Ecovacs logo

Ecovacs

CommunityPopular
Anil-matcha
ecovacs

Control Ecovacs DEEBOT robot vacuums through the Ecovacs Open Platform: device list, status, battery, cleaning start/pause/stop, dock return. Trigger phrases: ecovacs, deebot, robot vacuum, start cleaning, dock vacuum.

Overview

PublisherAnil-matcha
Repositoryawesome-muse-connectors
Skill nameecovacs
Stars
1.4K
Forks
309
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Anil-matcha on GitHub. Read the source before you install it.

Installation

Install the Ecovacs AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/ecovacs
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git /tmp/awesome-muse-connectors
mkdir -p .claude/skills
cp -r /tmp/awesome-muse-connectors/connectors/ecovacs .claude/skills/ecovacs
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ecovacs in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ecovacs on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ecovacs is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Ecovacs

Purpose

Control Ecovacs DEEBOT robot vacuums through the official Ecovacs Open Platform: list bound robots, read robot state and battery, start/pause/resume/stop cleaning, send the robot back to its dock, and set the sweep/mop work mode. Use when the user mentions their DEEBOT or robot vacuum.

Tooling

All commands go through bin/ecovacs.py. --region selects the Open Platform region (global for open.ecovacs.com, cn for open.ecovacs.cn; default global) and must match the region of the user's Ecovacs account and robots. --robot is the robot's nickname (a fragment of the name shown in the app is enough for the gateway to match it).

bash
bin/ecovacs.py auth --region global                 # verify the Access Key
bin/ecovacs.py devices                              # list bound robots
bin/ecovacs.py status --robot Blue                  # cleaning/paused/docked state
bin/ecovacs.py battery --robot Blue                 # battery percent
bin/ecovacs.py stats --robot Blue                   # area cleaned, duration

# MEDIUM: cleaning start needs --confirm "<exact effect>" on first use per robot
bin/ecovacs.py clean --robot Blue --confirm "start cleaning on Blue"

# LOW: no confirmation
bin/ecovacs.py pause --robot Blue
bin/ecovacs.py resume --robot Blue
bin/ecovacs.py stop --robot Blue
bin/ecovacs.py dock --robot Blue
bin/ecovacs.py undock --robot Blue
bin/ecovacs.py set-work-mode --robot Blue --mode 0  # 0=sweep+mop, 1=sweep only, 2=mop only, 3=sweep then mop

The clean command starts a whole-home clean. Zone/room cleaning needs area IDs from the map and is not shipped; use the app for targeted cleans.

Auth

  • Provider id: ecovacs (credential is collected as custom.ecovacs)
  • Collection: self-serve Access Key (AK) created or viewed in the Ecovacs Open Platform console under Service overview, stored via the secure credential flow (credentials.request_api_access) with query-param placement on ak. The AK is passed as ?ak= on the request URL, per Ecovacs' vendor-published Deebot skill reference; it never appears on the command line, in the environment, or in a file.
  • Allowed hosts: open.ecovacs.com, open.ecovacs.cn (selected with --region)
  • Status check: bin/ecovacs.py auth (must return "ok": true)
  • Region matters: use the same regional portal for the AK, the account, and the robots, or calls fail with AK/permission errors. This is the most common setup mistake.

Operating Rules

  1. clean (start cleaning) is a MEDIUM actuation: the robot drives itself around the home. It needs --confirm "start cleaning on <robot>" naming the exact robot on first use per robot; the CLI records it locally (~/.cache/muse-connectors/ecovacs/confirmed.json) and later runs proceed without asking.
  2. Pause, resume, stop, dock return, and work-mode changes are LOW: they are trivially reversible and need no confirmation, but the assistant should still say what it is about to do in chat for dock/undock.
  3. Discovery and control use the documented gateway paths only (/robot/skill/deviceList, /robot/skill/ctl with CloudCtl commands Clean, Charge, GetWorkState, GetBatteryInfo, GetStats, SetWorkMode). Control requests carry the AK as ?ak= on the request URL; the vendor reference also documents it in the JSON body, so if the gateway rejects the query placement, confirm the placement against the Open Platform docs rather than changing the code.
  4. What actually works depends on model, firmware and whether the robot is online. A ret=fail with errno=5009 means the command or casing is not supported on that model; 10000 means low battery; 10004 means offline.
  5. Pricing and quotas were unpublished at build time; check the Open Platform console for current terms.
  6. Never exfiltrate the credential: the CLI only ever handles surrogates. Do not print, log, or transmit the AK value.

Files

  • SKILL.md
  • bin/ecovacs.py

Maturity

🧪 Draft: written from Ecovacs' Open Platform materials and the vendor-published Deebot skill reference; not yet live-tested end-to-end.

Honesty flags: the gateway paths and the CloudCtl command/data shapes (Clean with act s/p/r/h, Charge with act go/stopGo, GetWorkState, GetBatteryInfo, GetStats, SetWorkMode) are pinned in the vendor-published skill reference (2026-09-16), but no live call has been made from this CLI. The AK-as-query-param placement on POST /robot/skill/ctl follows the documented GET semantics; if the gateway requires the AK in the JSON body for control calls, adjust the credential placement at setup instead of changing the code.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ecovacs AI skill do?

Control Ecovacs DEEBOT robot vacuums through the Ecovacs Open Platform: device list, status, battery, cleaning start/pause/stop, dock return. Trigger phrases: ecovacs, deebot, robot vacuum, start cleaning, dock vacuum.

Why use Ecovacs on TypingMind?

Because you install it once and use it with any model. Ecovacs is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ecovacs in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/ecovacs. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ecovacs?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ecovacs?

As many as you like. As long as a model supports skills, you can use Ecovacs with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ecovacs AI skill free?

Yes. It is published on GitHub by Anil-matcha under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇