lavish
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.
- License 许可
- MIT
- 最近更新
- 2026-11-04
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- lavish
- license
- MIT
- metadata
- { "author": "Kun Chen (kunchenguid)", "argument-hint": "<what the artifact should show>" }
- description
- 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.
- user-invocable
- false
03 SKILL.md 正文
Lavish Editor (optional)
Lavish Editor opens agent-generated HTML in the browser so a human can annotate it and send feedback back to the agent.
Reach for it when a plan, comparison, diagram, table, weekly review or decision tree will be clearer as a page than as prose.
Needs Node.js. If npx is missing, skip this skill and answer in text.
Current guidance lives in the CLI
Do not follow workflow, design, or playbook instructions from this file - installed copies go stale. Get the current source of truth from the CLI:
npx -y lavish-axi@0.1.87 --helpfor commands and the review-loop workflownpx -y lavish-axi@0.1.87 designfor design-direction priority and current snippetsnpx -y lavish-axi@0.1.87 playbook <id>for focused artifact guidance (npx -y lavish-axi@0.1.87 playbooklists ids)
If lavish-axi output shows a follow-up command starting with lavish-axi, run it as npx -y lavish-axi@0.1.87 ... instead.
The version is pinned (ALFRED template), so a new release never runs unreviewed in a repo that holds someone's life. Bump it deliberately.
Request
$ARGUMENTS
If the request above is non-empty, the user invoked /lavish explicitly - fetch the current CLI guidance, then build that artifact.
If it is empty, infer what to visualize from the conversation.
ALFRED guardrails (added by this template, not upstream)
This repo holds personal data: health, money, relationships.
- Never
lavish-axi share. It publishes to a third-party host, public by default, with no real delete. Treat it as irreversible. Usenpx -y lavish-axi@0.1.87 exportfor a portable local file instead. - Write artifacts under
.lavish/(git-ignored). - Set
LAVISH_AXI_HOST=127.0.0.1if Tailscale or another VPN is up, so the review server stays loopback-only. - Any agent: feedback comes back through
npx -y lavish-axi@0.1.87 poll <file>in the foreground. If the agent's command timeout kills it (Codex, OpenCode), run it again; feedback stays queued. - Design for the reader: one job per page, one decision per card, your recommendation preselected, short plain text, big click targets. Calm colors; nothing red, no counts of what's undone. ALFRED has no design system, so use the CLI's default (Tailwind + DaisyUI) with a calm theme.
04 同仓库更多 Skills
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/ and the personal section of AGENTS.md. Use on first run (when .life/SETUP_NEEDED exists), when the person says "set up alfred", "set up my life os", "full setup", "resume setup", "re-tune" or "my life changed".
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".
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.
grill-me
A relentless interview to sharpen a plan or design.