[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X7P3PCEAKA2SBETXHHTNBA":3,"skill-same:01M6X7P3PCEAKA2SBETXHHTNBA":57},{"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":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M6X7P3PCEAKA2SBETXHHTNBA","visual-verdict",null,"Structured visual QA verdict for screenshot-to-reference comparisons","Cheggin\u002Frequest-for-startups","Cheggin","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F79483996?v=4","01M6X6MGT5512GJHE8DY5B1ZQJ","Reagan Hsu","01M6X6MGY03X7ZJNVRFM3R1040",1,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-verdict\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27],"visual","verdict","visual verdict","qa","screenshot","reference","structured","visual qa","for","2026-11-10 10:12:30",false,"---\nname: visual-verdict\ndescription: Structured visual QA verdict for screenshot-to-reference comparisons\nlevel: 2\n---\n\n\u003CPurpose>\nUse this skill to compare generated UI screenshots against one or more reference images and return a strict JSON verdict that can drive the next edit iteration.\n\u003C\u002FPurpose>\n\n\u003CUse_When>\n- The task includes visual fidelity requirements (layout, spacing, typography, component styling)\n- You have a generated screenshot and at least one reference image\n- You need deterministic pass\u002Ffail guidance before continuing edits\n\u003C\u002FUse_When>\n\n\u003CInputs>\n- `reference_images[]` (one or more image paths)\n- `generated_screenshot` (current output image)\n- Optional: `category_hint` (e.g., `hackernews`, `sns-feed`, `dashboard`)\n\u003C\u002FInputs>\n\n\u003COutput_Contract>\nReturn **JSON only** with this exact shape:\n\n```json\n{\n  \"score\": 0,\n  \"verdict\": \"revise\",\n  \"category_match\": false,\n  \"differences\": [\"...\"],\n  \"suggestions\": [\"...\"],\n  \"reasoning\": \"short explanation\"\n}\n```\n\nRules:\n- `score`: integer 0-100\n- `verdict`: short status (`pass`, `revise`, or `fail`)\n- `category_match`: `true` when the generated screenshot matches the intended UI category\u002Fstyle\n- `differences[]`: concrete visual mismatches (layout, spacing, typography, colors, hierarchy)\n- `suggestions[]`: actionable next edits tied to the differences\n- `reasoning`: 1-2 sentence summary\n\n\u003CThreshold_And_Loop>\n- Target pass threshold is **90+**.\n- If `score \u003C 90`, continue editing and rerun `\u002Fstartup-harness:visual-verdict` before any further visual review pass.\n- Do **not** treat the visual task as complete until the next screenshot clears the threshold.\n\u003C\u002FThreshold_And_Loop>\n\n\u003CDebug_Visualization>\nWhen mismatch diagnosis is hard:\n1. Keep `$visual-verdict` as the authoritative decision.\n2. Use pixel-level diff tooling (pixel diff \u002F pixelmatch overlay) as a **secondary debug aid** to localize hotspots.\n3. Convert pixel diff hotspots into concrete `differences[]` and `suggestions[]` updates.\n\u003C\u002FDebug_Visualization>\n\n\u003CExample>\n```json\n{\n  \"score\": 87,\n  \"verdict\": \"revise\",\n  \"category_match\": true,\n  \"differences\": [\n    \"Top nav spacing is tighter than reference\",\n    \"Primary button uses smaller font weight\"\n  ],\n  \"suggestions\": [\n    \"Increase nav item horizontal padding by 4px\",\n    \"Set primary button font-weight to 600\"\n  ],\n  \"reasoning\": \"Core layout matches, but style details still diverge.\"\n}\n```\n\u003C\u002FExample>\n\nTask: {{ARGUMENTS}}\n","\u003CPurpose>\nUse this skill to compare generated UI screenshots against one or more reference images and return a strict JSON verdict that can drive the next edit iteration.\n\u003C\u002FPurpose>\n\n\u003CUse_When>\n- The task includes visual fidelity requirements (layout, spacing, typography, component styling)\n- You have a generated screenshot and at least one reference image\n- You need deterministic pass\u002Ffail guidance before continuing edits\n\u003C\u002FUse_When>\n\n\u003CInputs>\n- `reference_images[]` (one or more image paths)\n- `generated_screenshot` (current output image)\n- Optional: `category_hint` (e.g., `hackernews`, `sns-feed`, `dashboard`)\n\u003C\u002FInputs>\n\n\u003COutput_Contract>\nReturn **JSON only** with this exact shape:\n\n```json\n{\n  \"score\": 0,\n  \"verdict\": \"revise\",\n  \"category_match\": false,\n  \"differences\": [\"...\"],\n  \"suggestions\": [\"...\"],\n  \"reasoning\": \"short explanation\"\n}\n```\n\nRules:\n- `score`: integer 0-100\n- `verdict`: short status (`pass`, `revise`, or `fail`)\n- `category_match`: `true` when the generated screenshot matches the intended UI category\u002Fstyle\n- `differences[]`: concrete visual mismatches (layout, spacing, typography, colors, hierarchy)\n- `suggestions[]`: actionable next edits tied to the differences\n- `reasoning`: 1-2 sentence summary\n\n\u003CThreshold_And_Loop>\n- Target pass threshold is **90+**.\n- If `score \u003C 90`, continue editing and rerun `\u002Fstartup-harness:visual-verdict` before any further visual review pass.\n- Do **not** treat the visual task as complete until the next screenshot clears the threshold.\n\u003C\u002FThreshold_And_Loop>\n\n\u003CDebug_Visualization>\nWhen mismatch diagnosis is hard:\n1. Keep `$visual-verdict` as the authoritative decision.\n2. Use pixel-level diff tooling (pixel diff \u002F pixelmatch overlay) as a **secondary debug aid** to localize hotspots.\n3. Convert pixel diff hotspots into concrete `differences[]` and `suggestions[]` updates.\n\u003C\u002FDebug_Visualization>\n\n\u003CExample>\n```json\n{\n  \"score\": 87,\n  \"verdict\": \"revise\",\n  \"category_match\": true,\n  \"differences\": [\n    \"Top nav spacing is tighter than reference\",\n    \"Primary button uses smaller font weight\"\n  ],\n  \"suggestions\": [\n    \"Increase nav item horizontal padding by 4px\",\n    \"Set primary button font-weight to 600\"\n  ],\n  \"reasoning\": \"Core layout matches, but style details still diverge.\"\n}\n```\n\u003C\u002FExample>\n\nTask: {{ARGUMENTS}}\n",{"name":5,"level":33,"description":7},2,"main","92dddf7f6e7b55d1424795ce11586b05dba9d8c8","skills\u002Fvisual-verdict",3,"https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups","https:\u002F\u002Fgithub.com\u002FCheggin","reaganhsu.com","MTS @datacurve-ai, prev. founding eng @browser-use ","2026-04-24 08:33:47",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add Cheggin\u002Frequest-for-startups --skill visual-verdict",{"tool":49,"command":50},"bunx","bunx skills add Cheggin\u002Frequest-for-startups --skill visual-verdict",{"tool":52,"command":53},"pnpm","pnpm dlx skills add Cheggin\u002Frequest-for-startups --skill visual-verdict","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-verdict\u002FSKILL.md",true,[],[58,81,101,144,167,181],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":28},"01M6X7PHK069RZH25A3RXN5049","writer-memory","Agentic memory system for writers - track characters, relationships, scenes, and themes","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fwriter-memory\u002FSKILL.md",[],[65,66,67,68,69,70,71,72,73,74,75,76,77,78,27,79,80],"memory","writer","writer memory","agentic","init","validate","status","system","export","query","relationships","scenes","memory system","themes","track","characters",{"skillNo":82,"name":83,"nameZh":6,"description":84,"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":28},"01M6X7PC3G9228Z323X5YAKTVW","wiki","LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fwiki\u002FSKILL.md",[],[83,88,89,90,91,92,93,94,95,96,97,74,98,99,100],"sessions","lint","wiki lint","wiki query","markdown","knowledge","model","llm wiki","karpathy","base","knowledge base","across","add",{"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":123,"publishedAt":28},"01M6X7P5XFW5C16H3JE4NFQ7MF","website-creation","Build production-quality SaaS websites with opinionated design presets. Use when creating any startup website. The user MUST pick a design style before building. Enforces shadcn\u002Fui, Figma design principles, specific CSS values per style, and anti-AI-writing. Load alongside anti-ai-writing skill. LIGHT MODE ONLY.","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fwebsite-creation\u002FSKILL.md",[107,112,115,120],{"categoryNo":108,"categoryName":109,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":113,"categoryName":114,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":121,"categoryName":122,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000036","内容创作者",[124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143],"website","creation","website creation","design","writing","css","figma","shadcn","audit","ui","polish","pick","only","design principles","Anti-AI","full","brand-guidelines","mode","design style","when",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":158,"publishedAt":28},"01M6X7NXEWWC4NFT0ZK1RRSGES","visual-qa-pipeline","Screenshot every page with Playwright, feed to visual QA agent for design evaluation, report results to Slack. Use after every build phase to verify UI matches the chosen design preset. Integrates with the Playwright skill and the website-creation preset system.","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-qa-pipeline\u002FSKILL.md",[150,153,156,157],{"categoryNo":151,"categoryName":152,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000005","邮件与沟通",{"categoryNo":154,"categoryName":155,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":108,"categoryName":109,"taxonomyType":110,"taxonomyTypeDesc":111},{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},[22,159,19,26,160,127,161,162,23,124,133,163,134,164,139,125,103,27,165,166],"pipeline","visual qa pipeline","review","slack","Evaluation","page","phase","verify ui",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":28},"01M6X7NSNW00RQ8J531F52YHV9","verify","Verify that a change really works before you claim completion","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[169,174,175,159,176,177,178,179,180],"change","deploy","quality","claim","you","true","deploy-pipeline",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":187,"publishedAt":28},"01M6X7NKFDAT5EYKQ7YRFXAHA9","user-feedback-collector","Build an in-app feedback widget that collects user feedback, categorizes it by type (bug, feature request, general), routes it to appropriate agents, and converts feature requests into GitHub Issues. Use when adding feedback collection, building feedback widgets, setting up user feedback routing, or aggregating feedback trends.","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fuser-feedback-collector\u002FSKILL.md",[],[188,189,190,191,192,193,194,195,196,197,198,199,200,125,201,202,203,179,103,143],"feedback","user","feedback collector","collector","user feedback collector","github","routing","state","issues","collection","use","up","general","feature","app","type"]