AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

daily-focus-board

Spin up a personal, motivating daily focus board that renders in a browser canvas and that the user drives by talking to their AI partner. Tasks track status (to-do → in progress → done) with timestamped progress notes and roll up into a "today's momentum" feed; numeric-goal tasks (pages, pomodoros, reps) render as progress-bar counters. Executive-function / neurodivergent-friendly by design: Focus mode, kind "not today" carryover (no overdue-shaming), a brain-dump box, reduced-motion, and gentle deadline countdowns. Add, reorder, and relabel tasks live, assign Eisenhower priority (Do first / Schedule / Delegate / Later), open with an above/below-the-line check-in and a daily mantra, and save an end-of-day recap. Use when someone wants to plan their day, stay focused, kick off a work session, or track progress. Progress persists in the browser (localStorage).

Original source
github
License
MIT
Pinned revision
5269f7ea2d6c3a9bfda5ed878b6726cf509121fd

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

This skill also requires local files or dependencies. Remote reading alone may not be enough.

Ask your assistant

Use Agentic Memory skills to read github--daily-focus-board at revision 5269f7ea2d6c3a9bfda5ed878b6726cf509121fd, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 4

references/customize.md

Customizing the Daily Focus Board

Theming

Colors live in the :root CSS block of assets/board.template.html (--ember, --good, --urgent, backgrounds). The look is warm/dark by default. Tag colors: new (green), deadline (red), career (purple) — add your own by copying a .tagedit.<name> rule and passing that name as a task's tagc (use a plain class name: letters, digits, -, _).

v2 — file-backed state (closes the agent loop)

v1 stores progress in the browser (localStorage), which the agent can't read back. To let your AI partner read your progress (e.g. to write your end-of-day journal) and write it (e.g. "mark the design doc done" from chat), back the board with a JSON file instead:

  • Board writes state to board-state.json (via a tiny local endpoint or the File System Access API) instead of localStorage, and reads it on load.
  • The agent reads/writes that same JSON. Now it's a two-way loop: you talk, the board updates, and the agent can summarize the day from the same source of truth.

This is the genuinely agentic version — but it needs a small local write path, so it's a deliberate upgrade, not the zero-setup v1.

Optional — the "shared signals" bridge (for multi-agent workshop users)

The board's momentum notes are the same shape as an agent progress signal: a timestamped self-report of what got done. If you run a multi-agent setup that emits .signals/*.json (e.g. one signal per unit of work), you can feed those into the momentum feed so agent work and your work share one timeline — "my personal board and my agent team share one nervous system."

Keep this opt-in. The board must stand completely alone with zero workshop dependency — that's what makes it universal. The bridge is a bonus for advanced users, never a requirement.