← Search

Roborock Vacuums
Smart Home 📌 Pinned version: commit e6fe517
⚙ Needs: Before you start: read this whole install prompt…

Roborock Vacuums

Read status and send supported cleaning, pause or return-to-dock commands to a compatible Roborock vacuum through python-roborock's encrypted local TCP channel on port 58867 via Muse Home Link

At a glance
What
Read status and send supported cleaning, pause or return-to-dock commands to a compatible Roborock vacuum through python-roborock's encrypted local TCP channel on port 58867 via Muse Home Link
Cost
Free
Needs
Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else.
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

M
Created by: Meta (facebookincubator)
⌁

Install

Copy the install package below, then paste it into Muse📌 Pinned version: commit e6fe517

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites — Muse Home Link and a compatible physical device are required to USE this skill, not to install it: installing the skill file itself needs no account, no key and no device, and this install does NOT set up Home Link, pair anything or ask for any credential. But the skill is instructions only. To use it I must read and follow ~/docs/devices/home_link.md in my Muse environment, have the compatible physical device named below already set up on my local network, and have the vacuum's existing local key and device UID, supplied securely, plus the model information the compatible client needs, and my permission for the requested robot movement with a safe, prepared cleaning area. Installing the file configures none of that. Install "Roborock Vacuums" for me. It works with a confirmed Roborock-app-compatible vacuum that supports the local channel described by python-roborock; a Roborock vendor label alone does not select this skill. That channel is an encrypted local TCP channel on port 58867 at the current local endpoint — different from the UDP miIO path used by some Mi Home devices, and not interchangeable with A01 wet/dry protocols. It initializes the channel with the current host, the existing local key and the device UID, preserving protocol negotiation, framing/encryption, sequence correlation and keepalive. It reads the model's supported status, battery, current mission and errors, then sends only the documented local cleaning, pause or return-to-dock command the model supports, correlates the response and polls or subscribes to fresh state. Cloud bootstrap and fallback paths are disabled or omitted: a local failure is reported, never quietly switched to a cloud channel. Verification means the status reflects the requested mission — an acknowledgement alone does not prove movement or completion, and returning to dock is not docked/charging; faults are reported without automatic retries. Limits: no cloud account or bootstrap, no map retrieval, no room-map setup, no cloud-dependent station functions; not every Roborock generation supports the same local protocol. Repository: https://github.com/facebookincubator/muse-gadget-sdk (the skill is the whole skills/gadget-roborock-vacuums/ folder at the pinned commit: SKILL.md only, 1 file) Pinned version: install the code at commit e6fe5174092702ffddae6f90759a38d55a4ebae1 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/facebookincubator/muse-gadget-sdk into a temporary folder, check out commit e6fe5174092702ffddae6f90759a38d55a4ebae1, and copy the skills/gadget-roborock-vacuums/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - SKILL.md: SHA-256 4ce605b976b71994568c3b0b3a5fec590f77eb50adb1e931abe2a128aaa6a2f2 If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full, and tell me in plain words: what the skill does when used, what it connects to, whether it reads or sends any personal information or credentials, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 1 file only: SKILL.md (2,778 bytes). There is no script, no code and no configuration in it; at use time it works through python-roborock's encrypted local TCP channel (port 58867) routed through Muse Home Link against my own vacuum. It has no dependency on any other gadget skill in this lot, and it is not the Mi Home UDP miIO path. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit. No vacuum is contacted and no movement is started during installation. - At use time, exchanges go only to my local vacuum, initialized with its current host, its existing local key and its device UID. The client's cloud bootstrap and fallback paths are disabled or omitted, and a local failure is reported, never quietly switched to a cloud channel; no credential is sent to any cloud or third party. - The skill does no cloud account or bootstrap work, no map retrieval, no room-map setup and no cloud-dependent station functions, and A01 wet/dry devices are not interchangeable with this vacuum path. - Do not pair any device, do not ask for or set any credential, do not run any control, print, scan or playback action, and do not use the skill in any way during this install: Home Link setup, pairing and use are my decisions, later, when I actually ask for them. 3. When I say "yes, install", install it as a skill: copy the whole gadget-roborock-vacuums folder into the agent's skills directory, in a folder named exactly "gadget-roborock-vacuums", keeping its 1 file (SKILL.md at its root). The exact folder name matters: relative links between sibling gadget skills depend on these exact names. 4. Verify with no network calls: frontmatter valid (name: gadget-roborock-vacuums), the 1 file in place with matching fingerprint. Do not run anything and do not connect to any device to verify. 5. Report what was installed, where, and what I still need to do myself (for example: read ~/docs/devices/home_link.md in my Muse environment and follow its Home Link rules; have a compatible Roborock vacuum already set up on my local network; supply its existing local key and device UID securely; and give permission for the requested movement with a safe, prepared cleaning area — knowing a local failure will be reported, never switched to the cloud; using the skill is a separate step that only starts when I ask for it, and the use-time exchanges disclosed above happen only then). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.

🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this build does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-22
🔒 Security and provenance
📌 Pinned version: commit e6fe517 · 2026-10-22
🔎 Last checked · Oct 22, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a build before installing →

?

Questions

How do I install a build?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.