[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79EPC3P66JDEE8P1JHNDBTY":3,"skill-same:01M79EPC3P66JDEE8P1JHNDBTY":84},{"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":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79EPC3P66JDEE8P1JHNDBTY","visual-explain",null,"Present a substantive plan or end-of-work delivery as an interactive visual in T3, preserving existing HTML questionnaires.","AO-HyS\u002Fdevelopment-system","AO-HyS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F286554351?v=4","01M79DCXZGC6076EH5QATNXCY2","AO HyS","01M79DCY06TSBCJ946VP0BT0RG",0,"MIT","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.5.0\u002Fskills\u002Finternal\u002Fvisual-explain\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: visual-explain\ndescription: Present a substantive plan or end-of-work delivery as an interactive visual in T3, preserving existing HTML questionnaires.\n---\n\n# Visual plans and deliveries\n\nUse this for presenting a substantive plan and for closing nontrivial work.\nOrdinary answers, progress updates and brief confirmations stay in text unless\nthe user asks for a visual. An explicit text-only request wins. Grill sessions\nkeep their existing HTML questionnaires, questions, drafts and submission flow.\n\nThe approved direction is **the line and the window**: one meaningful sequence,\na movable focus, and two annotations explaining the focused step. Draw the work\nbefore arranging prose. Do not turn the output into a table, tabs, a dashboard,\nrepeated cards or a second questionnaire. Use the user's actual content and\nauthority; an approval marker records a real boundary, never creates one.\n\n## Compose\n\n- For a plan, show the objective, proposed work, dependencies and any real\n  decision needed. The focused annotations say what the step includes and\n  leaves out. Preserve an already approved plan and continue authorized work.\n- For a delivery, show the actual result, evidence and remaining limits. The\n  annotations say what was verified and what was not. Distinguish preparing,\n  installing, loading and observed behavior; use pending\u002Fblocked honestly.\n- Use 2–8 meaningful stages. Do not add stages to fill a template. If the work\n  branches, say so in its annotations; never invent a linear dependency or\n  reduce a comparison to a decorative timeline. A different visual explicitly\n  requested by the user takes precedence.\n\nEvery plan and delivery closes with two explicit statements in the user's\nlanguage, visible without selecting a stage: **What I need from you** and\n**What happens next**. Name the exact decision, input or action needed and what\nit unlocks; when none is needed, say \"I don't need anything from you right now.\"\nThen name the next action, its owner and any genuine dependency. When the\nauthorized work is complete, say that instead of inventing follow-up work.\nUse the existing `closing` text; do not add panels, tables or another approval\nflow. A gate label or linked report is not a substitute. Keep a pending user\naction explicit in the accompanying message too. Never request approval already\ngiven, block independent authorized work or imply optional work is required.\n\nRead [the approved direction](references\u002Fdirection.md) for composition and\nresponsive behavior. Use [the packet reference](references\u002Fpacket.md) and adapt\nthe plan or delivery example in `examples\u002F`. The renderer supplies the approved\nmechanics; do not independently redesign them for each response.\n\n```sh\nnode \u002Fabsolute\u002Fpath\u002Fto\u002Fvisual-explain\u002Fscripts\u002Frender.mjs --input \u002Fprivate\u002Fpacket.json --output \u002Fprivate\u002Fvisual.html\n```\n\nAll output is self-contained. Text is escaped, there are no remote resources,\nstorage, submissions, clipboard actions or external calls. Focusing a stage\nonly changes the local explanation. Keep secrets and private transcripts out.\n\n## Verify and deliver\n\nOnly the parent publishes the visual in its owning thread. Discover T3 tools\nfrom the live catalog. Use `html_preview` on the exact HTML before `html_render`;\nuse the measured content height within the host's limit. Retain the candidate\nhash and any unreadable, inaccessible or unverified state. Reuse an unchanged\ncandidate's valid evidence. Browser authority, review budgets and required\nspecialist roles still apply; this skill grants no extra sessions or effects.\n\nCheck the focused stage, annotations, keyboard, mobile reflow, both themes and\nreduced motion within the authorized pass. Meaningful visual changes need\nindependent critique against the approved direction, not only a clean console.\nResolve material findings before describing the result as accepted.\n\nIf T3 preview\u002Frender is unavailable or not authorized, deliver a concise text\nsummary and the durable HTML path, explicitly marked unpreviewed when applicable.\nDo not silently substitute another browser or claim inline delivery. If a\ndependency is missing, record it without inventing a successful rendering.\n\nA nontrivial closure still produces the normal `development-system document`\nreport with evidence and verification scope. Link its persistent `htmlPath` in\nthe closing message; the inline visual summarizes it instead of duplicating the\nwhole report. Keep reports and questionnaire renderers unchanged. The final\nprose adds the useful caveat, next action and report link, not a transcription\nof the visual. No global installation, publication or acceptance is implied.\n","# Visual plans and deliveries\n\nUse this for presenting a substantive plan and for closing nontrivial work.\nOrdinary answers, progress updates and brief confirmations stay in text unless\nthe user asks for a visual. An explicit text-only request wins. Grill sessions\nkeep their existing HTML questionnaires, questions, drafts and submission flow.\n\nThe approved direction is **the line and the window**: one meaningful sequence,\na movable focus, and two annotations explaining the focused step. Draw the work\nbefore arranging prose. Do not turn the output into a table, tabs, a dashboard,\nrepeated cards or a second questionnaire. Use the user's actual content and\nauthority; an approval marker records a real boundary, never creates one.\n\n## Compose\n\n- For a plan, show the objective, proposed work, dependencies and any real\n  decision needed. The focused annotations say what the step includes and\n  leaves out. Preserve an already approved plan and continue authorized work.\n- For a delivery, show the actual result, evidence and remaining limits. The\n  annotations say what was verified and what was not. Distinguish preparing,\n  installing, loading and observed behavior; use pending\u002Fblocked honestly.\n- Use 2–8 meaningful stages. Do not add stages to fill a template. If the work\n  branches, say so in its annotations; never invent a linear dependency or\n  reduce a comparison to a decorative timeline. A different visual explicitly\n  requested by the user takes precedence.\n\nEvery plan and delivery closes with two explicit statements in the user's\nlanguage, visible without selecting a stage: **What I need from you** and\n**What happens next**. Name the exact decision, input or action needed and what\nit unlocks; when none is needed, say \"I don't need anything from you right now.\"\nThen name the next action, its owner and any genuine dependency. When the\nauthorized work is complete, say that instead of inventing follow-up work.\nUse the existing `closing` text; do not add panels, tables or another approval\nflow. A gate label or linked report is not a substitute. Keep a pending user\naction explicit in the accompanying message too. Never request approval already\ngiven, block independent authorized work or imply optional work is required.\n\nRead [the approved direction](references\u002Fdirection.md) for composition and\nresponsive behavior. Use [the packet reference](references\u002Fpacket.md) and adapt\nthe plan or delivery example in `examples\u002F`. The renderer supplies the approved\nmechanics; do not independently redesign them for each response.\n\n```sh\nnode \u002Fabsolute\u002Fpath\u002Fto\u002Fvisual-explain\u002Fscripts\u002Frender.mjs --input \u002Fprivate\u002Fpacket.json --output \u002Fprivate\u002Fvisual.html\n```\n\nAll output is self-contained. Text is escaped, there are no remote resources,\nstorage, submissions, clipboard actions or external calls. Focusing a stage\nonly changes the local explanation. Keep secrets and private transcripts out.\n\n## Verify and deliver\n\nOnly the parent publishes the visual in its owning thread. Discover T3 tools\nfrom the live catalog. Use `html_preview` on the exact HTML before `html_render`;\nuse the measured content height within the host's limit. Retain the candidate\nhash and any unreadable, inaccessible or unverified state. Reuse an unchanged\ncandidate's valid evidence. Browser authority, review budgets and required\nspecialist roles still apply; this skill grants no extra sessions or effects.\n\nCheck the focused stage, annotations, keyboard, mobile reflow, both themes and\nreduced motion within the authorized pass. Meaningful visual changes need\nindependent critique against the approved direction, not only a clean console.\nResolve material findings before describing the result as accepted.\n\nIf T3 preview\u002Frender is unavailable or not authorized, deliver a concise text\nsummary and the durable HTML path, explicitly marked unpreviewed when applicable.\nDo not silently substitute another browser or claim inline delivery. If a\ndependency is missing, record it without inventing a successful rendering.\n\nA nontrivial closure still produces the normal `development-system document`\nreport with evidence and verification scope. Link its persistent `htmlPath` in\nthe closing message; the inline visual summarizes it instead of duplicating the\nwhole report. Keep reports and questionnaire renderers unchanged. The final\nprose adds the useful caveat, next action and report link, not a transcription\nof the visual. No global installation, publication or acceptance is implied.\n",{"name":5,"description":7},"main","9f5b43aadb1a92441d65e9cb74a584cd6fca62bc","artifacts\u002F2.5.0\u002Fskills\u002Finternal\u002Fvisual-explain","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system","https:\u002F\u002Fgithub.com\u002FAO-HyS","https:\u002F\u002Faohys.net\u002F","Software Boutique, we make your projects come true live. ","2026-11-14 03:17:27",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add AO-HyS\u002Fdevelopment-system --skill visual-explain",{"tool":38,"command":39},"bunx","bunx skills add AO-HyS\u002Fdevelopment-system --skill visual-explain",{"tool":41,"command":42},"pnpm","pnpm dlx skills add AO-HyS\u002Fdevelopment-system --skill visual-explain","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.5.0\u002Fskills\u002Finternal\u002Fvisual-explain\u002FSKILL.md",true,[46,52,58,64,68,72,76,80],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",232,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.5.0\u002Fskills\u002Finternal\u002Fvisual-explain\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"assets\u002Fline-window.css","ASSET","资产文件",5854,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.5.0\u002Fskills\u002Finternal\u002Fvisual-explain\u002Fassets\u002Fline-window.css",{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"assets\u002Fline-window.js","SCRIPT","脚本",5058,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.5.0\u002Fskills\u002Finternal\u002Fvisual-explain\u002Fassets\u002Fline-window.js",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"examples\u002Fdelivery.json",2026,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.5.0\u002Fskills\u002Finternal\u002Fvisual-explain\u002Fexamples\u002Fdelivery.json",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"examples\u002Fplan.json",2062,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.5.0\u002Fskills\u002Finternal\u002Fvisual-explain\u002Fexamples\u002Fplan.json",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fdirection.md",2058,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.5.0\u002Fskills\u002Finternal\u002Fvisual-explain\u002Freferences\u002Fdirection.md",{"path":77,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fpacket.md",2207,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.5.0\u002Fskills\u002Finternal\u002Fvisual-explain\u002Freferences\u002Fpacket.md",{"path":81,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002Frender.mjs",6224,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.5.0\u002Fskills\u002Finternal\u002Fvisual-explain\u002Fscripts\u002Frender.mjs",[85,92,99,106,113,120],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M79EQ4BPYQTX8RWN1Y1J2K1F","working-backwards","Define a software feature through PRFAQ and staged documents when the user requests working backwards before coding.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fworking-backwards\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M79EQ2E8P85Y1Y7VNJZMNEJE","flow-implement","Implement a requested software change through verification, corrections, and its authorized delivery endpoint.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fflow-implement\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M79EQ0PNMKHPJ78F8WMNX06P","development-steward","Run the scheduled, read-only weekly maintenance review for the six explicitly opted-in repositories and prepare one concise private report for Check-in.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fdevelopment-steward\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M79EPXJ56MX7955GWP1HD4B0","grill-with-docs","Run one recoverable interview for functional, visual, or mixed software grills; reuse equivalent answers and offer the shared HTML questionnaire.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Finternal\u002Fgrill-with-docs\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M79EPTFPHYEV40ZG52Z0GVS2","global-agent-guardrails","Install, audit, test, or update the Development System's global destructive-command guard for Codex, Claude Code and T3 Code. Use when configuring agent safety hooks or investigating whether dangerous shell operations are blocked.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Finternal\u002Fglobal-agent-guardrails\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":124,"licenseFileUrl":125,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":19},"01M79EPR0KPHKAFN7V6CEEDR0Y","impeccable","Design or refine frontend UI using project context and a focused design playbook; also handles visual critique and polish.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Fexternal\u002Fimpeccable\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Fexternal\u002Fimpeccable\u002FSKILL.md",[],[]]