[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DM4JBQ8K0B18VR4638MSXR":3,"skill-same:01M7DM4JBQ8K0B18VR4638MSXR":76},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":52,"install":53,"resources":66},"01M7DM4JBQ8K0B18VR4638MSXR","ecommerce-image-workflow",null,"Reference-product ecommerce image workflow for generating a compact set\nof product-faithful main, feature, and lifestyle images from real product\nreference photos. V1 requires uploaded product imagery and intentionally\ndefers brief-only concept generation and platform-specific batch exports.","andremolnar\u002Fopen-open-design","andremolnar","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F919644?v=4","01M7DHE1X4QH6SJBHR92VG5N84","01M7DHE1XRHK1WQV34AM9M328E",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fandremolnar\u002Fopen-open-design\u002Fblob\u002Fmain\u002Fskills\u002Fecommerce-image-workflow\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ecommerce-image-workflow\nen_name: \"Ecommerce Image Workflow\"\ndescription: |\n  Reference-product ecommerce image workflow for generating a compact set\n  of product-faithful main, feature, and lifestyle images from real product\n  reference photos. V1 requires uploaded product imagery and intentionally\n  defers brief-only concept generation and platform-specific batch exports.\ntriggers:\n  - \"ecommerce product images\"\n  - \"product image set\"\n  - \"product photography workflow\"\n  - \"product main image\"\n  - \"product feature shot\"\n  - \"reference product commerce images\"\n  - \"lifestyle product image\"\n  - \"amazon product images\"\n  - \"shopify product images\"\n  - \"taobao product images\"\nod:\n  mode: image\n  surface: image\n  category: image-generation\n  scenario: marketing\n  preview:\n    type: html\n    entry: example.html\n  design_system:\n    requires: false\n  example_prompt: |\n    Use the Ecommerce Image Workflow to turn my uploaded product reference\n    photo into a compact ecommerce image set: one main packshot, one feature\n    highlight image, and one lifestyle scene. Preserve the exact product\n    identity, color, material, logo placement, structure, and proportions.\n---\n\n# Ecommerce Image Workflow\n\nCreate a compact ecommerce image set from real product reference imagery.\nThis V1 skill is intentionally narrow: it supports **reference-product mode\nonly**. If the user only describes a product and does not provide a product\nphoto, ask for one and stop. Do not create a brief-only concept product in\nthis version.\n\n## Resource map\n\n```text\necommerce-image-workflow\u002F\n|-- SKILL.md\n|-- example.html\n`-- references\u002F\n    `-- checklist.md\n```\n\n## What this skill produces\n\nBy default, generate three ecommerce-ready image assets for one product:\n\n1. **Main image** - clean product-first packshot on white or soft neutral\n   background.\n2. **Feature image** - one selling point shown clearly with controlled callout\n   space, without relying on tiny unreadable in-image text.\n3. **Lifestyle image** - product shown in a plausible use context while keeping\n   the product faithful to the reference.\n\nAlso create:\n\n- `image-manifest.json` describing reference inputs, slots, prompts, outputs,\n  aspect ratios, and fidelity notes.\n- `ecommerce-gallery.html` as a small preview gallery linking the generated\n  files and summarizing the image roles.\n\n## Input contract\n\nRequired:\n\n- At least one uploaded product reference image in the active project.\n\nAsk only for missing essentials:\n\n- Product name or short label if it is not obvious.\n- Main selling point if the feature image cannot be inferred safely.\n- Target marketplace or aspect only if the user asks for platform-specific\n  framing.\n\nDo not ask broad discovery questions. Keep the workflow moving.\n\n## Workflow\n\n### Step 0 - Confirm reference-product mode\n\nBefore planning, verify that the current project includes a real product\nreference image.\n\nIf no product image is available, reply:\n\n> Please upload at least one product reference image first. This V1 workflow\n> preserves a real product from reference photos; brief-only concept generation\n> is deferred to a later version.\n\nThen stop.\n\n### Step 1 - Extract product identity anchors\n\nInspect the reference image and write a short internal identity lock:\n\n- Product category and form factor.\n- Shape and silhouette.\n- Primary colors and materials.\n- Logo, label, pattern, fasteners, ports, straps, handles, or other fixed\n  details.\n- Scale cues and proportions.\n- What must not change.\n\nUse these anchors in every generation prompt.\n\n### Step 2 - Build a three-slot shot plan\n\nCreate a compact shot plan before dispatch:\n\n| Slot | Default aspect | Goal |\n|---|---:|---|\n| main | 1:1 | Product-first marketplace image on white or soft neutral background |\n| feature | 4:5 | One clear selling point with close-up detail or simple callout space |\n| lifestyle | 4:5 | Realistic use context with the product still visually faithful |\n\nIf the project metadata provides `imageAspect`, use it when the user expects a\nsingle aspect across the set. Otherwise use the slot defaults above.\n\n### Step 3 - Compose prompts with a fidelity lock\n\nEvery prompt must include this product fidelity instruction near the top:\n\n```text\nPreserve the exact product identity from the reference image: shape,\nsilhouette, color, material, logo\u002Flabel placement, visible construction\ndetails, and proportions. Do not redesign the product. Do not add, remove,\nor relocate product features.\n```\n\nThen add slot-specific instructions:\n\n#### Main image prompt\n\n- Product centered and fully visible.\n- White, off-white, or very light grey background.\n- Soft studio lighting with clean shadow.\n- No props unless the user asked for them.\n- No in-frame marketing text.\n\n#### Feature image prompt\n\n- Focus on one user-provided or safely inferred feature.\n- Use close-up composition, cutaway-style crop, or clean negative space for\n  later designer-added labels.\n- Keep the product visually balanced in the frame. If no explicit callout\n  structure is being generated, center the product. If label space is needed,\n  offset the product only slightly and make the empty space feel intentional.\n- Do not invent certifications, performance numbers, materials, or claims.\n- Avoid tiny rendered text; leave label space instead.\n\n#### Lifestyle image prompt\n\n- Use a realistic environment matched to the product category.\n- Keep the product the focal point.\n- Show human interaction only if it helps explain use and does not obscure the\n  product.\n- Preserve product scale and structure.\n\n### Step 4 - Dispatch through the media contract\n\nUse the unified OpenDesign media dispatcher. Do not call provider APIs or\ncustom model commands directly.\n\nFor each slot, run the standard generate\u002Fwait loop:\n\n```bash\n# POSIX bash. Do not call provider APIs directly.\nout=$(\"$OD_NODE_BIN\" \"$OD_BIN\" media generate \\\n  --project \"$OD_PROJECT_ID\" \\\n  --surface image \\\n  --model \"\u003CimageModel from metadata>\" \\\n  --aspect \"\u003Cslot aspect or imageAspect from metadata>\" \\\n  --image \"\u003Cproject-relative product reference image>\" \\\n  --output \"\u003Cproduct-slug>-\u003Cslot>.png\" \\\n  --prompt \"\u003Cfull slot prompt>\")\nec=$?\nif [ \"$ec\" -ne 0 ]; then echo \"$out\" >&2; exit \"$ec\"; fi\n\nlast=$(printf '%s\\n' \"$out\" | tail -1)\ntask_id=$(printf '%s\\n' \"$last\" |\n  python3 -c \"import sys,json; d=json.load(sys.stdin); print(d.get('taskId',''))\" 2>\u002Fdev\u002Fnull)\nsince=$(printf '%s\\n' \"$last\" |\n  python3 -c \"import sys,json; d=json.load(sys.stdin); print(d.get('nextSince',0))\" 2>\u002Fdev\u002Fnull)\nsince=\"${since:-0}\"\n\nwhile [ -n \"$task_id\" ]; do\n  out=$(\"$OD_NODE_BIN\" \"$OD_BIN\" media wait \"$task_id\" --since \"$since\")\n  ec=$?\n  last=$(printf '%s\\n' \"$out\" | tail -1)\n  since=$(printf '%s\\n' \"$last\" |\n    python3 -c \"import sys,json; d=json.load(sys.stdin); print(d.get('nextSince',0))\" 2>\u002Fdev\u002Fnull)\n  since=\"${since:-0}\"\n  if [ \"$ec\" -eq 0 ]; then\n    task_id=\"\"\n  elif [ \"$ec\" -ne 2 ]; then\n    echo \"$out\" >&2\n    exit \"$ec\"\n  fi\ndone\n\nprintf '%s\\n' \"$last\"\n```\n\nThe final line must be JSON with `{\"file\": {\"name\": \"...\", ...}}`.\nRecord each final returned filename in `image-manifest.json`.\n\nIf the active image model or provider cannot use `--image`, stop and tell the\nuser that this workflow needs a reference-capable image generation path for\nproduct fidelity.\n\n### Step 5 - Write `image-manifest.json`\n\nAfter generation, create a project file named `image-manifest.json`:\n\n```json\n{\n  \"workflow\": \"ecommerce-image-workflow\",\n  \"mode\": \"reference-product\",\n  \"productName\": \"Example product\",\n  \"referenceImages\": [\"reference-product.png\"],\n  \"fidelityNotes\": [\n    \"Preserve product identity, color, material, construction, and proportions.\",\n    \"Do not treat these outputs as platform-compliance proof without human review.\"\n  ],\n  \"slots\": [\n    {\n      \"id\": \"main\",\n      \"role\": \"marketplace packshot\",\n      \"aspect\": \"1:1\",\n      \"output\": \"example-product-main.png\",\n      \"promptSummary\": \"Centered product-first packshot on a clean neutral background.\"\n    },\n    {\n      \"id\": \"feature\",\n      \"role\": \"single feature highlight\",\n      \"aspect\": \"4:5\",\n      \"output\": \"example-product-feature.png\",\n      \"promptSummary\": \"Close-up or negative-space composition for one verified selling point.\"\n    },\n    {\n      \"id\": \"lifestyle\",\n      \"role\": \"usage context\",\n      \"aspect\": \"4:5\",\n      \"output\": \"example-product-lifestyle.png\",\n      \"promptSummary\": \"Realistic scene with the product as the focal point.\"\n    }\n  ]\n}\n```\n\nKeep the manifest honest. If a detail is unknown, write `null` or a short note\ninstead of inventing claims.\n\n### Step 6 - Write `ecommerce-gallery.html`\n\nCreate a simple single-file HTML gallery that:\n\n- Shows the reference image first.\n- Shows the three generated slots with their role names.\n- Lists product-fidelity notes.\n- Links to `image-manifest.json`.\n- Uses system fonts and local project files only; no CDN imports.\n\n### Step 7 - Hand off\n\nReply with:\n\n- The generated filenames.\n- A one-sentence summary of the fidelity lock used.\n- A reminder that marketplace-specific compliance, final text overlays, and\n  claim\u002Flegal review remain human review steps.\n\nDo not emit an `\u003Cartifact>` tag.\n\n## Hard rules\n\n- V1 requires real product reference imagery. No brief-only concept products.\n- One product per run.\n- Default to exactly three slots: main, feature, lifestyle.\n- Preserve the product; do not redesign it.\n- Do not invent claims, certifications, measurements, ingredients, or\n  performance data.\n- Use `\"$OD_NODE_BIN\" \"$OD_BIN\" media generate`; do not call provider APIs\n  directly.\n- Always create `image-manifest.json` after generation.\n- Run `references\u002Fchecklist.md` before handoff.\n","# Ecommerce Image Workflow\n\nCreate a compact ecommerce image set from real product reference imagery.\nThis V1 skill is intentionally narrow: it supports **reference-product mode\nonly**. If the user only describes a product and does not provide a product\nphoto, ask for one and stop. Do not create a brief-only concept product in\nthis version.\n\n## Resource map\n\n```text\necommerce-image-workflow\u002F\n|-- SKILL.md\n|-- example.html\n`-- references\u002F\n    `-- checklist.md\n```\n\n## What this skill produces\n\nBy default, generate three ecommerce-ready image assets for one product:\n\n1. **Main image** - clean product-first packshot on white or soft neutral\n   background.\n2. **Feature image** - one selling point shown clearly with controlled callout\n   space, without relying on tiny unreadable in-image text.\n3. **Lifestyle image** - product shown in a plausible use context while keeping\n   the product faithful to the reference.\n\nAlso create:\n\n- `image-manifest.json` describing reference inputs, slots, prompts, outputs,\n  aspect ratios, and fidelity notes.\n- `ecommerce-gallery.html` as a small preview gallery linking the generated\n  files and summarizing the image roles.\n\n## Input contract\n\nRequired:\n\n- At least one uploaded product reference image in the active project.\n\nAsk only for missing essentials:\n\n- Product name or short label if it is not obvious.\n- Main selling point if the feature image cannot be inferred safely.\n- Target marketplace or aspect only if the user asks for platform-specific\n  framing.\n\nDo not ask broad discovery questions. Keep the workflow moving.\n\n## Workflow\n\n### Step 0 - Confirm reference-product mode\n\nBefore planning, verify that the current project includes a real product\nreference image.\n\nIf no product image is available, reply:\n\n> Please upload at least one product reference image first. This V1 workflow\n> preserves a real product from reference photos; brief-only concept generation\n> is deferred to a later version.\n\nThen stop.\n\n### Step 1 - Extract product identity anchors\n\nInspect the reference image and write a short internal identity lock:\n\n- Product category and form factor.\n- Shape and silhouette.\n- Primary colors and materials.\n- Logo, label, pattern, fasteners, ports, straps, handles, or other fixed\n  details.\n- Scale cues and proportions.\n- What must not change.\n\nUse these anchors in every generation prompt.\n\n### Step 2 - Build a three-slot shot plan\n\nCreate a compact shot plan before dispatch:\n\n| Slot | Default aspect | Goal |\n|---|---:|---|\n| main | 1:1 | Product-first marketplace image on white or soft neutral background |\n| feature | 4:5 | One clear selling point with close-up detail or simple callout space |\n| lifestyle | 4:5 | Realistic use context with the product still visually faithful |\n\nIf the project metadata provides `imageAspect`, use it when the user expects a\nsingle aspect across the set. Otherwise use the slot defaults above.\n\n### Step 3 - Compose prompts with a fidelity lock\n\nEvery prompt must include this product fidelity instruction near the top:\n\n```text\nPreserve the exact product identity from the reference image: shape,\nsilhouette, color, material, logo\u002Flabel placement, visible construction\ndetails, and proportions. Do not redesign the product. Do not add, remove,\nor relocate product features.\n```\n\nThen add slot-specific instructions:\n\n#### Main image prompt\n\n- Product centered and fully visible.\n- White, off-white, or very light grey background.\n- Soft studio lighting with clean shadow.\n- No props unless the user asked for them.\n- No in-frame marketing text.\n\n#### Feature image prompt\n\n- Focus on one user-provided or safely inferred feature.\n- Use close-up composition, cutaway-style crop, or clean negative space for\n  later designer-added labels.\n- Keep the product visually balanced in the frame. If no explicit callout\n  structure is being generated, center the product. If label space is needed,\n  offset the product only slightly and make the empty space feel intentional.\n- Do not invent certifications, performance numbers, materials, or claims.\n- Avoid tiny rendered text; leave label space instead.\n\n#### Lifestyle image prompt\n\n- Use a realistic environment matched to the product category.\n- Keep the product the focal point.\n- Show human interaction only if it helps explain use and does not obscure the\n  product.\n- Preserve product scale and structure.\n\n### Step 4 - Dispatch through the media contract\n\nUse the unified OpenDesign media dispatcher. Do not call provider APIs or\ncustom model commands directly.\n\nFor each slot, run the standard generate\u002Fwait loop:\n\n```bash\n# POSIX bash. Do not call provider APIs directly.\nout=$(\"$OD_NODE_BIN\" \"$OD_BIN\" media generate \\\n  --project \"$OD_PROJECT_ID\" \\\n  --surface image \\\n  --model \"\u003CimageModel from metadata>\" \\\n  --aspect \"\u003Cslot aspect or imageAspect from metadata>\" \\\n  --image \"\u003Cproject-relative product reference image>\" \\\n  --output \"\u003Cproduct-slug>-\u003Cslot>.png\" \\\n  --prompt \"\u003Cfull slot prompt>\")\nec=$?\nif [ \"$ec\" -ne 0 ]; then echo \"$out\" >&2; exit \"$ec\"; fi\n\nlast=$(printf '%s\\n' \"$out\" | tail -1)\ntask_id=$(printf '%s\\n' \"$last\" |\n  python3 -c \"import sys,json; d=json.load(sys.stdin); print(d.get('taskId',''))\" 2>\u002Fdev\u002Fnull)\nsince=$(printf '%s\\n' \"$last\" |\n  python3 -c \"import sys,json; d=json.load(sys.stdin); print(d.get('nextSince',0))\" 2>\u002Fdev\u002Fnull)\nsince=\"${since:-0}\"\n\nwhile [ -n \"$task_id\" ]; do\n  out=$(\"$OD_NODE_BIN\" \"$OD_BIN\" media wait \"$task_id\" --since \"$since\")\n  ec=$?\n  last=$(printf '%s\\n' \"$out\" | tail -1)\n  since=$(printf '%s\\n' \"$last\" |\n    python3 -c \"import sys,json; d=json.load(sys.stdin); print(d.get('nextSince',0))\" 2>\u002Fdev\u002Fnull)\n  since=\"${since:-0}\"\n  if [ \"$ec\" -eq 0 ]; then\n    task_id=\"\"\n  elif [ \"$ec\" -ne 2 ]; then\n    echo \"$out\" >&2\n    exit \"$ec\"\n  fi\ndone\n\nprintf '%s\\n' \"$last\"\n```\n\nThe final line must be JSON with `{\"file\": {\"name\": \"...\", ...}}`.\nRecord each final returned filename in `image-manifest.json`.\n\nIf the active image model or provider cannot use `--image`, stop and tell the\nuser that this workflow needs a reference-capable image generation path for\nproduct fidelity.\n\n### Step 5 - Write `image-manifest.json`\n\nAfter generation, create a project file named `image-manifest.json`:\n\n```json\n{\n  \"workflow\": \"ecommerce-image-workflow\",\n  \"mode\": \"reference-product\",\n  \"productName\": \"Example product\",\n  \"referenceImages\": [\"reference-product.png\"],\n  \"fidelityNotes\": [\n    \"Preserve product identity, color, material, construction, and proportions.\",\n    \"Do not treat these outputs as platform-compliance proof without human review.\"\n  ],\n  \"slots\": [\n    {\n      \"id\": \"main\",\n      \"role\": \"marketplace packshot\",\n      \"aspect\": \"1:1\",\n      \"output\": \"example-product-main.png\",\n      \"promptSummary\": \"Centered product-first packshot on a clean neutral background.\"\n    },\n    {\n      \"id\": \"feature\",\n      \"role\": \"single feature highlight\",\n      \"aspect\": \"4:5\",\n      \"output\": \"example-product-feature.png\",\n      \"promptSummary\": \"Close-up or negative-space composition for one verified selling point.\"\n    },\n    {\n      \"id\": \"lifestyle\",\n      \"role\": \"usage context\",\n      \"aspect\": \"4:5\",\n      \"output\": \"example-product-lifestyle.png\",\n      \"promptSummary\": \"Realistic scene with the product as the focal point.\"\n    }\n  ]\n}\n```\n\nKeep the manifest honest. If a detail is unknown, write `null` or a short note\ninstead of inventing claims.\n\n### Step 6 - Write `ecommerce-gallery.html`\n\nCreate a simple single-file HTML gallery that:\n\n- Shows the reference image first.\n- Shows the three generated slots with their role names.\n- Lists product-fidelity notes.\n- Links to `image-manifest.json`.\n- Uses system fonts and local project files only; no CDN imports.\n\n### Step 7 - Hand off\n\nReply with:\n\n- The generated filenames.\n- A one-sentence summary of the fidelity lock used.\n- A reminder that marketplace-specific compliance, final text overlays, and\n  claim\u002Flegal review remain human review steps.\n\nDo not emit an `\u003Cartifact>` tag.\n\n## Hard rules\n\n- V1 requires real product reference imagery. No brief-only concept products.\n- One product per run.\n- Default to exactly three slots: main, feature, lifestyle.\n- Preserve the product; do not redesign it.\n- Do not invent claims, certifications, measurements, ingredients, or\n  performance data.\n- Use `\"$OD_NODE_BIN\" \"$OD_BIN\" media generate`; do not call provider APIs\n  directly.\n- Always create `image-manifest.json` after generation.\n- Run `references\u002Fchecklist.md` before handoff.\n",{"od":23,"name":5,"en_name":32,"triggers":33,"description":44},{"mode":24,"preview":25,"surface":24,"category":28,"scenario":29,"design_system":30,"example_prompt":31},"image",{"type":26,"entry":27},"html","example.html","image-generation","marketing",{"requires":19},"Use the Ecommerce Image Workflow to turn my uploaded product reference\nphoto into a compact ecommerce image set: one main packshot, one feature\nhighlight image, and one lifestyle scene. Preserve the exact product\nidentity, color, material, logo placement, structure, and proportions.","Ecommerce Image Workflow",[34,35,36,37,38,39,40,41,42,43],"ecommerce product images","product image set","product photography workflow","product main image","product feature shot","reference product commerce images","lifestyle product image","amazon product images","shopify product images","taobao product images","Reference-product ecommerce image workflow for generating a compact set\nof product-faithful main, feature, and lifestyle images from real product\nreference photos. V1 requires uploaded product imagery and intentionally\ndefers brief-only concept generation and platform-specific batch exports.\n","main","3a6721b94dec7506e324023f2855495c9c54d0d2","skills\u002Fecommerce-image-workflow",0,"https:\u002F\u002Fgithub.com\u002Fandremolnar\u002Fopen-open-design","https:\u002F\u002Fopen-design.ai","https:\u002F\u002Fgithub.com\u002Fandremolnar","2026-10-30 01:33:11",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add andremolnar\u002Fopen-open-design --skill ecommerce-image-workflow",{"tool":59,"command":60},"bunx","bunx skills add andremolnar\u002Fopen-open-design --skill ecommerce-image-workflow",{"tool":62,"command":63},"pnpm","pnpm dlx skills add andremolnar\u002Fopen-open-design --skill ecommerce-image-workflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fandremolnar\u002Fopen-open-design\u002Fblob\u002Fmain\u002Fskills\u002Fecommerce-image-workflow\u002FSKILL.md",true,[67,72],{"path":27,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"REFERENCE","参考文档",12014,"https:\u002F\u002Fgithub.com\u002Fandremolnar\u002Fopen-open-design\u002Fblob\u002Fmain\u002Fskills\u002Fecommerce-image-workflow\u002Fexample.html",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fchecklist.md",3188,"https:\u002F\u002Fgithub.com\u002Fandremolnar\u002Fopen-open-design\u002Fblob\u002Fmain\u002Fskills\u002Fecommerce-image-workflow\u002Freferences\u002Fchecklist.md",[77,84,91,98,105,114],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M7DMPDFNBD52ZP0GNY046Z2A","Beta Skill","Instruction-only fixture skill.","https:\u002F\u002Fgithub.com\u002Fandremolnar\u002Fopen-open-design\u002Fblob\u002Fmain\u002Ftools\u002Frelease\u002Ftests\u002Ffixtures\u002Fcatalog\u002Fskills\u002Fbeta\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M7DMPC4JJ8ENX7VWTMP38Y9C","Alpha Skill","First fixture skill with a runnable demo.","https:\u002F\u002Fgithub.com\u002Fandremolnar\u002Fopen-open-design\u002Fblob\u002Fmain\u002Ftools\u002Frelease\u002Ftests\u002Ffixtures\u002Fcatalog\u002Fskills\u002Falpha\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":18},"01M7DMP9J5BX307VWVD67J0BBM","Deck One","A small deck template fixture.","https:\u002F\u002Fgithub.com\u002Fandremolnar\u002Fopen-open-design\u002Fblob\u002Fmain\u002Ftools\u002Frelease\u002Ftests\u002Ffixtures\u002Fcatalog\u002Fdesign-templates\u002Fdeck-one\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":18},"01M7DMP7GNYTFXGK9RDZ2X723P","youtube-clipper","YouTube clip generation and editing with automated workflows — pull source video, slice highlights, add captions, and export.","https:\u002F\u002Fgithub.com\u002Fandremolnar\u002Fopen-open-design\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FSKILL.md",[],[],{"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":113,"publishedAt":18},"01M7DMP2WHMNKM0P5BXRYAG8D1","writing-guidelines","Review docs\u002Fprose for Writing Guidelines compliance. Use when asked to \"review my docs\", \"check writing style\", \"audit prose\", \"review docs voice and tone\", or \"check this page against the writing handbook\".","MIT","https:\u002F\u002Fgithub.com\u002Fandremolnar\u002Fopen-open-design\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-guidelines\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fandremolnar\u002Fopen-open-design\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-guidelines\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":18},"01M7DMP0GVJQ37CGXYQDD20VWS","wpds","WordPress Design System. Apply WordPress's official design tokens, typography, and component patterns to themes and sites.","https:\u002F\u002Fgithub.com\u002Fandremolnar\u002Fopen-open-design\u002Fblob\u002Fmain\u002Fskills\u002Fwpds\u002FSKILL.md",[],[]]