AI Desk Card

What it does

When your agent uses it

• Setting up an M5Paper e-ink card for the first time, including firmware and Wi-Fi
• Pushing a calendar, todo list or PR queue to the desk display
• Scheduling the card to refresh during working hours
• Troubleshooting a card that does not respond, or putting it to sleep

Example prompts

• “I just got an M5Paper; walk me through flashing it and connecting Wi-Fi.”
• “Show today's calendar and my open todos on the desk card.”
• “Refresh the card every 30 minutes during working hours.”
• “The card is not responding, find out why.”

Requirements

• An M5Paper V1.1 or M5Paper Color device
• PlatformIO (pio) to flash firmware
• Python 3 to run the daemon
• A Wi-Fi network for the device
• Pre-approved tools (allowed-tools): Bash, Read, Write, Edit

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1ALWAYS probe state first
2. 25 — Identify the device profile
3. 3Route based on state
4. 4Push a widget (the hot path)
5. 5When to suggest scheduled pushes

What it can do on your machine

Read from SKILL.md and the folder at commit dc3b498. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Write
  • Edit

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • bash
  • curl
  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AI Desk Card loads about 2k tokens when it runs. Until then it costs about 231 tokens; SKILL.md has 756 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~231

When it runs · the whole SKILL.md, loaded when a task matches

~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Write, Edit

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from op7418/ai-desk-card at commit dc3b498, republished under its GPL-3.0 licence (© op7418). 756 words, ~2,038 tokens.

name

ai-desk-card

description

Drive a physical e-ink desk card (M5Paper 540×960) sitting next to the user's monitor. Use whenever the user wants to: - show / push / display ANYTHING on their card / 卡片 / 副屏 / 墨水屏 / e-ink display / desk card / glanceable display / secondary display - set up the device for the first time (flash firmware, pair, provision Wi-Fi) — phrases like "刚拿到 M5Paper", "怎么装卡片", "first-time setup", "刷固件", "卡片没反应" - schedule recurring pushes / "每小时刷一次" / "工作时间显示日历" / "auto-refresh every 30 min" - configure what the card shows (weather, todos, calendar, inbox, PR queue, AI status, focus, scratch, deadlines, messages, now-playing, git-status, system, next-meeting, break-reminder, ai-tasks) - put the device to sleep / show business card / "息屏" / "睡眠" Single Skill, agent-agnostic: probes current state, then routes to the right sub-flow. Never asks "is the daemon running" — it checks.

allowed-tools

Bash, Read, Write, Edit

trigger_keywords

card, desk card, 卡片, 副屏, 墨水屏, e-ink, M5Paper, paper card, glanceable display, secondary display, ai-desk-card, 桌面卡片, dashboard card

bash $SKILL_DIR/scripts/state.sh

{
  "hardware":   { "pio_installed": bool, "m5paper_usb": str|null },
  "firmware":   { "flashed": bool, "ours": bool, "version": str|null },
  "daemon":     { "running": bool, "pid": int|null },
  "transport":  { "connected": bool, "type": "BLETransport|SerialTransport|WiFiTransport|null" },
  "device":     { "alive": bool, "last_seen_seconds": int|null,
                  "active_transport": "Wi-Fi|USB|BLE|null",
                  "battery_pct": int|null, "uptime": str|null },
  "wifi":       { "provisioned": bool, "ip": str|null },
  "interests":  { "configured": bool, "path": str|null }
}

curl -sf -X POST "${CARD_DAEMON_URL:-http://127.0.0.1:9877}/widget" \
  -H 'Content-Type: application/json' \
  -d @- <<'JSON'
{
  "slot": "top-left",
  "type": "weather",
  "data": { "city": "Beijing", "temp_c": 22, "icon": "sun", "summary": "晴" }
}
JSON

© op7418, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 84 other files (scripts, assets) in the repository root of op7418/ai-desk-card.

• SKILL.md
• .gitignore
• HANDOVER.md
• LICENSE
• PLAN.md
• PLAN_RENDERING_V06.md
• PRODUCT.md
• README.en.md
• README.md
• assets/profile.yaml
• assets/qr.png
• daemon/card_daemon.py
• daemon/card_render.py
• daemon/card_render_color.py
• daemon/card_render_settings.py
• daemon/card_render_settings_color.py
• daemon/card_render_sleep.py
• daemon/card_render_sleep_color.py
• daemon/color_daemon.py
• … and 66 more

Open the folder on GitHubat commit dc3b498