Agent skill

AI Desk Card Onboarding

Walks a user through first-time setup of an AI Desk Card e-ink device, probing daemon, USB, BLE, Wi-Fi and firmware state and fixing whatever is missing.

Custom licenceAuto-check: notesDevelopment

SKILL.md written in Chinese; this summary is our English description.

Install AI Desk Card Onboarding

skills CLI

$ npx skills add op7418/ai-desk-card --skill card-onboard -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install op7418/ai-desk-card card-onboard --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/op7418/ai-desk-card.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/card-onboard .claude/skills/card-onboard && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "card-onboard" agent skill from https://github.com/op7418/ai-desk-card/tree/main/plugin/skills/card-onboard into .claude/skills/card-onboard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "card-onboard", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/op7418/ai-desk-card/tree/main/plugin/skills/card-onboard

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add op7418/ai-desk-card --skill card-onboard -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install op7418/ai-desk-card card-onboard --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/op7418/ai-desk-card.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugin/skills/card-onboard .agents/skills/card-onboard && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "card-onboard" agent skill from https://github.com/op7418/ai-desk-card/tree/main/plugin/skills/card-onboard into .agents/skills/card-onboard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "card-onboard", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add op7418/ai-desk-card --skill card-onboard -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install op7418/ai-desk-card card-onboard --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/op7418/ai-desk-card.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugin/skills/card-onboard .cursor/skills/card-onboard && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "card-onboard" agent skill from https://github.com/op7418/ai-desk-card/tree/main/plugin/skills/card-onboard into .cursor/skills/card-onboard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "card-onboard", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/op7418/ai-desk-card.git --path plugin/skills/card-onboard

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add op7418/ai-desk-card --skill card-onboard -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install op7418/ai-desk-card card-onboard --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/op7418/ai-desk-card.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugin/skills/card-onboard .gemini/skills/card-onboard && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "card-onboard" agent skill from https://github.com/op7418/ai-desk-card/tree/main/plugin/skills/card-onboard into .gemini/skills/card-onboard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "card-onboard", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install op7418/ai-desk-card card-onboard

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add op7418/ai-desk-card --skill card-onboard -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/op7418/ai-desk-card.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugin/skills/card-onboard .github/skills/card-onboard && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "card-onboard" agent skill from https://github.com/op7418/ai-desk-card/tree/main/plugin/skills/card-onboard into .github/skills/card-onboard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "card-onboard", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add op7418/ai-desk-card --skill card-onboard -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install op7418/ai-desk-card card-onboard --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/op7418/ai-desk-card.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugin/skills/card-onboard .opencode/skills/card-onboard && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "card-onboard" agent skill from https://github.com/op7418/ai-desk-card/tree/main/plugin/skills/card-onboard into .opencode/skills/card-onboard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "card-onboard", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: card-onboard
GitHub stars: 151
Token cost: ~1.2k tokens
SKILL.md length: 352 words
Files: 2 (incl. scripts)
Skills in repo: 4
Repo updated: May 22, 2026
First seen: Oct 7, 2026
Licence: Custom licence

At a glance

Walks a user through first-time setup of an AI Desk Card e-ink device, probing daemon, USB, BLE, Wi-Fi and firmware state and fixing whatever is missing.

Works in 5 steps: 拔 USB，daemon 自动 fallback 到 BLE → /card-stop && /card-start → daemon 自动扫描 Card-* 设备 → 1-2 分钟连上 → …
Setting up a new AI Desk Card for the first time
SKILL.md covers 一次性原则, 探针入口, 决策树（按顺序处理；命中分支就先修，再回到 probe 验证） and 安抚话术, plus 2 more sections
Runs Shell scripts from its folder; calls bash

What it does

The skill takes someone from an unboxed device to widgets on the screen over Wi-Fi. Its first rule is to run scripts/probe.sh before anything else, which returns the daemon state, the transport, a firmware check and mDNS visibility as one JSON object, instead of asking the user what is running. The agent reports progress at each step, stops and hands over diagnostics rather than retrying in a loop, and prefers Wi-Fi because a frame takes about 0.2 seconds there, against 1 to 32 seconds over USB, and BLE does not carry frames (a known issue).

A decision tree covers each state in order. A device already on Wi-Fi that the daemon is not using triggers a restart with /card-stop and /card-start; a stopped daemon is started; an offline device prompts for power or a USB-C data cable; a USB port that is present but not connected gets a restart.

A device running other firmware is offered a flash with /card-install flash only after the user agrees, since flashing erases other programs. A device with firmware but no Wi-Fi is offered /card-wifi-setup, with credentials stored on the device only. When everything is ready it offers a default widget set of weather, AI status, focus and to-do. The SKILL.md is written in Chinese.

When your agent uses it

Setting up a new AI Desk Card for the first time
Reconnecting the device after moving to a new machine or Wi-Fi network
Checking the device after a firmware update
Diagnosing why the card shows nothing or will not connect

Example prompts

“I just got my AI Desk Card; walk me through the first-time setup.”
“The card stopped responding after I moved to a new Wi-Fi network. Figure out what's wrong.”
“Flash the AI Desk Card firmware and get it onto Wi-Fi.”

Requirements

An AI Desk Card device based on the M5Paper e-ink display
A USB-C data cable for flashing and first pairing
Pre-approved tools (allowed-tools): Bash, Read

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

拔 USB，daemon 自动 fallback 到 BLE
/card-stop && /card-start
daemon 自动扫描 Card-* 设备 → 1-2 分钟连上
重 probe → transport.type == "BLETransport"
推 widget 失败时回到此分支建议配 Wi-Fi

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
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
- bash
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- github.com
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 Onboarding loads about 1.2k tokens when it runs. Until then it costs about 119 tokens; SKILL.md has 352 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~119
When it runs · the whole SKILL.md, loaded when a task matches: ~1.2k

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

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
```
allowed-tools: Bash, Read
```

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 352 words (~1,165 tokens).

“把用户从"刚拿到设备/啥都没装"带到"四个 widget 在屏上、Wi-Fi 在线、推帧 0.2 秒到位"。”

— opening of SKILL.md by op7418, Custom licence

name: card-onboard
allowed-tools: Bash, Read
trigger_keywords: card onboard, 入职, 第一次用, first-time setup, 刷固件, 怎么连卡片, ai-desk-card 连不上, 配对, 配 wifi

Outline of SKILL.md

card-onboard — AI Desk Card 首次接入流程
一次性原则
探针入口
决策树（按顺序处理；命中分支就先修，再回到 probe 验证）
G — mdns_peer != null 且 transport.type != "WiFiTransport"
A — daemon.running == false
B — daemon.running == true && serial_ports == [] && mdns_peer == null
C — transport.connected == false 但 serial_ports != []
D — transport.connected == true && firmware.our == false
E — transport.connected == true && firmware.our == true 但 mdns_peer == null
F — 全绿，要不要推默认 widget
Z — 用户明确要用 BLE only（不推荐）
安抚话术
不要做的事
排错信息收集

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (scripts) in plugin/skills/card-onboard of op7418/ai-desk-card.

SKILL.md
scripts/probe.sh

Open the folder on GitHubat commit dc3b498

Compare with similar skills

AI Desk Card Onboarding next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

AI Desk Card Onboarding compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
AI Desk Card Onboarding this skillop7418/ai-desk-card	151	—	~1.2k	Automated safety check: Notes	Custom licence	4 mo ago
RuView Hardware Setupruvnet/RuView	97k	—	~1.8k	Automated safety check: Notes	MIT	today
Esp32 Firmware Engineeralxv2016/folloup-sticky	117	1 repos	~3.8k	Automated safety check: Pass	GPL-3.0	2 mo ago
RuView mmWave Radar Setupruvnet/RuView	97k	—	~907	Automated safety check: Notes	MIT	today
Embedded DebugFastLED/FastLED	7.5k	—	~1.4k	Automated safety check: Pass	MIT	today
Auto EmbeddedDunCanYounG-1/MICU-auto-embedded	253	—	~1.6k	Automated safety check: Pass	CC-BY-NC-4.0	3 days ago

Similar skills

RuView Hardware Setup
ruvnet/RuView
Brings a RuView CSI sensing node online by building ESP32-S3 or ESP32-C6 firmware, flashing the board, provisioning WiFi and checking the serial output.
97k GitHub stars~1.8k tokensUpdated today
DevelopmentAuto-check: notes
Esp32 Firmware Engineer
alxv2016/folloup-sticky
ESP32 firmware engineering for ESP-IDF projects. An agent skill from alxv2016/folloup-sticky.
117 GitHub starsUsed in 1 repo~3.8k tokens
DevelopmentAuto-check passed
RuView mmWave Radar Setup
ruvnet/RuView
Sets up and runs 60 GHz and 24 GHz mmWave radar sensing on ESP32 boards in RuView, alone or fused with WiFi CSI.
97k GitHub stars~907 tokensUpdated today
DevelopmentAuto-check: notes
Embedded Debug
FastLED/FastLED
Firmware crash analysis, stack trace decoder, and register dump interpreter for ESP32/ARM/AVR platforms.
7.5k GitHub stars~1.4k tokensUpdated today
DevelopmentAuto-check passed
Auto Embedded
DunCanYounG-1/MICU-auto-embedded
全平台嵌入式 AI 开发框架（对标 Trellis）：把 RIPER-5 五阶段协议 + 四文件记忆 + 分层架构门禁 + Scout/Builder/Verifier 多 Agent + 24 个工具调用技能（build/flash/debug/serial/can/modbus/visa/static/memory/rtos/scons），做成『装进工程、项目级 hook…
253 GitHub stars~1.6k tokensUpdated 3 days ago
DevelopmentAuto-check passed
Embedded Cpp14 Misra
BlueAndi/Pixelix
A skill your agent uses when writing, reviewing, or refactoring C/C++ firmware code in this repository (src/, lib/, test/) — creating or editing .h/.hpp/.cpp files, applying MISRA-oriented and…
443 GitHub stars~2k tokensUpdated yesterday
DevelopmentAuto-check passed

Questions about AI Desk Card Onboarding

What does AI Desk Card Onboarding do?

Walks a user through first-time setup of an AI Desk Card e-ink device, probing daemon, USB, BLE, Wi-Fi and firmware state and fixing whatever is missing. The skill takes someone from an unboxed device to widgets on the screen over Wi-Fi.sh before anything else, which returns the daemon state, the transport, a firmware check and mDNS visibility as one JSON object, instead of asking the user what is running.

When should I use AI Desk Card Onboarding?

AI Desk Card Onboarding fits situations like: setting up a new AI Desk Card for the first time; reconnecting the device after moving to a new machine or Wi-Fi network; checking the device after a firmware update; diagnosing why the card shows nothing or will not connect.

How do I install AI Desk Card Onboarding in Claude Code?

Run `npx skills add op7418/ai-desk-card --skill card-onboard -a claude-code`. Or copy the skill folder (plugin/skills/card-onboard in op7418/ai-desk-card) into .claude/skills/card-onboard in your project. Claude Code loads it when a task matches its description.

How do I install AI Desk Card Onboarding in Codex?

Run `npx skills add op7418/ai-desk-card --skill card-onboard -a codex`. Or copy the skill folder (plugin/skills/card-onboard in op7418/ai-desk-card) into .agents/skills/card-onboard in your project. Codex loads it when a task matches its description.

Can I use AI Desk Card Onboarding in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add op7418/ai-desk-card --skill card-onboard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/card-onboard, .gemini/skills/card-onboard, .github/skills/card-onboard and .opencode/skills/card-onboard in your project.

What does AI Desk Card Onboarding need to run?

Going by SKILL.md and its folder, AI Desk Card Onboarding needs a shell for the scripts in its folder and the command-line tools its instructions call (bash). Our summary lists: An AI Desk Card device based on the M5Paper e-ink display; A USB-C data cable for flashing and first pairing. Its frontmatter pre-approves these tools: Bash, Read.

Does AI Desk Card Onboarding access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is AI Desk Card Onboarding safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does AI Desk Card Onboarding use?

AI Desk Card Onboarding has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does AI Desk Card Onboarding use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to AI Desk Card Onboarding?

Skills that share tags, products or a category with AI Desk Card Onboarding: RuView Hardware Setup (ruvnet/RuView, 97k stars), Esp32 Firmware Engineer (alxv2016/folloup-sticky, 117 stars), RuView mmWave Radar Setup (ruvnet/RuView, 97k stars) and Embedded Debug (FastLED/FastLED, 7.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Desk Card Onboarding?

op7418 (a GitHub user) maintains it in op7418/ai-desk-card, which has 151 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on May 22, 2026.

Source: op7418/ai-desk-card on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

AI Desk Card Onboarding

Install AI Desk Card Onboarding

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Files

Compare with similar skills

Similar skills

RuView Hardware Setup

Esp32 Firmware Engineer

RuView mmWave Radar Setup

Embedded Debug

Auto Embedded

Embedded Cpp14 Misra

More from op7418/ai-desk-card

AI Desk Card

M5Paper Card Widgets

AI Desk Card Wi-Fi Setup

Questions about AI Desk Card Onboarding

Install AI Desk Card Onboarding

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Files

Compare with similar skills

Similar skills

More from op7418/ai-desk-card

Related

Questions about AI Desk Card Onboarding