Seeed-Solution/reterminal_skill / skill
reterminal-skill
VerifiedUse when creating, uploading, sending, deleting, or managing SenseCraft HMI playlists and pages through the HMI API.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.1 KB |
| references/api.md | markdown | 2.5 KB |
| scripts/reterminal-skill.mjsexecutable | script | 15.3 KB |
SKILL.md
View on GitHub---
name: reterminal-skill
description: Use when creating, uploading, sending, deleting, or managing SenseCraft HMI playlists and pages through the HMI API.
---
# reTerminal
Use this skill when the user asks to create, upload, send, delete, or manage HMI playlists/pages with the SenseCraft HMI API.
## Requirements
The agent environment must provide:
- `HMI_API_BASE`: SenseCraft HMI API base URL, for example `https://sensecraft-hmi-api.seeed.cc`
- `HMI_API_KEY`: user API key sent as the `api-key` request header
Optional device defaults:
- `HMI_DEVICE_MAC`: default target device MAC address
- `HMI_DEVICE_ID`: default target device ID, resolved through `GET /api/v2/user/device/list`
- `HMI_DEVICE_NAME`: default exact device name, resolved through `GET /api/v2/user/device/list`
Do not request, create, persist, or echo API keys during install or routine use. API key management uses JWT-only endpoints and is outside this skill.
## Script
Use the bundled deterministic helper:
```bash
node scripts/reterminal-skill.mjs <command> [options]
```
Commands:
- `list-devices`
- `create-playlist --name NAME [--mac-address MAC]`
- `upload-image-base64 --image-base64 BASE64 [--filename NAME] [--mac-address MAC]`
- `upload-file --file PATH [--filename NAME] [--mac-address MAC]`
- `create-image-page --name NAME --image-url URL [--mac-address MAC]`
- `upsert-pages --playlist-id ID --page-id ID [--sort N]`
- `send-playlist --playlist-id ID [--mac-address MAC | --device-id ID | --device-name NAME]`
- `set-refresh-interval (--seconds N | --minutes N) [--mac-address MAC | --device-id ID | --device-name NAME]`
- `delete-playlist --playlist-id ID [--mac-address MAC | --device-id ID | --device-name NAME]`
- `delete-page --page-id ID [--mac-address MAC | --device-id ID | --device-name NAME]`
- `create-upload-send --name NAME (--image-base64 BASE64 | --file PATH) [--page-name NAME] [--mac-address MAC | --device-id ID | --device-name NAME]`
For commands that need a target device, prefer this order:
1. Use explicit `--mac-address`.
2. Otherwise use `HMI_DEVICE_MAC`.
3. Otherwise resolve `--device-id`, `--device-name`, `HMI_DEVICE_ID`, or `HMI_DEVICE_NAME` through `list-devices`.
4. If no selector is provided and exactly one device is returned, use that device.
5. If multiple devices are returned, stop and ask the user to choose a device ID or exact device name. Do not choose by fuzzy matching.
All commands print JSON. For failed downlink during `create-upload-send`, preserve the returned `playlist_id` and `page_id` from the JSON error so the user can retry or clean up.
For a 1-minute refresh interval, call `set-refresh-interval --minutes 1`; the script sends `refresh_interval: 60` because the current local API stores and downlinks the value in seconds.
## Safety
Deletion commands require explicit numeric IDs. Never delete playlists or pages by fuzzy name matching.
If the API returns `code=9003`, report that the API key is missing, invalid, revoked, or expired. If it returns `code=401`, report that authentication failed or the endpoint did not accept API-key fallback.
See `references/api.md` for endpoint details.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |