[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HVSBHCEVDPGE23WG4ABF8":3,"skill-same:01M71HVSBHCEVDPGE23WG4ABF8":134},{"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":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M71HVSBHCEVDPGE23WG4ABF8","workflow-builder",null,"Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","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\u002Fworkflow-builder\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"workflow","workflow builder","builder","multi-agent","judge","write","scripts","run","create","fresh","across","code","when","workflows","loop","files","design","pipeline","claude code workflow","orchestrate","2026-11-10 10:12:30",false,"---\nname: workflow-builder\ndescription: Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.\nlicense: MIT\nmetadata:\n  inspired_by: \"https:\u002F\u002Fgithub.com\u002Fray-amjad\u002Fclaude-code-workflow-creator (Ray Amjad)\"\n  targets: \"Claude Code Workflow tool (CLAUDE_CODE_WORKFLOWS=1, \u002Fworkflows)\"\n  version: 1.0.0\n---\n\n# Workflow Builder\n\nAuthor runnable workflow scripts for Claude Code's Workflow tool: deterministic multi-agent orchestration files (`.js`) that fan work out to fresh-context sub-agents under plain JavaScript control flow. Only leaf `agent()` calls spend tokens, so the main session stays clean and the whole run is resumable.\n\n## ALWAYS start every session with intake (non-negotiable)\n\nBefore proposing or writing any workflow, run the intake. Do not skip to code.\n\n1. **Ask what kind of workflow they want.** Use this opening question set:\n   - What repeatable, multi-step task do you want to automate?\n   - What is the one unit of work a single sub-agent does once?\n   - How many units — a known list, or discovered by looping?\n   - Do later steps need *all* prior results at once, or can each item flow on its own?\n   - Does any step need structured data back (a verdict, a list, scores)?\n   - Roughly how many tokens \u002F how deep should it go?\n\n2. **If the user is vague, do NOT stall.** Run the recommendation engine to turn whatever you have into 1-2 concrete proposals, then present them *with the reasoning*:\n   ```bash\n   python scripts\u002Fworkflow_intake.py --task \"their description\" \\\n     --units unknown --stages unknown --needs-all unknown --structured unknown\n   ```\n   The engine returns a recommended topology (fan-out \u002F pipeline \u002F loop \u002F barrier \u002F judge-panel), model picks, a budget guard, and a one-line rationale per choice. Present those as \"Here's what I'd build and why\" — never ask the user to re-answer questions they already half-answered.\n\n3. **Confirm the shape with the user** (topology + phases + parallel-vs-pipeline) before writing the file. This is the only approval gate.\n\nSee [references\u002Fdecision_and_intake_guide.md](references\u002Fdecision_and_intake_guide.md) for the full question framework, the vague-input playbook, and worked recommendation examples.\n\n## Decide if a workflow is even the right tool\n\n| Scenario | Use |\n|----------|-----|\n| Single sub-agent, one task | plain Agent tool |\n| Reusable procedure, Claude picks steps dynamically | a Skill |\n| Many sub-agents in a fixed topology, deterministic + resumable | **Workflow** ✓ |\n\nWorkflows earn their cost when work is parallel or multi-stage, must be reproducible, long enough to fail halfway (so resume matters), or benefits from isolating each step in its own context window. For one-off tasks, just use Claude directly.\n\n## Build → validate → run loop\n\n1. **Scaffold** a starter from the confirmed topology:\n   ```bash\n   python scripts\u002Fscaffold_workflow.py --topology pipeline --name pr-triage \\\n     --description \"Triage open PRs\" > .claude\u002Fworkflows\u002Fpr-triage.js\n   ```\n2. **Edit** the file: `meta` block first (pure literal, first statement), then the async body using the injected globals — `agent()`, `pipeline()`, `parallel()`, `phase()`, `log()`, `budget`, `args`, `workflow()`. Full surface in [references\u002Fapi_reference.md](references\u002Fapi_reference.md); copy-paste shapes in [references\u002Forchestration_patterns.md](references\u002Forchestration_patterns.md).\n3. **Validate** before running — catches the parser-fatal mistakes:\n   ```bash\n   python scripts\u002Fvalidate_workflow.py .claude\u002Fworkflows\u002Fpr-triage.js\n   ```\n4. **Run** it: enable the feature with `export CLAUDE_CODE_WORKFLOWS=1`, save the file under `.claude\u002Fworkflows\u002F`, then use `\u002Fworkflows` to launch and watch it live. Press **P** to pause\u002Fresume, **X** to skip a sub-agent. Failed agents retry automatically.\n\n## Hard rules (validator enforces these)\n\n- `meta` is a **pure literal** and the **first statement** — no variables, spreads, template strings, or function calls inside it.\n- **No non-determinism:** `Date.now()`, `Math.random()`, argless `new Date()` break resume — pass timestamps via `args`.\n- **No filesystem \u002F Node APIs** (`require`, `fs`, `process`, network) in the orchestrator — that work belongs *inside* `agent()` prompts.\n- `parallel()` takes **thunks** (`() => agent(...)`), not bare promises. Default to `pipeline()` unless a stage needs the whole prior result set.\n- **Guard every open-ended loop** with a counter or `budget.remaining()` check — unguarded loops hit the 1000-agent cap.\n- Filter skipped\u002Ffailed agents: `results.filter(Boolean)`.\n\n## Tooling\n\n- `scripts\u002Fworkflow_intake.py` — intake recommendation engine (topology + model + budget + rationale from vague input).\n- `scripts\u002Fvalidate_workflow.py` — stdlib linter for the rules above; PASS \u002F WARN \u002F FAIL with line numbers.\n- `scripts\u002Fscaffold_workflow.py` — generate a starter `.js` for any topology.\n- `assets\u002Ftemplates\u002F` — fan-out, pipeline, loop-until-budget starters. `assets\u002Fexamples\u002F` — a complete runnable workflow.\n\nAll scripts run with `--sample` (no args) and `--help`.\n","# Workflow Builder\n\nAuthor runnable workflow scripts for Claude Code's Workflow tool: deterministic multi-agent orchestration files (`.js`) that fan work out to fresh-context sub-agents under plain JavaScript control flow. Only leaf `agent()` calls spend tokens, so the main session stays clean and the whole run is resumable.\n\n## ALWAYS start every session with intake (non-negotiable)\n\nBefore proposing or writing any workflow, run the intake. Do not skip to code.\n\n1. **Ask what kind of workflow they want.** Use this opening question set:\n   - What repeatable, multi-step task do you want to automate?\n   - What is the one unit of work a single sub-agent does once?\n   - How many units — a known list, or discovered by looping?\n   - Do later steps need *all* prior results at once, or can each item flow on its own?\n   - Does any step need structured data back (a verdict, a list, scores)?\n   - Roughly how many tokens \u002F how deep should it go?\n\n2. **If the user is vague, do NOT stall.** Run the recommendation engine to turn whatever you have into 1-2 concrete proposals, then present them *with the reasoning*:\n   ```bash\n   python scripts\u002Fworkflow_intake.py --task \"their description\" \\\n     --units unknown --stages unknown --needs-all unknown --structured unknown\n   ```\n   The engine returns a recommended topology (fan-out \u002F pipeline \u002F loop \u002F barrier \u002F judge-panel), model picks, a budget guard, and a one-line rationale per choice. Present those as \"Here's what I'd build and why\" — never ask the user to re-answer questions they already half-answered.\n\n3. **Confirm the shape with the user** (topology + phases + parallel-vs-pipeline) before writing the file. This is the only approval gate.\n\nSee [references\u002Fdecision_and_intake_guide.md](references\u002Fdecision_and_intake_guide.md) for the full question framework, the vague-input playbook, and worked recommendation examples.\n\n## Decide if a workflow is even the right tool\n\n| Scenario | Use |\n|----------|-----|\n| Single sub-agent, one task | plain Agent tool |\n| Reusable procedure, Claude picks steps dynamically | a Skill |\n| Many sub-agents in a fixed topology, deterministic + resumable | **Workflow** ✓ |\n\nWorkflows earn their cost when work is parallel or multi-stage, must be reproducible, long enough to fail halfway (so resume matters), or benefits from isolating each step in its own context window. For one-off tasks, just use Claude directly.\n\n## Build → validate → run loop\n\n1. **Scaffold** a starter from the confirmed topology:\n   ```bash\n   python scripts\u002Fscaffold_workflow.py --topology pipeline --name pr-triage \\\n     --description \"Triage open PRs\" > .claude\u002Fworkflows\u002Fpr-triage.js\n   ```\n2. **Edit** the file: `meta` block first (pure literal, first statement), then the async body using the injected globals — `agent()`, `pipeline()`, `parallel()`, `phase()`, `log()`, `budget`, `args`, `workflow()`. Full surface in [references\u002Fapi_reference.md](references\u002Fapi_reference.md); copy-paste shapes in [references\u002Forchestration_patterns.md](references\u002Forchestration_patterns.md).\n3. **Validate** before running — catches the parser-fatal mistakes:\n   ```bash\n   python scripts\u002Fvalidate_workflow.py .claude\u002Fworkflows\u002Fpr-triage.js\n   ```\n4. **Run** it: enable the feature with `export CLAUDE_CODE_WORKFLOWS=1`, save the file under `.claude\u002Fworkflows\u002F`, then use `\u002Fworkflows` to launch and watch it live. Press **P** to pause\u002Fresume, **X** to skip a sub-agent. Failed agents retry automatically.\n\n## Hard rules (validator enforces these)\n\n- `meta` is a **pure literal** and the **first statement** — no variables, spreads, template strings, or function calls inside it.\n- **No non-determinism:** `Date.now()`, `Math.random()`, argless `new Date()` break resume — pass timestamps via `args`.\n- **No filesystem \u002F Node APIs** (`require`, `fs`, `process`, network) in the orchestrator — that work belongs *inside* `agent()` prompts.\n- `parallel()` takes **thunks** (`() => agent(...)`), not bare promises. Default to `pipeline()` unless a stage needs the whole prior result set.\n- **Guard every open-ended loop** with a counter or `budget.remaining()` check — unguarded loops hit the 1000-agent cap.\n- Filter skipped\u002Ffailed agents: `results.filter(Boolean)`.\n\n## Tooling\n\n- `scripts\u002Fworkflow_intake.py` — intake recommendation engine (topology + model + budget + rationale from vague input).\n- `scripts\u002Fvalidate_workflow.py` — stdlib linter for the rules above; PASS \u002F WARN \u002F FAIL with line numbers.\n- `scripts\u002Fscaffold_workflow.py` — generate a starter `.js` for any topology.\n- `assets\u002Ftemplates\u002F` — fan-out, pipeline, loop-until-budget starters. `assets\u002Fexamples\u002F` — a complete runnable workflow.\n\nAll scripts run with `--sample` (no args) and `--help`.\n",{"name":5,"license":14,"metadata":48,"description":7},{"targets":49,"version":50,"inspired_by":51},"Claude Code Workflow tool (CLAUDE_CODE_WORKFLOWS=1, \u002Fworkflows)","1.0.0","https:\u002F\u002Fgithub.com\u002Fray-amjad\u002Fclaude-code-workflow-creator (Ray Amjad)","claude\u002Fai-personal-assistant-main","fb33f7f5b3a206eb019c788e3c48e91c02ccb1f9",".claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder",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":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add marshadgani\u002FArshad.AI --skill workflow-builder",{"tool":66,"command":67},"bunx","bunx skills add marshadgani\u002FArshad.AI --skill workflow-builder",{"tool":69,"command":70},"pnpm","pnpm dlx skills add marshadgani\u002FArshad.AI --skill workflow-builder","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\u002Fworkflow-builder\u002FSKILL.md",true,[74,80,84,88,92,98,102,106,110,114,118,122,126,130],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"assets\u002Fexamples\u002Fpr-triage.js","SCRIPT","脚本",3610,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Fassets\u002Fexamples\u002Fpr-triage.js",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"assets\u002Ftemplates\u002Ffan-out.js",1127,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Fassets\u002Ftemplates\u002Ffan-out.js",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"assets\u002Ftemplates\u002Floop-until-budget.js",1203,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Fassets\u002Ftemplates\u002Floop-until-budget.js",{"path":89,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":90,"sourceHtmlUrl":91},"assets\u002Ftemplates\u002Fpipeline.js",1250,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Fassets\u002Ftemplates\u002Fpipeline.js",{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"expected_outputs\u002Fintake_pr_review.json","REFERENCE","参考文档",1206,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Fexpected_outputs\u002Fintake_pr_review.json",{"path":99,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":100,"sourceHtmlUrl":101},"expected_outputs\u002Fscaffold_pipeline.js",1233,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Fexpected_outputs\u002Fscaffold_pipeline.js",{"path":103,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":104,"sourceHtmlUrl":105},"expected_outputs\u002Fvalidate_sample.txt",555,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Fexpected_outputs\u002Fvalidate_sample.txt",{"path":107,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":108,"sourceHtmlUrl":109},"README.md",1468,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002FREADME.md",{"path":111,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Fapi_reference.md",6413,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Freferences\u002Fapi_reference.md",{"path":115,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Fdecision_and_intake_guide.md",5948,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Freferences\u002Fdecision_and_intake_guide.md",{"path":119,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Forchestration_patterns.md",5522,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Freferences\u002Forchestration_patterns.md",{"path":123,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":124,"sourceHtmlUrl":125},"scripts\u002Fscaffold_workflow.py",6816,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Fscripts\u002Fscaffold_workflow.py",{"path":127,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":128,"sourceHtmlUrl":129},"scripts\u002Fvalidate_workflow.py",10940,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Fscripts\u002Fvalidate_workflow.py",{"path":131,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":132,"sourceHtmlUrl":133},"scripts\u002Fworkflow_intake.py",10485,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fworkflow-builder\u002Fscripts\u002Fworkflow_intake.py",[135,168,193,221,249,273],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":139,"licenseFileUrl":140,"sourceHtmlUrl":141,"categories":142,"keywords":149,"publishedAt":167},"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",[143,146],{"categoryNo":144,"categoryName":145,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":147,"categoryName":148,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166],"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":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":139,"licenseFileUrl":172,"sourceHtmlUrl":173,"categories":174,"keywords":176,"publishedAt":167},"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",[175],{"categoryNo":147,"categoryName":148,"taxonomyType":20,"taxonomyTypeDesc":21},[25,177,178,163,179,180,181,153,182,183,156,184,185,186,187,188,189,190,191,192],"artifacts builder","artifacts","web artifacts builder","single-file","css","Tailwind","ui components","single","use","file","components","react","multi","state","routing","state management",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":197,"sourceHtmlUrl":198,"categories":199,"keywords":208,"publishedAt":167},"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",[200,203],{"categoryNo":201,"categoryName":202,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":204,"categoryName":205,"taxonomyType":206,"taxonomyTypeDesc":207},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[209,210,165,181,182,211,212,213,39,214,215,216,35,187,33,31,217,218,219,220],"ui styling","styling","mode","canvas","implementing","themes","utility","design systems","component","layout","forms","patterns",{"skillNo":222,"name":39,"nameZh":6,"description":223,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":224,"categories":225,"keywords":232,"publishedAt":167},"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",[226,229,230,231],{"categoryNo":227,"categoryName":228,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":201,"categoryName":202,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":204,"categoryName":205,"taxonomyType":206,"taxonomyTypeDesc":207},[39,233,234,235,209,236,237,238,239,31,240,241,242,243,244,245,246,247,165,248],"Media","tiktok","actions","logo","logo generation","chart","multi-platform","ads","youtube","generate","presentations","google","atlas cloud","screenshot","muapi","identity",{"skillNo":250,"name":251,"nameZh":6,"description":252,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":253,"categories":254,"keywords":257,"publishedAt":167},"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",[255,256],{"categoryNo":201,"categoryName":202,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":204,"categoryName":205,"taxonomyType":206,"taxonomyTypeDesc":207},[39,258,259,181,260,261,262,263,217,243,264,265,266,267,268,269,270,153,271,272],"design system","system","css variables","creation","Variables","architecture","systematic","token","spacing","layer","typography","brand","three","tokens","slide generation",{"skillNo":274,"name":275,"nameZh":6,"description":276,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":277,"categories":278,"keywords":281,"publishedAt":167},"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",[279,280],{"categoryNo":201,"categoryName":202,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":204,"categoryName":205,"taxonomyType":206,"taxonomyTypeDesc":207},[39,282,283,233,284,285,286,235,287,288,289,290,291,292,31,240,241,242,293,294],"banner","banner design","3D","direction","neon","Art","social","generated","hero","dimensions","display","options","website"]