[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EBK0ZQQJTBDARGPCVYAD1F":3,"skill-same:01M7EBK0ZQQJTBDARGPCVYAD1F":86},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7EBK0ZQQJTBDARGPCVYAD1F","imagegen-gemini",null,"Generate or edit raster images with Gemini (Nano Banana): photos, illustrations, textures, sprites, mockups, character cutouts, transparent-background subjects, batches of variants. Use when the output should be a bitmap asset rather than SVG, vector, or code-native visuals.","joaodavidsilva\u002Fskills","joaodavidsilva","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7389336?v=4","01M7EBJ7HADRG745ZRNHB763EW","João David Silva","01M7EBJ7HYJE4BVXESTBNW1BJ1",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fimagegen-gemini\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: imagegen-gemini\ndescription: \"Generate or edit raster images with Gemini (Nano Banana): photos, illustrations, textures, sprites, mockups, character cutouts, transparent-background subjects, batches of variants. Use when the output should be a bitmap asset rather than SVG, vector, or code-native visuals.\"\n---\n\n# Image Generation (Gemini)\n\nGenerates or edits bitmap images for the current project through the bundled `scripts\u002Fimage_gen.py`, which calls the Gemini Image API. Standard library only; needs `GEMINI_API_KEY` in the environment.\n\n## Fit\n\nReach for it when the asset is a photo, illustration, texture, sprite, mockup, or cutout. Build diagrams, icons, logos that extend an existing SVG system, and anything deterministic directly in SVG, HTML\u002FCSS, or canvas. A real screenshot or existing project art beats a generated stand-in.\n\n## Workflow\n\n1. **Intent.** Edit when the user wants to change an existing image while keeping parts of it. Generate when images are only style or subject references, or when none are given.\n2. **Destination.** Project-bound output goes into the workspace (user-named path, else `output\u002Fimagegen\u002F`). Preview-only output can stay in `tmp\u002Fimagegen\u002F`.\n3. **Inputs.** Collect the prompt, exact text (verbatim), constraints, and input images. Give each image a role: edit target (first `--image`) or reference.\n4. **Prompt.** Write the labeled spec below and read [reference\u002FPROMPTING.md](reference\u002FPROMPTING.md) for specificity, text, and edit invariants. Copy-paste recipes per asset type: [reference\u002FSAMPLE-PROMPTS.md](reference\u002FSAMPLE-PROMPTS.md).\n5. **Run.** Execute the script (see [reference\u002FCLI.md](reference\u002FCLI.md) for flags, models, batch, and troubleshooting):\n   ```bash\n   python3 scripts\u002Fimage_gen.py generate --prompt \"...\" --aspect-ratio 16:9 --size 2K --out output\u002Fimagegen\u002Fhero.jpg\n   ```\n   Many distinct assets: one `generate-batch` JSONL job per asset. Variants of one prompt: `--n`. Resolve `scripts\u002F` against this skill's directory.\n6. **Transparent subject.** Gemini returns opaque pixels. Read [reference\u002FTRANSPARENCY.md](reference\u002FTRANSPARENCY.md): generate on a flat key color, then remove it with `scripts\u002Fremove_chroma_key.py`.\n7. **Inspect.** Open every output and check subject, style, composition, text accuracy, and the constraints. Iterate with one targeted change, repeating the invariants each time.\n8. **Deliver.** Done when every requested file sits at its destination and you have reported, per asset: saved path, final prompt, and model. Keep only selected finals; delete discarded variants and scratch files unless asked to keep them. Existing assets are replaced only on explicit request; otherwise save a sibling such as `hero-v2.jpg`.\n\nIf a missing detail blocks success, ask one question; otherwise proceed.\n\n## Prompt spec\n\nUse only the lines that help. Keep specific prompts specific (normalize, do not expand); enrich generic ones with composition, polish level, and practical layout cues only.\n\n```text\nUse case: \u003Ctaxonomy slug>\nAsset type: \u003Cwhere the asset will be used>\nPrimary request: \u003Cuser's main prompt>\nInput images: \u003CImage 1: role; Image 2: role>\nScene\u002Fbackdrop: \u003Cenvironment>\nSubject: \u003Cmain subject>\nStyle\u002Fmedium: \u003Cphoto\u002Fillustration\u002F3D\u002Fetc>\nComposition\u002Fframing: \u003Cwide\u002Fclose\u002Ftop-down; placement>\nLighting\u002Fmood: \u003Clighting + mood>\nColor palette: \u003Cpalette notes>\nMaterials\u002Ftextures: \u003Csurface details>\nText (verbatim): \"\u003Cexact text>\"\nConstraints: \u003Cmust keep \u002F must have>\nAvoid: \u003Cdescribed positively, e.g. \"an empty street\" instead of \"no cars\">\n```\n\nThe script builds this spec from flags (`--use-case`, `--scene`, `--subject`, ...) and labels input images itself. `--no-augment` sends a hand-written prompt verbatim.\n\n### Use-case slugs\n\nGenerate: `photorealistic-natural`, `product-mockup`, `ui-mockup`, `infographic-diagram`, `scientific-educational`, `ads-marketing`, `productivity-visual`, `logo-brand`, `illustration-story`, `stylized-concept`, `historical-scene`.\n\nEdit: `text-localization`, `identity-preserve`, `precise-object-edit`, `lighting-weather`, `background-extraction`, `style-transfer`, `compositing`, `sketch-to-render`.\n\n## Reference map\n\n- [reference\u002FCLI.md](reference\u002FCLI.md): script flags, models, sizes, aspect ratios, batch JSONL, API key setup.\n- [reference\u002FTRANSPARENCY.md](reference\u002FTRANSPARENCY.md): chroma-key workflow and validation for cutouts.\n- [reference\u002FPROMPTING.md](reference\u002FPROMPTING.md): prompt principles and per-use-case tips.\n- [reference\u002FSAMPLE-PROMPTS.md](reference\u002FSAMPLE-PROMPTS.md): recipes for websites, games, wireframes, logos, edits.\n","# Image Generation (Gemini)\n\nGenerates or edits bitmap images for the current project through the bundled `scripts\u002Fimage_gen.py`, which calls the Gemini Image API. Standard library only; needs `GEMINI_API_KEY` in the environment.\n\n## Fit\n\nReach for it when the asset is a photo, illustration, texture, sprite, mockup, or cutout. Build diagrams, icons, logos that extend an existing SVG system, and anything deterministic directly in SVG, HTML\u002FCSS, or canvas. A real screenshot or existing project art beats a generated stand-in.\n\n## Workflow\n\n1. **Intent.** Edit when the user wants to change an existing image while keeping parts of it. Generate when images are only style or subject references, or when none are given.\n2. **Destination.** Project-bound output goes into the workspace (user-named path, else `output\u002Fimagegen\u002F`). Preview-only output can stay in `tmp\u002Fimagegen\u002F`.\n3. **Inputs.** Collect the prompt, exact text (verbatim), constraints, and input images. Give each image a role: edit target (first `--image`) or reference.\n4. **Prompt.** Write the labeled spec below and read [reference\u002FPROMPTING.md](reference\u002FPROMPTING.md) for specificity, text, and edit invariants. Copy-paste recipes per asset type: [reference\u002FSAMPLE-PROMPTS.md](reference\u002FSAMPLE-PROMPTS.md).\n5. **Run.** Execute the script (see [reference\u002FCLI.md](reference\u002FCLI.md) for flags, models, batch, and troubleshooting):\n   ```bash\n   python3 scripts\u002Fimage_gen.py generate --prompt \"...\" --aspect-ratio 16:9 --size 2K --out output\u002Fimagegen\u002Fhero.jpg\n   ```\n   Many distinct assets: one `generate-batch` JSONL job per asset. Variants of one prompt: `--n`. Resolve `scripts\u002F` against this skill's directory.\n6. **Transparent subject.** Gemini returns opaque pixels. Read [reference\u002FTRANSPARENCY.md](reference\u002FTRANSPARENCY.md): generate on a flat key color, then remove it with `scripts\u002Fremove_chroma_key.py`.\n7. **Inspect.** Open every output and check subject, style, composition, text accuracy, and the constraints. Iterate with one targeted change, repeating the invariants each time.\n8. **Deliver.** Done when every requested file sits at its destination and you have reported, per asset: saved path, final prompt, and model. Keep only selected finals; delete discarded variants and scratch files unless asked to keep them. Existing assets are replaced only on explicit request; otherwise save a sibling such as `hero-v2.jpg`.\n\nIf a missing detail blocks success, ask one question; otherwise proceed.\n\n## Prompt spec\n\nUse only the lines that help. Keep specific prompts specific (normalize, do not expand); enrich generic ones with composition, polish level, and practical layout cues only.\n\n```text\nUse case: \u003Ctaxonomy slug>\nAsset type: \u003Cwhere the asset will be used>\nPrimary request: \u003Cuser's main prompt>\nInput images: \u003CImage 1: role; Image 2: role>\nScene\u002Fbackdrop: \u003Cenvironment>\nSubject: \u003Cmain subject>\nStyle\u002Fmedium: \u003Cphoto\u002Fillustration\u002F3D\u002Fetc>\nComposition\u002Fframing: \u003Cwide\u002Fclose\u002Ftop-down; placement>\nLighting\u002Fmood: \u003Clighting + mood>\nColor palette: \u003Cpalette notes>\nMaterials\u002Ftextures: \u003Csurface details>\nText (verbatim): \"\u003Cexact text>\"\nConstraints: \u003Cmust keep \u002F must have>\nAvoid: \u003Cdescribed positively, e.g. \"an empty street\" instead of \"no cars\">\n```\n\nThe script builds this spec from flags (`--use-case`, `--scene`, `--subject`, ...) and labels input images itself. `--no-augment` sends a hand-written prompt verbatim.\n\n### Use-case slugs\n\nGenerate: `photorealistic-natural`, `product-mockup`, `ui-mockup`, `infographic-diagram`, `scientific-educational`, `ads-marketing`, `productivity-visual`, `logo-brand`, `illustration-story`, `stylized-concept`, `historical-scene`.\n\nEdit: `text-localization`, `identity-preserve`, `precise-object-edit`, `lighting-weather`, `background-extraction`, `style-transfer`, `compositing`, `sketch-to-render`.\n\n## Reference map\n\n- [reference\u002FCLI.md](reference\u002FCLI.md): script flags, models, sizes, aspect ratios, batch JSONL, API key setup.\n- [reference\u002FTRANSPARENCY.md](reference\u002FTRANSPARENCY.md): chroma-key workflow and validation for cutouts.\n- [reference\u002FPROMPTING.md](reference\u002FPROMPTING.md): prompt principles and per-use-case tips.\n- [reference\u002FSAMPLE-PROMPTS.md](reference\u002FSAMPLE-PROMPTS.md): recipes for websites, games, wireframes, logos, edits.\n",{"name":5,"description":7},"main","43f20093cbb9c7c6c53205d079f1a6ed38e8f409","skills\u002Fdesign\u002Fimagegen-gemini","https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills","https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva","2026-11-13 00:08:54",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add joaodavidsilva\u002Fskills --skill imagegen-gemini",{"tool":36,"command":37},"bunx","bunx skills add joaodavidsilva\u002Fskills --skill imagegen-gemini",{"tool":39,"command":40},"pnpm","pnpm dlx skills add joaodavidsilva\u002Fskills --skill imagegen-gemini","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fimagegen-gemini\u002FSKILL.md",true,[44,50,56,60,64,68,72,76,82],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"agents\u002Fopenai.yaml","REFERENCE","参考文档",281,"https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fimagegen-gemini\u002Fagents\u002Fopenai.yaml",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"assets\u002Fimagegen-small.svg","ASSET","资产文件",2889,"https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fimagegen-gemini\u002Fassets\u002Fimagegen-small.svg",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"assets\u002Fimagegen.png",1711,"https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fimagegen-gemini\u002Fassets\u002Fimagegen.png",{"path":61,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":62,"sourceHtmlUrl":63},"reference\u002FCLI.md",5169,"https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fimagegen-gemini\u002Freference\u002FCLI.md",{"path":65,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":66,"sourceHtmlUrl":67},"reference\u002FPROMPTING.md",7728,"https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fimagegen-gemini\u002Freference\u002FPROMPTING.md",{"path":69,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":70,"sourceHtmlUrl":71},"reference\u002FSAMPLE-PROMPTS.md",16975,"https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fimagegen-gemini\u002Freference\u002FSAMPLE-PROMPTS.md",{"path":73,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":74,"sourceHtmlUrl":75},"reference\u002FTRANSPARENCY.md",1840,"https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fimagegen-gemini\u002Freference\u002FTRANSPARENCY.md",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Fimage_gen.py","SCRIPT","脚本",15017,"https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fimagegen-gemini\u002Fscripts\u002Fimage_gen.py",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Fremove_chroma_key.py",13682,"https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fimagegen-gemini\u002Fscripts\u002Fremove_chroma_key.py",[87,94,101,108,115,122],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7EBP8DHWNBT1JDGBE3F1C4E","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fwait-what\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7EBP6K4KE65Y6SHNXF6DZR9","to-questionnaire","Turn a decision you can't fully answer into a questionnaire for someone else to fill in.","https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fto-questionnaire\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7EBP4SF3TXCPYD5VCFHFYB9","teach","Teach the user a new skill or concept, within this workspace.","https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fteach\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7EBP2HG07RF956W8SEK006K","research","Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.","https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fresearch\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M7EBNYSRH90G1HJDSJS5KD41","prototype","Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.","https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fprototype\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":19},"01M7EBNWZY0J8K21XPS21RFGNF","grilling","Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.","https:\u002F\u002Fgithub.com\u002Fjoaodavidsilva\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fgrilling\u002FSKILL.md",[],[]]