[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CBAMR8ZGRPZQW10624BPTB":3,"skill-same:01M7CBAMR8ZGRPZQW10624BPTB":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7CBAMR8ZGRPZQW10624BPTB","sf-diagram-nanobananapro",null,"AI-powered image generation for Salesforce visuals via Nano Banana Pro. TRIGGER when: user asks for PNG\u002FSVG output, UI mockups, wireframes, visual ERDs, or says \"generate image\" \u002F \"create mockup\". DO NOT TRIGGER when: text-based Mermaid diagrams (use sf-diagram-mermaid), or non-visual documentation tasks.","om-scogo\u002Fskillsh-scraper","om-scogo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160466840?v=4","01M79AWB6DFVCQ7RK70CS34B96","Om Achrekar","01M79AWB6ZM9SKR8KDH1WSSM22",0,"MIT","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-diagram-nanobananapro\u002Fskills\u002Fsf-diagram-nanobananapro\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sf-diagram-nanobananapro\ndescription: >\n  AI-powered image generation for Salesforce visuals via Nano Banana Pro.\n  TRIGGER when: user asks for PNG\u002FSVG output, UI mockups, wireframes, visual ERDs,\n  or says \"generate image\" \u002F \"create mockup\".\n  DO NOT TRIGGER when: text-based Mermaid diagrams (use sf-diagram-mermaid),\n  or non-visual documentation tasks.\nlicense: MIT\nmetadata:\n  version: \"1.5.0\"\n  author: \"Jag Valaiyapathy\"\n  scoring: \"80 points across 5 categories\"\n---\n\n# sf-diagram-nanobananapro: Salesforce Visual AI Skill\n\nUse this skill when the user needs **rendered visuals**, not text diagrams: ERDs, UI mockups, architecture illustrations, slide-ready images, or image edits using Nano Banana Pro.\n\n## Hard Gate: Prerequisites First\n\nAlways run the prerequisites check before using the skill:\n\n```bash\n~\u002F.claude\u002Fskills\u002Fsf-diagram-nanobananapro\u002Fscripts\u002Fcheck-prerequisites.sh\n```\n\nIf prerequisites fail, stop and route the user to setup guidance in:\n- [references\u002Fgemini-cli-setup.md](references\u002Fgemini-cli-setup.md)\n\n---\n\n## When This Skill Owns the Task\n\nUse `sf-diagram-nanobananapro` when the user wants:\n- PNG \u002F SVG-style image output\n- rendered ERDs or architecture diagrams\n- LWC or Experience Cloud mockups \u002F wireframes\n- visual polish beyond Mermaid\n- edits to a previously generated image\n\nDelegate elsewhere when the user wants:\n- Mermaid or text-only diagrams → [sf-diagram-mermaid](..\u002Fsf-diagram-mermaid\u002FSKILL.md)\n- metadata discovery for ERDs → [sf-metadata](..\u002Fsf-metadata\u002FSKILL.md)\n- LWC implementation after the mockup → [sf-lwc](..\u002Fsf-lwc\u002FSKILL.md)\n- Apex review \u002F implementation → [sf-apex](..\u002Fsf-apex\u002FSKILL.md)\n\n---\n\n## Required Context to Gather First\n\nAsk for or infer:\n- image type: ERD, UI mockup, architecture illustration, or image edit\n- subject scope and key entities \u002F systems\n- target quality: draft vs presentation vs production asset\n- preferred style and aspect ratio\n- whether the user wants quick mode or an interview-driven prompt build\n\n---\n\n## Interview-First Workflow\n\nUnless the user explicitly asks for **quick\u002Fsimple\u002Fjust generate**, ask clarifying questions first.\n\n### Minimum question set\n| Request type | Ask about |\n|---|---|\n| ERD \u002F schema | objects, visual style, purpose, extras |\n| UI mockup | component type, object\u002Fcontext, device\u002Flayout, style |\n| architecture image | systems, boundaries, protocols, emphasis |\n| image edit | what to keep, what to change, output quality |\n\nQuestion bank: [references\u002Finterview-questions.md](references\u002Finterview-questions.md)\n\n### Quick mode defaults\nIf the user says “quick”, “simple”, or “just generate”, default to:\n- professional style\n- 1K draft output\n- legend included when helpful\n- one image first, then iterate\n\n---\n\n## Recommended Workflow\n\n### 1. Gather inputs\nDecide which of these are needed:\n- object list \u002F metadata\n- purpose: draft vs presentation vs documentation\n- desired aesthetic\n- aspect ratio \u002F resolution\n- whether this is a fresh render or edit of an existing image\n\n### 2. Build a concrete prompt\nGood prompts specify:\n- subject and scope\n- composition \u002F layout\n- color treatment\n- labels \u002F legends \u002F relationship lines\n- output quality goal\n\n### 3. Generate a fast draft first\n```bash\ngemini --yolo \"\u002Fgenerate 'Professional Salesforce ERD with Account, Contact, Opportunity; clean legend; white background; Salesforce-style colors'\"\n```\n\n### 4. Iterate before final\nUse natural-language edits:\n```bash\ngemini --yolo \"\u002Fedit 'Move Account to center, thicken relationship lines, add legend in bottom right'\"\n```\n\n### 5. Use the Python script for controlled final output\nUse the script when you need higher resolution or explicit edit inputs:\n```bash\nuv run scripts\u002Fgenerate_image.py \\\n  -p \"Final production-quality Salesforce ERD with legend and field highlights\" \\\n  -f \"crm-erd-final.png\" \\\n  -r 4K\n```\n\nFull iteration guide: [references\u002Fiteration-workflow.md](references\u002Fiteration-workflow.md)\n\n---\n\n## Default Style Guidance\n\nFor ERDs, default to the **architect.salesforce.com** aesthetic unless the user asks otherwise:\n- dark border + light fill cards\n- cloud-specific accent colors\n- clean labels and relationship lines\n- presentation-ready whitespace and hierarchy\n\nStyle guide: [references\u002Farchitect-aesthetic-guide.md](references\u002Farchitect-aesthetic-guide.md)\n\n---\n\n## Common Patterns\n\n| Pattern | Default approach |\n|---|---|\n| visual ERD | get metadata if available, then render a draft first |\n| LWC mockup | use component template + user context + one draft iteration |\n| architecture illustration | emphasize systems and flows, reduce field-level detail |\n| image refinement | use `\u002Fedit` for small changes before regenerating |\n| final production asset | switch to script-driven 2K\u002F4K generation |\n\nExamples: [references\u002Fexamples-index.md](references\u002Fexamples-index.md)\n\n---\n\n## Output \u002F Review Guidance\n\nAfter generating, do one of these:\n- open the file in Preview for visual inspection\n- attach\u002Fread the image in the coding session for multimodal review\n- ask the user whether to iterate on layout, labeling, or color before finalizing\n\nKeep the first pass cheap; only spend on high-res output after the composition is right.\n\n---\n\n## Cross-Skill Integration\n\n| Need | Delegate to | Reason |\n|---|---|---|\n| Mermaid first draft or text diagram | [sf-diagram-mermaid](..\u002Fsf-diagram-mermaid\u002FSKILL.md) | faster structural diagramming |\n| object \u002F field discovery for ERD | [sf-metadata](..\u002Fsf-metadata\u002FSKILL.md) | accurate schema grounding |\n| turn mockup into real component | [sf-lwc](..\u002Fsf-lwc\u002FSKILL.md) | implementation after design |\n| review Apex \u002F trigger code in parallel | [sf-apex](..\u002Fsf-apex\u002FSKILL.md) | code-quality follow-up |\n\n---\n\n## Reference Map\n\n### Start here\n- [references\u002Fgemini-cli-setup.md](references\u002Fgemini-cli-setup.md)\n- [references\u002Finterview-questions.md](references\u002Finterview-questions.md)\n- [references\u002Fiteration-workflow.md](references\u002Fiteration-workflow.md)\n\n### Visual style \u002F examples\n- [references\u002Farchitect-aesthetic-guide.md](references\u002Farchitect-aesthetic-guide.md)\n- [references\u002Fexamples-index.md](references\u002Fexamples-index.md)\n- [assets\u002Ferd\u002F](assets\u002Ferd\u002F)\n- [assets\u002Flwc\u002F](assets\u002Flwc\u002F)\n- [assets\u002Farchitecture\u002F](assets\u002Farchitecture\u002F)\n- [assets\u002Freview\u002F](assets\u002Freview\u002F)\n\n---\n\n## Score Guide\n\n| Score | Meaning |\n|---|---|\n| 70+ | strong image prompt \u002F workflow choice |\n| 55–69 | usable draft with iteration needed |\n| 40–54 | partial alignment to request |\n| \u003C 40 | poor fit; re-interview and rebuild prompt |\n","# sf-diagram-nanobananapro: Salesforce Visual AI Skill\n\nUse this skill when the user needs **rendered visuals**, not text diagrams: ERDs, UI mockups, architecture illustrations, slide-ready images, or image edits using Nano Banana Pro.\n\n## Hard Gate: Prerequisites First\n\nAlways run the prerequisites check before using the skill:\n\n```bash\n~\u002F.claude\u002Fskills\u002Fsf-diagram-nanobananapro\u002Fscripts\u002Fcheck-prerequisites.sh\n```\n\nIf prerequisites fail, stop and route the user to setup guidance in:\n- [references\u002Fgemini-cli-setup.md](references\u002Fgemini-cli-setup.md)\n\n---\n\n## When This Skill Owns the Task\n\nUse `sf-diagram-nanobananapro` when the user wants:\n- PNG \u002F SVG-style image output\n- rendered ERDs or architecture diagrams\n- LWC or Experience Cloud mockups \u002F wireframes\n- visual polish beyond Mermaid\n- edits to a previously generated image\n\nDelegate elsewhere when the user wants:\n- Mermaid or text-only diagrams → [sf-diagram-mermaid](..\u002Fsf-diagram-mermaid\u002FSKILL.md)\n- metadata discovery for ERDs → [sf-metadata](..\u002Fsf-metadata\u002FSKILL.md)\n- LWC implementation after the mockup → [sf-lwc](..\u002Fsf-lwc\u002FSKILL.md)\n- Apex review \u002F implementation → [sf-apex](..\u002Fsf-apex\u002FSKILL.md)\n\n---\n\n## Required Context to Gather First\n\nAsk for or infer:\n- image type: ERD, UI mockup, architecture illustration, or image edit\n- subject scope and key entities \u002F systems\n- target quality: draft vs presentation vs production asset\n- preferred style and aspect ratio\n- whether the user wants quick mode or an interview-driven prompt build\n\n---\n\n## Interview-First Workflow\n\nUnless the user explicitly asks for **quick\u002Fsimple\u002Fjust generate**, ask clarifying questions first.\n\n### Minimum question set\n| Request type | Ask about |\n|---|---|\n| ERD \u002F schema | objects, visual style, purpose, extras |\n| UI mockup | component type, object\u002Fcontext, device\u002Flayout, style |\n| architecture image | systems, boundaries, protocols, emphasis |\n| image edit | what to keep, what to change, output quality |\n\nQuestion bank: [references\u002Finterview-questions.md](references\u002Finterview-questions.md)\n\n### Quick mode defaults\nIf the user says “quick”, “simple”, or “just generate”, default to:\n- professional style\n- 1K draft output\n- legend included when helpful\n- one image first, then iterate\n\n---\n\n## Recommended Workflow\n\n### 1. Gather inputs\nDecide which of these are needed:\n- object list \u002F metadata\n- purpose: draft vs presentation vs documentation\n- desired aesthetic\n- aspect ratio \u002F resolution\n- whether this is a fresh render or edit of an existing image\n\n### 2. Build a concrete prompt\nGood prompts specify:\n- subject and scope\n- composition \u002F layout\n- color treatment\n- labels \u002F legends \u002F relationship lines\n- output quality goal\n\n### 3. Generate a fast draft first\n```bash\ngemini --yolo \"\u002Fgenerate 'Professional Salesforce ERD with Account, Contact, Opportunity; clean legend; white background; Salesforce-style colors'\"\n```\n\n### 4. Iterate before final\nUse natural-language edits:\n```bash\ngemini --yolo \"\u002Fedit 'Move Account to center, thicken relationship lines, add legend in bottom right'\"\n```\n\n### 5. Use the Python script for controlled final output\nUse the script when you need higher resolution or explicit edit inputs:\n```bash\nuv run scripts\u002Fgenerate_image.py \\\n  -p \"Final production-quality Salesforce ERD with legend and field highlights\" \\\n  -f \"crm-erd-final.png\" \\\n  -r 4K\n```\n\nFull iteration guide: [references\u002Fiteration-workflow.md](references\u002Fiteration-workflow.md)\n\n---\n\n## Default Style Guidance\n\nFor ERDs, default to the **architect.salesforce.com** aesthetic unless the user asks otherwise:\n- dark border + light fill cards\n- cloud-specific accent colors\n- clean labels and relationship lines\n- presentation-ready whitespace and hierarchy\n\nStyle guide: [references\u002Farchitect-aesthetic-guide.md](references\u002Farchitect-aesthetic-guide.md)\n\n---\n\n## Common Patterns\n\n| Pattern | Default approach |\n|---|---|\n| visual ERD | get metadata if available, then render a draft first |\n| LWC mockup | use component template + user context + one draft iteration |\n| architecture illustration | emphasize systems and flows, reduce field-level detail |\n| image refinement | use `\u002Fedit` for small changes before regenerating |\n| final production asset | switch to script-driven 2K\u002F4K generation |\n\nExamples: [references\u002Fexamples-index.md](references\u002Fexamples-index.md)\n\n---\n\n## Output \u002F Review Guidance\n\nAfter generating, do one of these:\n- open the file in Preview for visual inspection\n- attach\u002Fread the image in the coding session for multimodal review\n- ask the user whether to iterate on layout, labeling, or color before finalizing\n\nKeep the first pass cheap; only spend on high-res output after the composition is right.\n\n---\n\n## Cross-Skill Integration\n\n| Need | Delegate to | Reason |\n|---|---|---|\n| Mermaid first draft or text diagram | [sf-diagram-mermaid](..\u002Fsf-diagram-mermaid\u002FSKILL.md) | faster structural diagramming |\n| object \u002F field discovery for ERD | [sf-metadata](..\u002Fsf-metadata\u002FSKILL.md) | accurate schema grounding |\n| turn mockup into real component | [sf-lwc](..\u002Fsf-lwc\u002FSKILL.md) | implementation after design |\n| review Apex \u002F trigger code in parallel | [sf-apex](..\u002Fsf-apex\u002FSKILL.md) | code-quality follow-up |\n\n---\n\n## Reference Map\n\n### Start here\n- [references\u002Fgemini-cli-setup.md](references\u002Fgemini-cli-setup.md)\n- [references\u002Finterview-questions.md](references\u002Finterview-questions.md)\n- [references\u002Fiteration-workflow.md](references\u002Fiteration-workflow.md)\n\n### Visual style \u002F examples\n- [references\u002Farchitect-aesthetic-guide.md](references\u002Farchitect-aesthetic-guide.md)\n- [references\u002Fexamples-index.md](references\u002Fexamples-index.md)\n- [assets\u002Ferd\u002F](assets\u002Ferd\u002F)\n- [assets\u002Flwc\u002F](assets\u002Flwc\u002F)\n- [assets\u002Farchitecture\u002F](assets\u002Farchitecture\u002F)\n- [assets\u002Freview\u002F](assets\u002Freview\u002F)\n\n---\n\n## Score Guide\n\n| Score | Meaning |\n|---|---|\n| 70+ | strong image prompt \u002F workflow choice |\n| 55–69 | usable draft with iteration needed |\n| 40–54 | partial alignment to request |\n| \u003C 40 | poor fit; re-interview and rebuild prompt |\n",{"name":5,"license":15,"metadata":24,"description":28},{"author":25,"scoring":26,"version":27},"Jag Valaiyapathy","80 points across 5 categories","1.5.0","AI-powered image generation for Salesforce visuals via Nano Banana Pro. TRIGGER when: user asks for PNG\u002FSVG output, UI mockups, wireframes, visual ERDs, or says \"generate image\" \u002F \"create mockup\". DO NOT TRIGGER when: text-based Mermaid diagrams (use sf-diagram-mermaid), or non-visual documentation tasks.\n","main","8859218955d9504cd18b59e7892100718039d3b4","data\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-diagram-nanobananapro\u002Fskills\u002Fsf-diagram-nanobananapro",1,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper","https:\u002F\u002Fgithub.com\u002Fom-scogo","SDE-1 @ Scogo ","2026-07-18 12:22:46",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add om-scogo\u002Fskillsh-scraper --skill sf-diagram-nanobananapro",{"tool":43,"command":44},"bunx","bunx skills add om-scogo\u002Fskillsh-scraper --skill sf-diagram-nanobananapro",{"tool":46,"command":47},"pnpm","pnpm dlx skills add om-scogo\u002Fskillsh-scraper --skill sf-diagram-nanobananapro","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-diagram-nanobananapro\u002Fskills\u002Fsf-diagram-nanobananapro\u002FSKILL.md",true,[],[52,59,64,71,76,83],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7D6MC9FAAEV4CMNYX8W7JTG","arxiv-search","Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002Fskills\u002Farxiv-search\u002FSKILL.md",[],[],{"skillNo":60,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7D6M85CKKN87TA98VCQV4H7","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002FSkill.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7D4ZTCS4DR3CE4JY06X84T2","working-with-legacy-code","Safely change and test untested codebases using Feathers' \"Working Effectively with Legacy Code\". Use when the user mentions \"legacy code\", \"no tests\", \"untested codebase\", \"how do I test this\", \"seams\", \"characterization tests\", \"golden master\", \"sprout method\", \"afraid to change this code\", \"monster method\", \"dependency breaking\", or \"inherited a messy codebase\". Also trigger when changing code without tests safely, getting a class under test when constructors, statics, or singletons block it, adding features to tangled modules, or planning incremental test coverage for an old codebase. Covers the legacy-code change algorithm, seams, characterization tests, sprout\u002Fwrap, and dependency-breaking techniques. For refactoring code that already has tests, see refactoring-patterns. For day-to-day code quality, see clean-code.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002Fworking-with-legacy-code\u002FSKILL.md",[],[],{"skillNo":72,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7D4ZHZKJD2RSNGAF63V14P4","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002FSkill.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7D4ZB4CJBFW5JE67CPH2QRV","web-typography","Select, pair, and implement typefaces for web projects. Use when the user mentions \"font pairing\", \"which typeface\", \"line height\", \"responsive typography\", \"web font loading\", \"type hierarchy\", \"variable fonts\", \"FOUT\u002FFOIT\", \"typographic scale\", or \"the text is hard to read\". Also trigger when choosing between system fonts and web fonts, optimizing font-loading performance, or designing readable long-form content. Covers readability evaluation, CSS implementation, and performance optimization. For overall UI design systems, see refactoring-ui. For dramatic typographic experiences, see top-design.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002Fweb-typography\u002FSKILL.md",[],[],{"skillNo":84,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7D4Z4MVYVY3NMJ18BNV6WNA","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002FSkill.md",[],[]]