Build a Jarvis that briefs you every morning

Here's a reference image of the dashboard vibe I want (attached). Build it as ONE self-contained dashboard.html file (Canvas plus CSS, no external libraries). Near-black navy background, a glowing central core with orbital rings and rotating dashed HUD arcs, and a heads-up layout: top-left a JARVIS title, subtitle and today's date; top-right a live ticking clock and a connector status list (green dot online, amber blinking offline); a streaming activity log down the left that reveals one line at a time; a stats panel on the right with thin glowing bars; a calendar and a weather panel; big figures across the bottom; and a bottom bar with a glowing "BRIEF ME" button.

Read ALL the numbers and text from a separate jarvis_data.js that sets window.JARVIS_DATA, so I only edit that file day to day. Save brief.mp3 alongside dashboard.html, add a hidden audio element for it, and make clicking BRIEF ME play it and pulse the core while it speaks.

Make it look expensive and responsive. Then take a screenshot of what you built, compare it to my reference image, list the differences, and fix them. Repeat until it matches.

# Who I am
I'm [name], I [what you do]. I care most about [your #1 goal right now].

# What I'm working on this month
- [project 1], [project 2], [project 3]

# My priorities, ranked
1. [top priority]  2. [next]  3. [next]

# My tone
[e.g. warm, direct, no corporate filler]

# Hard rules
- Always draft, never send. Never take irreversible actions without asking.
- Only use the apps I've connected.

You are my personal assistant, my own Jarvis. First, read my CLAUDE.md so you know who I am, my projects, my priorities and my tone. From now on, act as a proactive chief of staff for me, not a generic chatbot.

Keep this skill fully self-contained: list every source to pull and exactly how to format the brief, because when it runs on a schedule it has no memory of our chats.

Build me a "morning brief" routine, and save it as a reusable skill I can trigger by phrase (like "run my morning brief", "brief me", or "what's on my plate"). When I trigger it, do this:

1. CALENDAR: read today's events from my Google Calendar. Flag anything that needs prep, and any conflicts or gaps.
2. INBOX: scan my Gmail from the last 24 hours. Group it into needs-a-reply / FYI / ignore. For the needs-a-reply group, draft short replies in my tone and leave them in Drafts. Never send.
3. PRIORITIES + TASKS: read my priorities and task list (from my Notion or my priorities note), and pick the 3 things that actually matter most today, ranked, with a one-line why for each.
4. ONE THING TO KNOW: surface a single important signal, a deadline, a number that moved, a follow-up I'm forgetting.

Then write it as 6 to 8 short spoken lines, in my voice, warm and direct, no filler. END with the single most important question: "What should I handle first?"

Write the brief in [your language]. Save it to brief.txt and to a Notion page. Then rewrite jarvis_data.js so the dashboard shows today's real numbers and a one-line activity log per source you read, and mark each connector online or offline based on whether the call actually succeeded. Then read the brief out loud through my Fish Audio voice.

If a source is empty or a connector is down, say so plainly in the brief and mark it offline on the dashboard. Never fill a gap with a plausible guess.

Rules, always: you draft, I approve. Never send email, post, delete, or take any irreversible action on your own. Only pull from the apps I've connected.

Write me a speak script that turns text into audio and plays it, with three tiers so it never goes silent:

1. Fish Audio. POST https://api.fish.audio/v1/tts, model sent as an HTTP header (model: s2.1-pro-free), reference_id and text in the body, API key read from FISH_API_KEY in my .env file. Generate the speech in [your language].
2. If that fails, fall back to edge-tts with the voice en-GB-RyanNeural at --rate=-4%.
3. If that fails, fall back to the built-in system voice (say -v Daniel on macOS).

Two things that matter: after the API call, check the response is ACTUALLY audio before playing it (check the bytes with `file`, not just the HTTP status), and check the exit code and that the output file exists before moving on, so a failure falls through to the next tier instead of silently producing nothing.

Print which tier spoke, like "voice: fish-audio" or "voice: edge-tts fallback", so I can see when my main voice quietly stopped working.

Save the audio as brief.mp3 in the same folder as dashboard.html so the BRIEF ME button finds it.

Every time my morning brief skill runs, have it rewrite jarvis_data.js from what it actually read: today's date, the event count and next event, the unread and needs-a-reply counts, my top 3 priorities, and one activity-log line per source. Set each connector's status to online only if that call actually returned data, otherwise offline. Never write a number the run didn't actually retrieve. Then serve the folder at http://localhost:8787 with a tiny local server, and give me a one-line script that starts the server and opens the page.