiers to track (7 sources)\n- [`references\u002Fevidence_thresholds.md`](references\u002Fevidence_thresholds.md) — the four gates, forking paths, and the uncomfortable arithmetic of LinkedIn A\u002FB tests (7 sources)\n\n- [`assets\u002Fexample_post_export.csv`](assets\u002Fexample_post_export.csv) — a 12-post export in the expected shape\n- [`assets\u002Fmeasurement_log_template.md`](assets\u002Fmeasurement_log_template.md) — the Tier 1 outcome log you keep by hand\n\n## Distinct from\n\n- **`marketing-skill\u002Fsocial-media-analyzer`** — cross-platform brand campaign reporting. This\n  is one person's own LinkedIn export, with refusals attached.\n- **`linkedin-strategy`** — decides what to do next. This says what happened.\n- **`product-team\u002Fexperiment-designer`** — product A\u002FB tests with real traffic; here n is\n  posts, and usually too small.\n\n---\n**Version:** 1.0.0\n",{"name":5,"license":14,"metadata":53,"description":7},{"author":54,"updated":55,"version":56,"category":57},"Alireza Rezvani",1787616000000,"1.0.0","marketing","claude\u002Fai-personal-assistant-main","fb33f7f5b3a206eb019c788e3c48e91c02ccb1f9",".claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-analytics",0,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI","https:\u002F\u002Farshad-ai-seven.vercel.app","https:\u002F\u002Fgithub.com\u002Fmarshadgani","2026-11-02 00:51:35",{"source":8,"skillName":5,"commands":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add marshadgani\u002FArshad.AI --skill linkedin-analytics",{"tool":72,"command":73},"bunx","bunx skills add marshadgani\u002FArshad.AI --skill linkedin-analytics",{"tool":75,"command":76},"pnpm","pnpm dlx skills add marshadgani\u002FArshad.AI --skill linkedin-analytics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-analytics\u002FSKILL.md",true,[80,86,90,96,100,106,110],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"assets\u002Fexample_post_export.csv","ASSET","资产文件",992,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-analytics\u002Fassets\u002Fexample_post_export.csv",{"path":87,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":88,"sourceHtmlUrl":89},"assets\u002Fmeasurement_log_template.md",2440,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-analytics\u002Fassets\u002Fmeasurement_log_template.md",{"path":91,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fevidence_thresholds.md","REFERENCE","参考文档",6592,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-analytics\u002Freferences\u002Fevidence_thresholds.md",{"path":97,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Flinkedin_metrics_canon.md",5913,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-analytics\u002Freferences\u002Flinkedin_metrics_canon.md",{"path":101,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Fexperiment_planner.py","SCRIPT","脚本",10919,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-analytics\u002Fscripts\u002Fexperiment_planner.py",{"path":107,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Fpattern_miner.py",14604,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-analytics\u002Fscripts\u002Fpattern_miner.py",{"path":111,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Fpost_performance_analyzer.py",10888,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-analytics\u002Fscripts\u002Fpost_performance_analyzer.py",[115,147,172,201,231,255],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":119,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":129,"publishedAt":146},"01M71MVWH15PQRS9KT3J24D7WV","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[123,126],{"categoryNo":124,"categoryName":125,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":127,"categoryName":128,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[130,131,132,34,133,134,135,136,137,138,139,140,141,142,143,144,145],"webapp","testing","webapp testing","applications","local","frontend","debugging","toolkit","logs","browser","with","playwright","web","behavior","ui","screenshots","2026-11-10 10:56:23",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":119,"licenseFileUrl":151,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":146},"01M71MVMAZ1J606SGA4JPHRDAZ","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[154],{"categoryNo":127,"categoryName":128,"taxonomyType":20,"taxonomyTypeDesc":21},[156,157,158,142,159,160,161,34,162,163,135,164,45,165,166,167,168,169,170,171],"builder","artifacts builder","artifacts","web artifacts builder","single-file","css","Tailwind","ui components","single","file","components","react","multi","state","routing","state management",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":176,"sourceHtmlUrl":177,"categories":178,"keywords":185,"publishedAt":146},"01M71MSTFAEYT9J9GA587SP3RB","ui-styling","Create beautiful, accessible user interfaces with shadcn\u002Fui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fui-styling\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fui-styling\u002FSKILL.md",[179,182],{"categoryNo":180,"categoryName":181,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":183,"categoryName":184,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000032","设计师",[186,187,144,161,162,188,189,190,191,192,193,194,31,166,195,196,197,198,199,200],"ui styling","styling","mode","canvas","implementing","design","themes","utility","design systems","across","create","component","layout","forms","patterns",{"skillNo":202,"name":191,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":214,"publishedAt":146},"01M71MSM72HXKQRCY5D45WYPNP","Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social\u002Fads\u002Fweb\u002Fprint), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Actions: design logo, create CIP, generate mockups, build slides, design banner, generate icon, create social photos, social media images, brand identity, design system. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fdesign\u002FSKILL.md",[206,209,210,213],{"categoryNo":207,"categoryName":208,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":180,"categoryName":181,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":211,"categoryName":212,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":183,"categoryName":184,"taxonomyType":25,"taxonomyTypeDesc":26},[191,215,216,217,186,218,219,220,221,196,222,223,224,225,226,227,228,229,144,230],"Media","tiktok","actions","logo","logo generation","chart","multi-platform","ads","youtube","generate","presentations","google","atlas cloud","screenshot","muapi","identity",{"skillNo":232,"name":233,"nameZh":6,"description":234,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":235,"categories":236,"keywords":239,"publishedAt":146},"01M71MSH9T7S227MN2YSYB2EP5","design-system","Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing\u002Ftypography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fdesign-system\u002FSKILL.md",[237,238],{"categoryNo":180,"categoryName":181,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":183,"categoryName":184,"taxonomyType":25,"taxonomyTypeDesc":26},[191,240,241,161,242,243,244,245,197,225,246,247,248,249,250,251,252,34,253,254],"design system","system","css variables","creation","Variables","architecture","systematic","token","spacing","layer","typography","brand","three","tokens","slide generation",{"skillNo":256,"name":257,"nameZh":6,"description":258,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":259,"categories":260,"keywords":263,"publishedAt":146},"01M71MSCFZ1HFMNBDMAFXDZV92","banner-design","Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter\u002FX, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fbanner-design\u002FSKILL.md",[261,262],{"categoryNo":180,"categoryName":181,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":183,"categoryName":184,"taxonomyType":25,"taxonomyTypeDesc":26},[191,264,265,215,266,267,268,217,269,270,271,272,273,274,196,222,223,224,275,276],"banner","banner design","3D","direction","neon","Art","social","generated","hero","dimensions","display","options","website"]