[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7135R6SQE1ABCND82VVVRAR":3,"skill-same:01M7135R6SQE1ABCND82VVVRAR":82},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M7135R6SQE1ABCND82VVVRAR","wechat-visual-director",null,"Project-level visual direction skill for WeChat Official Account articles. Use when planning, improving, diversifying, generating, or reviewing cover images and body illustrations for公众号文章, especially when Codex image generation should be used without being constrained by repetitive preset-based illustration skills.","EthanYoQ\u002FSkill-hub","EthanYoQ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F257484394?v=4","01M70C9QKWR1YS0S7V26DNB18H","Ethan","01M70C9QMER047R5ANZZA6KC2P",11,"MIT","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fwechat-visual-director\u002Fd34d5ba7914639a9\u002Fwechat-visual-director\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"wechat","visual","wechat visual director","director","cover","generation","codex","Image Generation","preset","公众号","image","when","use","project","for","direction","planning","illustration","official","images","2026-11-10 10:12:30",false,"---\nname: wechat-visual-director\ndescription: Project-level visual direction skill for WeChat Official Account articles. Use when planning, improving, diversifying, generating, or reviewing cover images and body illustrations for公众号文章, especially when Codex image generation should be used without being constrained by repetitive preset-based illustration skills.\n---\n\n# WeChat Visual Director\n\nUse this skill before generating article visuals. Its job is to choose visual concepts that fit the article, not to force every image through the same style preset.\n\n## Core Rule\n\nDesign first, generate second.\n\nDo not start with `type + style + palette`. Start with article role, reader emotion, evidence type, and what the image must make easier to understand.\n\n## Visual Workflow\n\n1. Classify each needed visual.\n   - Cover: promise, tension, or central metaphor.\n   - Evidence visual: real screenshot, repo evidence, chart, table, UI state.\n   - Explanation visual: architecture, workflow, comparison, framework, timeline.\n   - Scene visual: workplace pain, decision moment, human context.\n2. Decide whether the visual should be generated.\n   - Use real screenshots for UI, repo pages, CLI output, dashboards, and product states.\n   - Use generated images for conceptual covers, scenes, metaphors, and explanatory illustrations.\n   - Do not generate decorative filler.\n3. Create 2-3 distinct visual routes for important images.\n   - Each route must differ in metaphor, composition, and rendering language.\n   - Avoid minor palette-only variation.\n4. Pick one route and write a prompt file.\n   - Save prompts before generation.\n   - Keep on-image text minimal; prefer no text for complex Chinese labels.\n   - If text is required, use short Chinese labels only.\n5. Generate with Codex native image generation when available.\n   - Use the native `image_gen`\u002F`imagegen` capability directly in Codex.\n   - Do not route through a separate Codex CLI on another computer.\n   - Use `baoyu-image-gen` only when an explicit API provider is needed.\n6. Review the image.\n   - Reject images that look like generic AI stock art, repetitive template covers, fake dashboards, unreadable text, or unrelated metaphors.\n   - Regenerate from a revised prompt; do not patch generated text with programmatic overlays.\n\n## Diversity Matrix\n\nFor a multi-image article, intentionally vary at least three dimensions:\n\n- Composition: close-up, overhead map, split-screen, layered system, single object, human scene.\n- Visual language: editorial photo-real, hand-drawn notes, precise product diagram, magazine infographic, cinematic metaphor, paper cutout, UI screenshot.\n- Cognitive function: hook, proof, compare, sequence, explain, summarize.\n- Texture: clean digital, paper, marker, screen glow, realistic workplace, blueprint.\n- Camera: macro, desk-level, isometric, documentary, top-down, wide scene.\n\nNever make every body image share the same border, palette, icon style, or abstract blob background.\n\n## Use External Skills As References\n\n- Use `visual-storytelling-design` when the article has data, comparisons, mechanisms, or claim framing that needs annotation and honest context.\n- Use `aesthetic` when visual hierarchy, mood, typography, or inspiration-quality review is needed.\n- Use `baoyu-article-illustrator` only after this skill has decided image roles and routes.\n- Use `baoyu-cover-image` only for cover generation, not for all body images.\n\n## Output Contract\n\nFor visual planning, produce:\n\n- Visual inventory with image role, evidence\u002Fgeneration decision, and placement.\n- Route options for cover and key body visuals.\n- Final prompt file paths to create.\n- Generation aspect ratios.\n- Review checklist and rejection criteria.\n\nFor direct generation, create prompt files first, then generate.\n\n","# WeChat Visual Director\n\nUse this skill before generating article visuals. Its job is to choose visual concepts that fit the article, not to force every image through the same style preset.\n\n## Core Rule\n\nDesign first, generate second.\n\nDo not start with `type + style + palette`. Start with article role, reader emotion, evidence type, and what the image must make easier to understand.\n\n## Visual Workflow\n\n1. Classify each needed visual.\n   - Cover: promise, tension, or central metaphor.\n   - Evidence visual: real screenshot, repo evidence, chart, table, UI state.\n   - Explanation visual: architecture, workflow, comparison, framework, timeline.\n   - Scene visual: workplace pain, decision moment, human context.\n2. Decide whether the visual should be generated.\n   - Use real screenshots for UI, repo pages, CLI output, dashboards, and product states.\n   - Use generated images for conceptual covers, scenes, metaphors, and explanatory illustrations.\n   - Do not generate decorative filler.\n3. Create 2-3 distinct visual routes for important images.\n   - Each route must differ in metaphor, composition, and rendering language.\n   - Avoid minor palette-only variation.\n4. Pick one route and write a prompt file.\n   - Save prompts before generation.\n   - Keep on-image text minimal; prefer no text for complex Chinese labels.\n   - If text is required, use short Chinese labels only.\n5. Generate with Codex native image generation when available.\n   - Use the native `image_gen`\u002F`imagegen` capability directly in Codex.\n   - Do not route through a separate Codex CLI on another computer.\n   - Use `baoyu-image-gen` only when an explicit API provider is needed.\n6. Review the image.\n   - Reject images that look like generic AI stock art, repetitive template covers, fake dashboards, unreadable text, or unrelated metaphors.\n   - Regenerate from a revised prompt; do not patch generated text with programmatic overlays.\n\n## Diversity Matrix\n\nFor a multi-image article, intentionally vary at least three dimensions:\n\n- Composition: close-up, overhead map, split-screen, layered system, single object, human scene.\n- Visual language: editorial photo-real, hand-drawn notes, precise product diagram, magazine infographic, cinematic metaphor, paper cutout, UI screenshot.\n- Cognitive function: hook, proof, compare, sequence, explain, summarize.\n- Texture: clean digital, paper, marker, screen glow, realistic workplace, blueprint.\n- Camera: macro, desk-level, isometric, documentary, top-down, wide scene.\n\nNever make every body image share the same border, palette, icon style, or abstract blob background.\n\n## Use External Skills As References\n\n- Use `visual-storytelling-design` when the article has data, comparisons, mechanisms, or claim framing that needs annotation and honest context.\n- Use `aesthetic` when visual hierarchy, mood, typography, or inspiration-quality review is needed.\n- Use `baoyu-article-illustrator` only after this skill has decided image roles and routes.\n- Use `baoyu-cover-image` only for cover generation, not for all body images.\n\n## Output Contract\n\nFor visual planning, produce:\n\n- Visual inventory with image role, evidence\u002Fgeneration decision, and placement.\n- Route options for cover and key body visuals.\n- Final prompt file paths to create.\n- Generation aspect ratios.\n- Review checklist and rejection criteria.\n\nFor direct generation, create prompt files first, then generate.\n\n",{"name":5,"description":7},"mine","1e7390741dffd3d5041fca4ebc056071ee3ba137","archives\u002Fuser-installed-skills\u002Fwechat-visual-director\u002Fd34d5ba7914639a9\u002Fwechat-visual-director",5,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub","https:\u002F\u002Fgithub.com\u002FEthanYoQ","www.orz.md","Part Marketer, Part AI Explorer.","2026-11-07 14:52:29",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add EthanYoQ\u002FSkill-hub --skill wechat-visual-director",{"tool":64,"command":65},"bunx","bunx skills add EthanYoQ\u002FSkill-hub --skill wechat-visual-director",{"tool":67,"command":68},"pnpm","pnpm dlx skills add EthanYoQ\u002FSkill-hub --skill wechat-visual-director","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fwechat-visual-director\u002Fd34d5ba7914639a9\u002Fwechat-visual-director\u002FSKILL.md",true,[72,78],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"agents\u002Fopenai.yaml","REFERENCE","参考文档",222,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fwechat-visual-director\u002Fd34d5ba7914639a9\u002Fwechat-visual-director\u002Fagents\u002Fopenai.yaml",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fvisual-strategy.md",1754,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fwechat-visual-director\u002Fd34d5ba7914639a9\u002Fwechat-visual-director\u002Freferences\u002Fvisual-strategy.md",[83,109,140,163,181,196],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":90,"publishedAt":44},"01M713CBDSYARG4PXFXK2R2NNN","xhs-pharma-social-listening","Run evidence-disciplined Xiaohongshu social listening for foreign pharma employee pain points. Use when the user asks to collect and analyze notes\u002Fcomments about pharma companies, aliases, roles, compliance, medical affairs, or AI topics, then produce a cited and scored sampled-insight report. Includes independent-evidence counting, MediaCrawler batch collection, and CAPTCHA\u002F461 fallback to Agent Reach\u002FOpenCLI.","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F10-business-industry\u002Fxhs-pharma-social-listening\u002FSKILL.md",[89],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[91,92,93,94,95,96,35,97,98,99,100,101,102,103,104,105,106,38,107,108],"social","xhs pharma social listening","social listening","xhs","medical","counting","collection","batch","analyze","notes","run","opencli","fallback","captcha","agent reach","evidence","collect","produce",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":121,"publishedAt":44},"01M713C8Q76ZP0WXXBRAFKS6EE","healthcare-phi-compliance","Protected Health Information (PHI) and Personally Identifiable Information (PII) compliance patterns for healthcare applications. Covers data classification, access control, audit trails, encryption, and common leak vectors. Use when code touches PHI or PII in a healthcare system, or when auditing access control, audit trails, or leak vectors.","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F10-business-industry\u002Fhealthcare-phi-compliance\u002FSKILL.md",[115,116],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":117,"categoryName":118,"taxonomyType":119,"taxonomyTypeDesc":120},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[122,123,124,125,126,127,128,129,35,130,131,132,133,134,135,136,38,137,138,139],"healthcare","phi","compliance","healthcare phi compliance","pii","compliance patterns","information","access","encryption","code","common","audit","data","patterns","Access Control","system","applications","Auditing Access Control",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":147,"publishedAt":44},"01M713C5R2GE43X45T2K75TB76","healthcare-eval-harness","Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures. Use when a healthcare deployment must be gated on patient-safety tests for CDSS accuracy, PHI exposure, and workflow integrity.","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F10-business-industry\u002Fhealthcare-eval-harness\u002FSKILL.md",[146],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[122,148,149,150,151,152,153,35,154,155,156,157,123,38,158,159,160,161,36,162],"eval","harness","healthcare eval harness","eval harness","clinical","patient","workflow","Evaluation","Safety","integrity","deployment","accuracy","tests","deployments","super",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":170,"publishedAt":44},"01M713C2J17S91VYR7A8M696VR","healthcare-emr-patterns","EMR\u002FEHR development patterns for healthcare applications. Clinical safety, encounter workflows, prescription generation, clinical decision support integration, and accessibility-first UI for medical data entry. Use when building EMR or EHR features such as encounter workflows, prescription generation, or clinical data entry UI.","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F10-business-industry\u002Fhealthcare-emr-patterns\u002FSKILL.md",[169],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[122,171,135,172,173,95,152,174,35,175,176,177,156,134,178,179,180,38,138,36],"EMR","healthcare emr patterns","decision","workflows","support","clinical decision support","features","ui","as","development",{"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":188,"publishedAt":44},"01M713BZERTXV0N8X6SW9DDVWZ","healthcare-cdss-patterns","Clinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows. Use when building clinical decision support — drug interaction checks, dose validation, clinical scoring, or alert severity.","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F10-business-industry\u002Fhealthcare-cdss-patterns\u002FSKILL.md",[187],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[122,135,189,173,152,171,174,35,190,191,175,176,192,180,137,193,36,194,162,195],"healthcare cdss patterns","scoring","interaction","severity","classification","alert","decision support",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":203,"publishedAt":44},"01M713BVK3PQR7V4ZKYGMWMXJD","dxy-task-clarify","用户的请求含糊、缺背景、缺资料说明、缺读者或用途时使用。先用少量带选项的追问把任务问清楚，写成任务卡，用户确认后再执行。尤其适用于医生、科研人员和药企各岗位的工作，例如「帮我分析一下这些数据」「帮我准备明天的拜访」「写个总结」「做个 PPT」「回一下这封邮件」「整理一下会议纪要」「整理一下这些文献」「帮我准备下周的讲课」「写个病例汇报」「帮我写个提示词」。用户说「先问我」「帮我理清需求」「我不知道怎么描述」「我不会问 AI」时也使用。用途、资料、读者都已说清的请求，纯翻译，以及写代码、改代码，不使用。","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F10-business-industry\u002Fdxy-task-clarify\u002FSKILL.md",[202],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[204,205,206,207,208,209,210,211],"clarify","dxy task clarify","task","pptx","整理","翻译","数据","总结"]