𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 𝗰𝗮𝗻 𝘁𝘂𝗿𝗻 𝗶𝘁 𝗶𝗻𝘁𝗼 𝗮 𝗳𝘂𝗹𝗹 𝗼𝗽𝗲𝗿𝗮𝘁𝗶𝗻𝗴 𝘀𝘆𝘀𝘁𝗲𝗺: 𝗱𝗮𝘀𝗵𝗯𝗼𝗮𝗿𝗱, 𝘀𝗸𝗶𝗹𝗹𝘀, 𝗺𝗲𝗺𝗼𝗿𝘆, 𝗮𝗻𝗱 𝗹𝗼𝗰𝗮𝗹 𝘃𝗼𝗶𝗰𝗲.

𝗛𝗲𝗿𝗲'𝘀 𝘁𝗵𝗲 𝗳𝘂𝗹𝗹 𝗯𝗿𝗲𝗮𝗸𝗱𝗼𝘄𝗻 — 𝗹𝗮𝘆𝗲𝗿 𝗯𝘆 𝗹𝗮𝘆𝗲𝗿.

𝟭. 𝗧𝗛𝗘 𝗖𝗢𝗠𝗠𝗔𝗡𝗗 𝗖𝗘𝗡𝗧𝗘𝗥

→ One Obsidian plugin, written by Claude Code, holds every metric you care about.
→ Token usage, calendar, social numbers, daily reports, research summaries. One screen.

𝟮. 𝗢𝗡𝗘-𝗖𝗟𝗜𝗖𝗞 𝗥𝗨𝗡𝗦

→ Every skill becomes a button on the dashboard, or a spoken command.
→ Fire a morning intel report without ever opening a terminal.

𝟯. 𝗩𝗢𝗜𝗖𝗘, 𝗧𝗛𝗥𝗘𝗘 𝗧𝗜𝗘𝗥𝗦

→ Tier one runs a skill. Tier two looks up an existing report.
→ Tier three runs deep research headlessly, in the background.
→ Answers come back as speech. It works even when Obsidian isn't the active window.

𝟰. 𝗧𝗛𝗘 𝗦𝗞𝗜𝗟𝗟 𝗕𝗔𝗖𝗞𝗕𝗢𝗡𝗘

→ List what you already do by hand: research scanning, social metrics, scheduling.
→ Codify each one into a deterministic skill. Test it manually, then automate it.

𝟱. 𝗧𝗛𝗘 𝗠𝗘𝗠𝗢𝗥𝗬 𝗟𝗔𝗬𝗘𝗥

→ Three tiers: raw data, wiki-style syntheses, finished deliverables.
→ Claude Code gets a map of your vault, so it burns fewer tokens finding things.
→ This isn't about more memory. It's about organised memory.

𝟲. 𝗛𝗢𝗪 𝗧𝗢 𝗕𝗨𝗜𝗟𝗗 𝗜𝗧

→ Talk through your daily workflows, or just read your own Claude Code logs.
→ Mock the dashboard visually, then let Claude Code generate the plugin from it.
→ Add hot reload and you're done.

𝗛𝗲𝗿𝗲'𝘀 𝘁𝗵𝗲 𝗽𝗮𝗿𝘁 𝗺𝗼𝘀𝘁 𝗽𝗲𝗼𝗽𝗹𝗲 𝘀𝗸𝗶𝗽:

𝗔 𝗰𝗼𝗺𝗺𝗮𝗻𝗱 𝗰𝗲𝗻𝘁𝗲𝗿 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗮 𝘀𝗸𝗶𝗹𝗹 𝗯𝗮𝗰𝗸𝗯𝗼𝗻𝗲 𝗶𝘀 𝗮 𝗽𝗿𝗲𝘁𝘁𝘆 𝗳𝗮𝗰𝗲 𝘄𝗶𝘁𝗵 𝗻𝗼𝘁𝗵𝗶𝗻𝗴 𝗯𝗲𝗵𝗶𝗻𝗱 𝗶𝘁.

The dashboard is the last step, not the first.

Start with what you actually do every day.

𝗧𝗛𝗘 𝗪𝗛𝗢𝗟𝗘 𝗦𝗬𝗦𝗧𝗘𝗠 𝗜𝗡 𝗙𝗢𝗨𝗥 𝗟𝗜𝗡𝗘𝗦

Skills = what it can do.
Memory = what it can find.
Dashboard = what you can see.
Voice = how you reach it.