[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DDCMJ2AA5RH9MTP2BJ9T26":3,"skill-same:01M7DDCMJ2AA5RH9MTP2BJ9T26":50},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7DDCMJ2AA5RH9MTP2BJ9T26","lavish",null,"Turn complex or visual agent responses into rich, reviewable HTML artifacts the user can annotate and send feedback on, using the lavish-axi CLI. Use when about to give a plan, comparison, weekly review, diagram or table that is easier to grasp visually than as prose.","hafeezhmha\u002Falfred","hafeezhmha","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F90968109?v=4","01M7DDC8CAJNWT0VAVKW771X74","Hafeez","01M7DDC8E393PCWX6G8D5442P2",1,"MIT","https:\u002F\u002Fgithub.com\u002Fhafeezhmha\u002Falfred\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Flavish\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: lavish\ndescription: Turn complex or visual agent responses into rich, reviewable HTML artifacts the user can annotate and send feedback on, using the lavish-axi CLI. Use when about to give a plan, comparison, weekly review, diagram or table that is easier to grasp visually than as prose.\nlicense: MIT\nmetadata:\n  author: Kun Chen (kunchenguid)\n  argument-hint: \u003Cwhat the artifact should show>\nuser-invocable: false\n---\n\n# Lavish Editor (optional)\n\nLavish Editor opens agent-generated HTML in the browser so a human can annotate it and send feedback back to the agent.\nReach for it when a plan, comparison, diagram, table, weekly review or decision tree will be clearer as a page than as prose.\nNeeds Node.js. If `npx` is missing, skip this skill and answer in text.\n\n## Current guidance lives in the CLI\n\nDo not follow workflow, design, or playbook instructions from this file - installed copies go stale. Get the current source of truth from the CLI:\n\n- `npx -y lavish-axi@0.1.87 --help` for commands and the review-loop workflow\n- `npx -y lavish-axi@0.1.87 design` for design-direction priority and current snippets\n- `npx -y lavish-axi@0.1.87 playbook \u003Cid>` for focused artifact guidance (`npx -y lavish-axi@0.1.87 playbook` lists ids)\n\nIf lavish-axi output shows a follow-up command starting with `lavish-axi`, run it as `npx -y lavish-axi@0.1.87 ...` instead.\n\nThe version is pinned (ALFRED template), so a new release never runs\nunreviewed in a repo that holds someone's life. Bump it deliberately.\n\n## Request\n\n$ARGUMENTS\n\nIf the request above is non-empty, the user invoked `\u002Flavish` explicitly - fetch the current CLI guidance, then build that artifact.\nIf it is empty, infer what to visualize from the conversation.\n\n## ALFRED guardrails (added by this template, not upstream)\n\nThis repo holds personal data: health, money, relationships.\n\n- **Never `lavish-axi share`.** It publishes to a third-party host, public by\n  default, with no real delete. Treat it as irreversible. Use\n  `npx -y lavish-axi@0.1.87 export` for a portable local file instead.\n- Write artifacts under `.lavish\u002F` (git-ignored).\n- Set `LAVISH_AXI_HOST=127.0.0.1` if Tailscale or another VPN is up, so the\n  review server stays loopback-only.\n- **Any agent**: feedback comes back through `npx -y lavish-axi@0.1.87 poll \u003Cfile>`\n  in the foreground. If the agent's command timeout kills it (Codex,\n  OpenCode), run it again; feedback stays queued.\n- **Design for the reader**: one job per page, one decision per card, your\n  recommendation preselected, short plain text, big click targets. Calm\n  colors; nothing red, no counts of what's undone. ALFRED has no design\n  system, so use the CLI's default (Tailwind + DaisyUI) with a calm theme.\n","# Lavish Editor (optional)\n\nLavish Editor opens agent-generated HTML in the browser so a human can annotate it and send feedback back to the agent.\nReach for it when a plan, comparison, diagram, table, weekly review or decision tree will be clearer as a page than as prose.\nNeeds Node.js. If `npx` is missing, skip this skill and answer in text.\n\n## Current guidance lives in the CLI\n\nDo not follow workflow, design, or playbook instructions from this file - installed copies go stale. Get the current source of truth from the CLI:\n\n- `npx -y lavish-axi@0.1.87 --help` for commands and the review-loop workflow\n- `npx -y lavish-axi@0.1.87 design` for design-direction priority and current snippets\n- `npx -y lavish-axi@0.1.87 playbook \u003Cid>` for focused artifact guidance (`npx -y lavish-axi@0.1.87 playbook` lists ids)\n\nIf lavish-axi output shows a follow-up command starting with `lavish-axi`, run it as `npx -y lavish-axi@0.1.87 ...` instead.\n\nThe version is pinned (ALFRED template), so a new release never runs\nunreviewed in a repo that holds someone's life. Bump it deliberately.\n\n## Request\n\n$ARGUMENTS\n\nIf the request above is non-empty, the user invoked `\u002Flavish` explicitly - fetch the current CLI guidance, then build that artifact.\nIf it is empty, infer what to visualize from the conversation.\n\n## ALFRED guardrails (added by this template, not upstream)\n\nThis repo holds personal data: health, money, relationships.\n\n- **Never `lavish-axi share`.** It publishes to a third-party host, public by\n  default, with no real delete. Treat it as irreversible. Use\n  `npx -y lavish-axi@0.1.87 export` for a portable local file instead.\n- Write artifacts under `.lavish\u002F` (git-ignored).\n- Set `LAVISH_AXI_HOST=127.0.0.1` if Tailscale or another VPN is up, so the\n  review server stays loopback-only.\n- **Any agent**: feedback comes back through `npx -y lavish-axi@0.1.87 poll \u003Cfile>`\n  in the foreground. If the agent's command timeout kills it (Codex,\n  OpenCode), run it again; feedback stays queued.\n- **Design for the reader**: one job per page, one decision per card, your\n  recommendation preselected, short plain text, big click targets. Calm\n  colors; nothing red, no counts of what's undone. ALFRED has no design\n  system, so use the CLI's default (Tailwind + DaisyUI) with a calm theme.\n",{"name":5,"license":15,"metadata":24,"description":7,"user-invocable":20},{"author":25,"argument-hint":26},"Kun Chen (kunchenguid)","\u003Cwhat the artifact should show>","main","979ab4d3c106448c0ae25734f309bdabd4486cc4",".claude\u002Fskills\u002Flavish",0,"https:\u002F\u002Fgithub.com\u002Fhafeezhmha\u002Falfred","https:\u002F\u002Fgithub.com\u002Fhafeezhmha","https:\u002F\u002Fhafeezhmha.vercel.app","the machine - it's learning!","2026-11-04 23:21:29",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add hafeezhmha\u002Falfred --skill lavish",{"tool":42,"command":43},"bunx","bunx skills add hafeezhmha\u002Falfred --skill lavish",{"tool":45,"command":46},"pnpm","pnpm dlx skills add hafeezhmha\u002Falfred --skill lavish","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhafeezhmha\u002Falfred\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Flavish\u002FSKILL.md",true,[],[51,58,65,72],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7DDCTD5STFZP036S3TFA3DQ","life-architect","Set up or re-tune ALFRED for this person. Default is a 3-minute quick start that learns the rest one question a day; a full interview is available. Writes context.md, current.md, queue.md, areas\u002F and the personal section of AGENTS.md. Use on first run (when .life\u002FSETUP_NEEDED exists), when the person says \"set up alfred\", \"set up my life os\", \"full setup\", \"resume setup\", \"re-tune\" or \"my life changed\".","https:\u002F\u002Fgithub.com\u002Fhafeezhmha\u002Falfred\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Flife-architect\u002FSKILL.md",[],[],{"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":19},"01M7DDCFDK8YG9SH1C69CWPC2H","i-have-adhd","Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Use when the person says \"adhd mode on\"; stays on until \"stop adhd mode\".","https:\u002F\u002Fgithub.com\u002Fhafeezhmha\u002Falfred\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fi-have-adhd\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7DDCB63EE1X9TF8KC7DAYS7","grilling","Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, faces a big life decision, or uses any 'grill' trigger phrases.","https:\u002F\u002Fgithub.com\u002Fhafeezhmha\u002Falfred\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgrilling\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7DDC9T1MSKVWRB0SEKXSNFY","grill-me","A relentless interview to sharpen a plan or design.","https:\u002F\u002Fgithub.com\u002Fhafeezhmha\u002Falfred\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgrill-me\u002FSKILL.md",[],[]]