[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HCF4PT91BFEWW8QQ5R3FZ":3,"skill-same:01M71HCF4PT91BFEWW8QQ5R3FZ":104},{"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":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M71HCF4PT91BFEWW8QQ5R3FZ","linkedin-skills",null,"Use when someone wants to grow an organic LinkedIn presence — a content strategy for a career change or consulting or thought leadership, a rewritten profile or headline, post drafts and hooks, a posting cadence or newsletter plan, connection notes and outreach, a commenting strategy, repurposing an article or talk into posts, or a read on why their reach dropped. Triggers on \"grow my LinkedIn\", \"fix my headline\", \"write a LinkedIn post\", \"what should I post about\", \"LinkedIn strategy\", \"connection request\", \"my reach dropped\". Forks context to route to one of five sub-skills, and refuses automation, scraping, pods, and bulk DMs before any drafting starts.","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-skills\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"linkedin skills","linkedin","plan","leadership","notes","route","router","drafting","when","policy gate","presence","cadence","managed","fix","hooks","social","Media","posts","scraping","bulk","2026-11-10 10:12:30",false,"---\nname: linkedin-skills\ndescription: Use when someone wants to grow an organic LinkedIn presence — a content strategy for a career change or consulting or thought leadership, a rewritten profile or headline, post drafts and hooks, a posting cadence or newsletter plan, connection notes and outreach, a commenting strategy, repurposing an article or talk into posts, or a read on why their reach dropped. Triggers on \"grow my LinkedIn\", \"fix my headline\", \"write a LinkedIn post\", \"what should I post about\", \"LinkedIn strategy\", \"connection request\", \"my reach dropped\". Forks context to route to one of five sub-skills, and refuses automation, scraping, pods, and bulk DMs before any drafting starts.\ncontext: fork\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: Alireza Rezvani\n  category: marketing\n  updated: 2026-08-25\n  build_pattern: \"Domain orchestrator — deterministic lane router + policy gate, five managed sub-skills\"\n  distinct_from: \"marketing-skill\u002Fx-twitter-growth (X\u002FTwitter-specific); marketing-skill\u002Fsocial-content (multi-platform calendars); marketing-skill\u002Fsocial-media-analyzer (cross-platform reporting); productivity\u002Fandreessen (venture judgement, not audience building)\"\n---\n\n# LinkedIn — Organic Presence Orchestrator\n\n> **Portability + safety:** 17 stdlib-only Python scripts. **No LinkedIn credentials, no API\n> calls, no scraping, nothing auto-sent.** Every output is text the account holder posts\n> themselves — automated posting, connecting, and commenting are prohibited by LinkedIn's\n> User Agreement §8.2, and a restricted account ends the whole project.\n\nBuilding an authentic presence over months, not generating a post. The five lanes cover what\nactually moves: who you are (profile), what you stand for (strategy), what you publish\n(content), who you talk to (engagement), and what any of it did (analytics).\n\n## Step 1 — Gate, before anything is drafted\n\n```bash\npython3 scripts\u002Flinkedin_policy_gate.py --text \"\u003Cthe user's own words>\" --output human\n```\n\n- **exit 4 REFUSE** — a named rule is broken (automation, scraping, pods, bulk DMs, fake\n  identity, fabricated proof, a prohibited automation platform). Do not draft it: name the\n  rule, offer the substitute the gate prints, and route there instead. A REFUSE outranks any\n  route below.\n- **exit 3 CONSTRAIN** — proceed, and state the constraint out loud in your reply.\n- **exit 0 ALLOW** — proceed.\n\n## Step 2 — Route\n\n```bash\npython3 scripts\u002Flinkedin_goal_router.py --text \"\u003Cthe goal>\" --output human\n```\n\nExit 0 routes — invoke that lane, surfacing any `prerequisite` as a question first.\nExit 2 is ambiguous — ask **one** question naming both candidates, with a recommendation.\nExit 3 has no signal — ask what they want to walk away with, rather than guessing.\n\n| Lane | Typical ask |\n|---|---|\n| `linkedin-profile` | \"fix my headline\", \"my profile gets views but nothing happens\" |\n| `linkedin-strategy` | \"what should I post about\", \"how often\", \"should I start a newsletter\" |\n| `linkedin-content` | \"write this post\", \"turn my talk into posts\", \"is this hook any good\" |\n| `linkedin-engagement` | \"who should I comment on\", \"write a connection note\" |\n| `linkedin-analytics` | \"why did reach drop\", \"what's working\", \"should I test this\" |\n\n## Step 3 — Forcing questions\n\nOne at a time, each with a recommended answer. Stop as soon as the lane can run honestly.\n`\u002Fcs:grill-linkedin` walks all five with the recommendation and the canon behind each.\n\n1. What has to be true in 90 days for this to have been worth it? *(Not a follower count.)*\n2. Who is this for, specifically enough that someone is excluded?\n3. How many minutes a week will you protect — measured from a bad week?\n4. What proof already exists? *(If none, the first pillar is process, not results.)*\n5. What will you not post about?\n\n## Hard rules\n\n- **Nothing is automated and nothing is sent.** No credentials, no API, no scraping.\n- **Refuse, then substitute.** Every REFUSE names the compliant alternative.\n- **The account holder is the author of record.** They read every line before it ships.\n- **No claim they cannot substantiate.** A real number, a bounded range, or nothing.\n- **Never silently chain lanes.** Offer the next one as a question.\n- **Cite the confidence level.** LinkedIn-official is 🟢, third-party studies are 🟡,\n  folklore is 🔴 and gets named as folklore.\n\n## Scripts\n\n| Script | Role |\n|---|---|\n| [`scripts\u002Flinkedin_policy_gate.py`](scripts\u002Flinkedin_policy_gate.py) | ALLOW \u002F CONSTRAIN \u002F REFUSE against User Agreement §8.2 + Community Policies. 7 refusal rules, each with a substitute. |\n| [`scripts\u002Flinkedin_goal_router.py`](scripts\u002Flinkedin_goal_router.py) | Deterministic five-lane classifier: route (0) \u002F ask (2) \u002F no-signal (3), with cross-lane prerequisites. |\n\n## References and assets\n\n- [`references\u002Flinkedin_platform_canon.md`](references\u002Flinkedin_platform_canon.md) — how the feed ranks, evidence-graded (7 sources)\n- [`references\u002Fpolicy_and_account_safety.md`](references\u002Fpolicy_and_account_safety.md) — §8.2, prohibited software, restriction triggers (7 sources)\n- [`assets\u002Flinkedin_operating_agreement.md`](assets\u002Flinkedin_operating_agreement.md) — the standing rules in one page, agreed before work starts\n\n## Distinct from\n\n- **`marketing-skill\u002Fx-twitter-growth`** — X\u002FTwitter mechanics. Different platform and rules.\n- **`marketing-skill\u002Fsocial-content` \u002F `social-media-manager`** — multi-platform brand\n  calendars. This is one person's presence on one platform, in depth.\n- **`marketing-skill\u002Fsocial-media-analyzer`** — cross-platform campaign reporting.\n\n---\n\n**Version:** 1.0.0 · 5 lanes · 17 stdlib scripts · nothing auto-sent\n","# LinkedIn — Organic Presence Orchestrator\n\n> **Portability + safety:** 17 stdlib-only Python scripts. **No LinkedIn credentials, no API\n> calls, no scraping, nothing auto-sent.** Every output is text the account holder posts\n> themselves — automated posting, connecting, and commenting are prohibited by LinkedIn's\n> User Agreement §8.2, and a restricted account ends the whole project.\n\nBuilding an authentic presence over months, not generating a post. The five lanes cover what\nactually moves: who you are (profile), what you stand for (strategy), what you publish\n(content), who you talk to (engagement), and what any of it did (analytics).\n\n## Step 1 — Gate, before anything is drafted\n\n```bash\npython3 scripts\u002Flinkedin_policy_gate.py --text \"\u003Cthe user's own words>\" --output human\n```\n\n- **exit 4 REFUSE** — a named rule is broken (automation, scraping, pods, bulk DMs, fake\n  identity, fabricated proof, a prohibited automation platform). Do not draft it: name the\n  rule, offer the substitute the gate prints, and route there instead. A REFUSE outranks any\n  route below.\n- **exit 3 CONSTRAIN** — proceed, and state the constraint out loud in your reply.\n- **exit 0 ALLOW** — proceed.\n\n## Step 2 — Route\n\n```bash\npython3 scripts\u002Flinkedin_goal_router.py --text \"\u003Cthe goal>\" --output human\n```\n\nExit 0 routes — invoke that lane, surfacing any `prerequisite` as a question first.\nExit 2 is ambiguous — ask **one** question naming both candidates, with a recommendation.\nExit 3 has no signal — ask what they want to walk away with, rather than guessing.\n\n| Lane | Typical ask |\n|---|---|\n| `linkedin-profile` | \"fix my headline\", \"my profile gets views but nothing happens\" |\n| `linkedin-strategy` | \"what should I post about\", \"how often\", \"should I start a newsletter\" |\n| `linkedin-content` | \"write this post\", \"turn my talk into posts\", \"is this hook any good\" |\n| `linkedin-engagement` | \"who should I comment on\", \"write a connection note\" |\n| `linkedin-analytics` | \"why did reach drop\", \"what's working\", \"should I test this\" |\n\n## Step 3 — Forcing questions\n\nOne at a time, each with a recommended answer. Stop as soon as the lane can run honestly.\n`\u002Fcs:grill-linkedin` walks all five with the recommendation and the canon behind each.\n\n1. What has to be true in 90 days for this to have been worth it? *(Not a follower count.)*\n2. Who is this for, specifically enough that someone is excluded?\n3. How many minutes a week will you protect — measured from a bad week?\n4. What proof already exists? *(If none, the first pillar is process, not results.)*\n5. What will you not post about?\n\n## Hard rules\n\n- **Nothing is automated and nothing is sent.** No credentials, no API, no scraping.\n- **Refuse, then substitute.** Every REFUSE names the compliant alternative.\n- **The account holder is the author of record.** They read every line before it ships.\n- **No claim they cannot substantiate.** A real number, a bounded range, or nothing.\n- **Never silently chain lanes.** Offer the next one as a question.\n- **Cite the confidence level.** LinkedIn-official is 🟢, third-party studies are 🟡,\n  folklore is 🔴 and gets named as folklore.\n\n## Scripts\n\n| Script | Role |\n|---|---|\n| [`scripts\u002Flinkedin_policy_gate.py`](scripts\u002Flinkedin_policy_gate.py) | ALLOW \u002F CONSTRAIN \u002F REFUSE against User Agreement §8.2 + Community Policies. 7 refusal rules, each with a substitute. |\n| [`scripts\u002Flinkedin_goal_router.py`](scripts\u002Flinkedin_goal_router.py) | Deterministic five-lane classifier: route (0) \u002F ask (2) \u002F no-signal (3), with cross-lane prerequisites. |\n\n## References and assets\n\n- [`references\u002Flinkedin_platform_canon.md`](references\u002Flinkedin_platform_canon.md) — how the feed ranks, evidence-graded (7 sources)\n- [`references\u002Fpolicy_and_account_safety.md`](references\u002Fpolicy_and_account_safety.md) — §8.2, prohibited software, restriction triggers (7 sources)\n- [`assets\u002Flinkedin_operating_agreement.md`](assets\u002Flinkedin_operating_agreement.md) — the standing rules in one page, agreed before work starts\n\n## Distinct from\n\n- **`marketing-skill\u002Fx-twitter-growth`** — X\u002FTwitter mechanics. Different platform and rules.\n- **`marketing-skill\u002Fsocial-content` \u002F `social-media-manager`** — multi-platform brand\n  calendars. This is one person's presence on one platform, in depth.\n- **`marketing-skill\u002Fsocial-media-analyzer`** — cross-platform campaign reporting.\n\n---\n\n**Version:** 1.0.0 · 5 lanes · 17 stdlib scripts · nothing auto-sent\n",{"name":5,"context":48,"license":14,"metadata":49,"description":7},"fork",{"author":50,"updated":51,"version":52,"category":53,"build_pattern":54,"distinct_from":55},"Alireza Rezvani",1787616000000,"1.0.0","marketing","Domain orchestrator — deterministic lane router + policy gate, five managed sub-skills","marketing-skill\u002Fx-twitter-growth (X\u002FTwitter-specific); marketing-skill\u002Fsocial-content (multi-platform calendars); marketing-skill\u002Fsocial-media-analyzer (cross-platform reporting); productivity\u002Fandreessen (venture judgement, not audience building)","claude\u002Fai-personal-assistant-main","fb33f7f5b3a206eb019c788e3c48e91c02ccb1f9",".claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-skills",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":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add marshadgani\u002FArshad.AI --skill linkedin-skills",{"tool":70,"command":71},"bunx","bunx skills add marshadgani\u002FArshad.AI --skill linkedin-skills",{"tool":73,"command":74},"pnpm","pnpm dlx skills add marshadgani\u002FArshad.AI --skill linkedin-skills","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-skills\u002FSKILL.md",true,[78,84,90,94,100],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"assets\u002Flinkedin_operating_agreement.md","ASSET","资产文件",3371,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-skills\u002Fassets\u002Flinkedin_operating_agreement.md",{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Flinkedin_platform_canon.md","REFERENCE","参考文档",7999,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-skills\u002Freferences\u002Flinkedin_platform_canon.md",{"path":91,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fpolicy_and_account_safety.md",7916,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-skills\u002Freferences\u002Fpolicy_and_account_safety.md",{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Flinkedin_goal_router.py","SCRIPT","脚本",8310,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-skills\u002Fscripts\u002Flinkedin_goal_router.py",{"path":101,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Flinkedin_policy_gate.py",15869,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Flinkedin-skills\u002Fscripts\u002Flinkedin_policy_gate.py",[105,140,166,195,224,248],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":109,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":121,"publishedAt":139},"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",[113,118],{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":119,"categoryName":120,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000009","前端开发",[122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138],"webapp","testing","webapp testing","for","applications","local","frontend","debugging","toolkit","logs","browser","with","playwright","web","behavior","ui","screenshots","2026-11-10 10:56:23",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":109,"licenseFileUrl":144,"sourceHtmlUrl":145,"categories":146,"keywords":148,"publishedAt":139},"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",[147],{"categoryNo":119,"categoryName":120,"taxonomyType":116,"taxonomyTypeDesc":117},[149,150,151,135,152,153,154,125,155,156,128,157,158,159,160,161,162,163,164,165],"builder","artifacts builder","artifacts","web artifacts builder","single-file","css","Tailwind","ui components","single","use","file","components","react","multi","state","routing","state management",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":170,"sourceHtmlUrl":171,"categories":172,"keywords":179,"publishedAt":139},"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",[173,176],{"categoryNo":174,"categoryName":175,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":177,"categoryName":178,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000032","设计师",[180,181,137,154,155,182,183,184,185,186,187,188,31,160,189,190,191,192,193,194],"ui styling","styling","mode","canvas","implementing","design","themes","utility","design systems","across","create","component","layout","forms","patterns",{"skillNo":196,"name":185,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":208,"publishedAt":139},"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",[200,203,204,207],{"categoryNo":201,"categoryName":202,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":174,"categoryName":175,"taxonomyType":116,"taxonomyTypeDesc":117},{"categoryNo":205,"categoryName":206,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":177,"categoryName":178,"taxonomyType":20,"taxonomyTypeDesc":21},[185,39,209,210,180,211,212,213,214,190,215,216,217,218,219,220,221,222,137,223],"tiktok","actions","logo","logo generation","chart","multi-platform","ads","youtube","generate","presentations","google","atlas cloud","screenshot","muapi","identity",{"skillNo":225,"name":226,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":232,"publishedAt":139},"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",[230,231],{"categoryNo":174,"categoryName":175,"taxonomyType":116,"taxonomyTypeDesc":117},{"categoryNo":177,"categoryName":178,"taxonomyType":20,"taxonomyTypeDesc":21},[185,233,234,154,235,236,237,238,191,218,239,240,241,242,243,244,245,125,246,247],"design system","system","css variables","creation","Variables","architecture","systematic","token","spacing","layer","typography","brand","three","tokens","slide generation",{"skillNo":249,"name":250,"nameZh":6,"description":251,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":252,"categories":253,"keywords":256,"publishedAt":139},"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",[254,255],{"categoryNo":174,"categoryName":175,"taxonomyType":116,"taxonomyTypeDesc":117},{"categoryNo":177,"categoryName":178,"taxonomyType":20,"taxonomyTypeDesc":21},[185,257,258,39,259,260,261,210,262,38,263,264,265,266,190,215,216,217,267,268],"banner","banner design","3D","direction","neon","Art","generated","hero","dimensions","display","options","website"]