[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75BKVE33VNDHVWSGS8TP1GX":3,"skill-same:01M75BKVE33VNDHVWSGS8TP1GX":75},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M75BKVE33VNDHVWSGS8TP1GX","show-me",null,"Explain topics and code changes with concise Markdown, focused sketches and evidence; use separately installed archify for HTML reports.","Yaphet2015\u002Fya-skills","Yaphet2015","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F17684609?v=4","01M75BHXC36T9EZJ2Y3DRRRH1E","Yaphet Y","01M75BHXCMYQ20CST1Z22JV099",0,"MIT","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fshow-me\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fshow-me\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: show-me\ndescription: Explain topics and code changes with concise Markdown, focused sketches and evidence; use separately installed archify for HTML reports.\n---\n\n# Show Me\n\nHelp the reader understand the current question with the smallest useful answer.\nStart from the conversation's actual context, skip the preamble, and keep prose\nbrief. Follow explicit language, format, destination, and template requests.\n\n## Tone\n\n- Use a tone that follows ASD-STE100 Simplified Technical English, but expressed in Chinese.\n- Always talk to me like I have ADHD.\n- Keep necessary code identifiers, then explain what they do in the same sentence.\n  Put file references after the plain claim. Use the requested language when specified.\n\n## Edit before choosing a format\n\nAnswer the current question first. Select the few facts that explain the result\nor change the decision. Remove the investigation diary, repeated conclusions,\nbackground the reader already knows, and exhaustive lists that were not requested.\nKeep a material risk, uncertainty or blocking condition visible beside the claim.\nDo not shorten by clipping text or hiding qualifications.\n\nDefault to one conclusion and up to three supporting points. Treat this as a\nreading budget, not a quota: fewer points are fine; a requested full audit or a\nnecessary qualification can need more. Explain code names in ordinary words.\nIf the question is already answered, stop. Apply this rule to Markdown and HTML.\n\n## Choose the right amount of output\n\n- For a focused explanation, stay in chat. A compact sketch and a short explanation\n  are usually enough; invoking this skill does not require creating a file.\n- Use HTML when a diagram, comparison or real interaction makes the answer\n  easier to understand than a brief chat response, or when HTML is requested.\n  Asking for a report alone does not require HTML. All HTML reports and diagrams\n  use the installed `archify` skill. Read [HTML handoff and delivery](references\u002Fhtml-reports.md)\n  when creating one. For a PR or code-change report, also read\n  [change evidence](references\u002Farchitecture-reports.md).\n- Use the requested format when the user specifies one. Apply the visual and\n  clarity principles that fit it rather than silently substituting HTML.\n\n## Pick the form that answers the question\n\n| What needs to become clear                               | Useful form                                                                             |\n| -------------------------------------------------------- | --------------------------------------------------------------------------------------- |\n| Logic, an algorithm, or state transitions                | Pseudocode                                                                              |\n| Runtime execution and call order                         | Call tree                                                                               |\n| UI composition or module ownership                       | Component tree or shallow file tree                                                     |\n| Communication or data flow between components            | Inline flow diagram, or interactive layered architecture and sequence views in a report |\n| A change whose surrounding structure is already familiar | Focused diff                                                                            |\n| Alternatives and their practical differences             | Compact comparison matrix                                                               |\n| Dense relationships or interactive views                 | Focused HTML diagram or report                                                          |\n\nUse real labels, paths, and data from the task. Include the calls, files, props,\nstates, and boundaries that change the reader's understanding. Match the product's\nvisual language when explaining its UI. Do not invent metrics or add decorative\ndiagrams to facts a short list already explains.\n\n## HTML generation\n\n`archify` is an independently installed skill. When HTML is needed, find it in\nthe current host's available-skills list and read the `SKILL.md` at its advertised\npath. If the host provides a separate skill-discovery tool, use that when needed.\nResolve its CLI and references from that installation. Load only the references\nneeded for the selected workflow; the same Agent continues the task.\n\nArchify owns HTML authoring, components, layout, diagrams, styling and generation\nchecks. Follow its explainer workflow for a report that combines a conclusion,\ncomparisons, code changes and verification evidence. Follow its native diagram\nworkflow for a requested standalone system or flow diagram, and run the applicable\nfinalizer.\n\n`show-me` owns the explanation's scope, brevity, change evidence and host delivery.\nPreserve explicit language, format and output requests during the handoff. Use the\nsame verified facts in chat and HTML. If archify cannot be found, explain that it\nmust be installed separately; finish with a useful chat explanation when possible.\n`yk install show-me` installs this skill only. Archify's installation and upgrades\nare independent; its location is supplied by the host. The former HTML generator\nis archived in the ya-skills source repository at `archive\u002Fshow-me-html\u002F`;\nnew HTML uses archify.\n\nSimple chat explanations still stay in chat. This skill explains and reports;\nit does not implement applications or rewrite repository documentation.\n\n## Output location\n\nDefault the report archive to\n`~\u002F.ya-skills\u002Fshow-me\u002Freports\u002F\u003Cproject>\u002F\u003Cbranch>\u002F\u003Ctimestamp>\u002Freport.html`.\nKeep the authoring document, receipts and evidence beside the report. Give\narchify this resolved directory as its explicit destination, as described in\n[HTML handoff and delivery](references\u002Fhtml-reports.md).\nAn explicit destination from the user or invoking workflow takes precedence.\nFollow the host delivery steps in [HTML report guidance](references\u002Fhtml-reports.md#verify-and-deliver).\nReturn a concise takeaway and a Markdown link to the delivered file. A file link\nalone is not proof that a side-panel preview opened.\n\n## Make the important change visible\n\nLead with the conclusion or relationship the reader needs to see. Put each\nvisual next to the short explanation it supports. Keep evidence separate from\nproposals, and keep a qualification visible when it changes the conclusion.\n\nFor changes, use a diff of the actual shape: a component, file tree, call chain,\nor state transition. For example:\n\n```diff\non(save)\n-  write content\n+  if content is unchanged\n+    return cached result\n+  write content\n+  invalidate cache\n```\n\nShow the complete block when most of it is new, omitted context would hide\nownership or execution order, or the reader needs a copyable target. Combine\nforms only when each answers a different part of the question. Stop when the\nkey point is clear.\n","# Show Me\n\nHelp the reader understand the current question with the smallest useful answer.\nStart from the conversation's actual context, skip the preamble, and keep prose\nbrief. Follow explicit language, format, destination, and template requests.\n\n## Tone\n\n- Use a tone that follows ASD-STE100 Simplified Technical English, but expressed in Chinese.\n- Always talk to me like I have ADHD.\n- Keep necessary code identifiers, then explain what they do in the same sentence.\n  Put file references after the plain claim. Use the requested language when specified.\n\n## Edit before choosing a format\n\nAnswer the current question first. Select the few facts that explain the result\nor change the decision. Remove the investigation diary, repeated conclusions,\nbackground the reader already knows, and exhaustive lists that were not requested.\nKeep a material risk, uncertainty or blocking condition visible beside the claim.\nDo not shorten by clipping text or hiding qualifications.\n\nDefault to one conclusion and up to three supporting points. Treat this as a\nreading budget, not a quota: fewer points are fine; a requested full audit or a\nnecessary qualification can need more. Explain code names in ordinary words.\nIf the question is already answered, stop. Apply this rule to Markdown and HTML.\n\n## Choose the right amount of output\n\n- For a focused explanation, stay in chat. A compact sketch and a short explanation\n  are usually enough; invoking this skill does not require creating a file.\n- Use HTML when a diagram, comparison or real interaction makes the answer\n  easier to understand than a brief chat response, or when HTML is requested.\n  Asking for a report alone does not require HTML. All HTML reports and diagrams\n  use the installed `archify` skill. Read [HTML handoff and delivery](references\u002Fhtml-reports.md)\n  when creating one. For a PR or code-change report, also read\n  [change evidence](references\u002Farchitecture-reports.md).\n- Use the requested format when the user specifies one. Apply the visual and\n  clarity principles that fit it rather than silently substituting HTML.\n\n## Pick the form that answers the question\n\n| What needs to become clear                               | Useful form                                                                             |\n| -------------------------------------------------------- | --------------------------------------------------------------------------------------- |\n| Logic, an algorithm, or state transitions                | Pseudocode                                                                              |\n| Runtime execution and call order                         | Call tree                                                                               |\n| UI composition or module ownership                       | Component tree or shallow file tree                                                     |\n| Communication or data flow between components            | Inline flow diagram, or interactive layered architecture and sequence views in a report |\n| A change whose surrounding structure is already familiar | Focused diff                                                                            |\n| Alternatives and their practical differences             | Compact comparison matrix                                                               |\n| Dense relationships or interactive views                 | Focused HTML diagram or report                                                          |\n\nUse real labels, paths, and data from the task. Include the calls, files, props,\nstates, and boundaries that change the reader's understanding. Match the product's\nvisual language when explaining its UI. Do not invent metrics or add decorative\ndiagrams to facts a short list already explains.\n\n## HTML generation\n\n`archify` is an independently installed skill. When HTML is needed, find it in\nthe current host's available-skills list and read the `SKILL.md` at its advertised\npath. If the host provides a separate skill-discovery tool, use that when needed.\nResolve its CLI and references from that installation. Load only the references\nneeded for the selected workflow; the same Agent continues the task.\n\nArchify owns HTML authoring, components, layout, diagrams, styling and generation\nchecks. Follow its explainer workflow for a report that combines a conclusion,\ncomparisons, code changes and verification evidence. Follow its native diagram\nworkflow for a requested standalone system or flow diagram, and run the applicable\nfinalizer.\n\n`show-me` owns the explanation's scope, brevity, change evidence and host delivery.\nPreserve explicit language, format and output requests during the handoff. Use the\nsame verified facts in chat and HTML. If archify cannot be found, explain that it\nmust be installed separately; finish with a useful chat explanation when possible.\n`yk install show-me` installs this skill only. Archify's installation and upgrades\nare independent; its location is supplied by the host. The former HTML generator\nis archived in the ya-skills source repository at `archive\u002Fshow-me-html\u002F`;\nnew HTML uses archify.\n\nSimple chat explanations still stay in chat. This skill explains and reports;\nit does not implement applications or rewrite repository documentation.\n\n## Output location\n\nDefault the report archive to\n`~\u002F.ya-skills\u002Fshow-me\u002Freports\u002F\u003Cproject>\u002F\u003Cbranch>\u002F\u003Ctimestamp>\u002Freport.html`.\nKeep the authoring document, receipts and evidence beside the report. Give\narchify this resolved directory as its explicit destination, as described in\n[HTML handoff and delivery](references\u002Fhtml-reports.md).\nAn explicit destination from the user or invoking workflow takes precedence.\nFollow the host delivery steps in [HTML report guidance](references\u002Fhtml-reports.md#verify-and-deliver).\nReturn a concise takeaway and a Markdown link to the delivered file. A file link\nalone is not proof that a side-panel preview opened.\n\n## Make the important change visible\n\nLead with the conclusion or relationship the reader needs to see. Put each\nvisual next to the short explanation it supports. Keep evidence separate from\nproposals, and keep a qualification visible when it changes the conclusion.\n\nFor changes, use a diff of the actual shape: a component, file tree, call chain,\nor state transition. For example:\n\n```diff\non(save)\n-  write content\n+  if content is unchanged\n+    return cached result\n+  write content\n+  invalidate cache\n```\n\nShow the complete block when most of it is new, omitted context would hide\nownership or execution order, or the reader needs a copyable target. Combine\nforms only when each answers a different part of the question. Stop when the\nkey point is clear.\n",{"name":5,"description":7},"main","b3f303dbd37b1f90e6f71e91aadbed231e664844","skills\u002Fshow-me","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills","https:\u002F\u002Fgithub.com\u002FYaphet2015","https:\u002F\u002Fblog.yaphet.me\u002F","Ex Ant Group, Kwai, Tencent","2026-11-13 15:07:07",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Yaphet2015\u002Fya-skills --skill show-me",{"tool":39,"command":40},"bunx","bunx skills add Yaphet2015\u002Fya-skills --skill show-me",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Yaphet2015\u002Fya-skills --skill show-me","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fshow-me\u002FSKILL.md",true,[47,51,57,61,65,71],{"path":48,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":16},"LICENSE","许可证",1067,{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Farchitecture-reports.md","REFERENCE","参考文档",3004,"https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fshow-me\u002Freferences\u002Farchitecture-reports.md",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fhtml-reports.md",4632,"https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fshow-me\u002Freferences\u002Fhtml-reports.md",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"skill.json",181,"https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fshow-me\u002Fskill.json",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"tools\u002Fbuild-report.cjs","SCRIPT","脚本",198,"https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fshow-me\u002Ftools\u002Fbuild-report.cjs",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"tools\u002Fvalidate.cjs",199,"https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fshow-me\u002Ftools\u002Fvalidate.cjs",[76,83,90,97,104,112],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":20},"01M75BMPRNYQBPMNZFTG5CPGN7","video-transcript","Video transcript (captions first, Whisper fallback). Use when the user wants text from a video.","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-transcript\u002FSKILL.md",[],[],{"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":89,"publishedAt":20},"01M75BMMA9AHMV0PHXXHJ1SWS6","validator","Deprecated. Plan Completion Standard. Use only when the user invokes \u002Fvalidator after a Plan is complete.","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvalidator\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":20},"01M75BMHVMK6A94MM8FKHGJD9R","ultra-simplify","Use when the user asks for a massive simplification pass","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fultra-simplify\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":20},"01M75BMEYYN24G2KKKG09XGD5M","ultra-produce","Deprecated. Coordinate native Planner, Builder and Verifier subagents through implementation and testing, with file-based handoffs, stage hooks and local commits. Use for an end-to-end delegated implementation workflow.","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fultra-produce\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":108,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":20},"01M75BMBF6T4KCH1M6HR8EZCZW","ultra-cr","Coordinate independent code reviewers, architectural impact analysis and finding verification. Use for multi-agent code review or an ultra-cr review against a diff and requirements, with resumable reports.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fultra-cr\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":20},"01M75BM7CCFS6WGQ36WGQ03TTA","ui-parity","Align existing UI surfaces or extract shared interactions with baseline regression checks, state comparisons, and rendered evidence. Use for UI parity work.","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fui-parity\u002FSKILL.md",[],[]]