dirigera-control

2
1
Source

Control IKEA Dirigera smart home devices (lights, outlets, scenes, controllers). Use when the user asks to control smart home devices, check device status, turn lights on/off, adjust brightness/color, control outlets, trigger scenes, check battery levels, or work with IKEA smart home automation. Accessible via Cloudflare tunnel on VPS.

Install

mkdir -p .claude/skills/dirigera-control && curl -L -o skill.zip "https://mcp.directory/api/skills/download/3622" && unzip -o skill.zip -d .claude/skills/dirigera-control && rm skill.zip

Installs to .claude/skills/dirigera-control

About this skill

IKEA Dirigera Smart Home Control

Control lights, outlets, scenes, and other IKEA smart home devices through the Dirigera hub.

Prerequisites

pip install dirigera

Hub Setup

Find Hub IP

Check the router/DHCP client list for "Dirigera" and note its IP address.

If the agent is on the same LAN, try the IP discovery script. It can:

  1. Scan the subnet for likely candidates (no token required).
  2. Verify the exact hub IP if a token is available.
  3. As a last resort, try generate-token against candidates (interactive).
python scripts/find_dirigera_ip.py
# or
python scripts/find_dirigera_ip.py --subnet 192.168.1.0/24
# verify with token (if you have it)
python scripts/find_dirigera_ip.py --token <dirigera-token>
# last resort: try generate-token against candidates
python scripts/find_dirigera_ip.py --try-generate-token

Generate Token

IMPORTANT: Token generation REQUIRES PHYSICAL USER ACTION. Follow this workflow:

Step 1: Start Token Generation Script

Run the wrapper script in the background. It will automatically wait for the button press:

python scripts/generate_token_wrapper.py <dirigera-ip-address> &

The token will be saved to dirigera_token.txt by default. To specify a custom location:

python scripts/generate_token_wrapper.py <dirigera-ip-address> --output /path/to/token.txt &

Step 2: END YOUR TURN AND INFORM THE USER

CRITICAL: After starting the script, you MUST:

  1. End your turn immediately - do not wait or continue processing
  2. Tell the user: "I've started the token generation process. Please press the ACTION BUTTON on the bottom of your Dirigera hub now. Let me know when you've pressed it."

Step 3: Wait for User Confirmation

The user will:

  1. Physically press the button on their Dirigera hub
  2. Reply to you confirming they pressed it (e.g., "Done" or "Pressed")

The script will automatically detect the button press and save the token to the file.

Step 4: Retrieve the Saved Token

After the user confirms, read the token from the file:

from pathlib import Path
token = Path("dirigera_token.txt").read_text().strip()

Or from a custom location:

TOKEN=$(cat /path/to/token.txt)

Then use the token to connect:

import dirigera
hub = dirigera.Hub(token=token, ip_address="<dirigera-ip>")

Alternative: Manual Command

For manual use (not recommended for agents):

generate-token <dirigera-ip-address>

This requires interactive terminal access and doesn't save output automatically.

Troubleshooting

If you cannot find the hub IP address:

  1. Check the router/DHCP list and look for "Dirigera".
  2. If the name is missing, match the hub's MAC address label to a new device entry.
  3. Ensure the hub and client are on the same network.
  4. If you have candidate IPs, run generate-token against them until one succeeds.
  5. If you already have a token, run python scripts/find_dirigera_ip.py --token <dirigera-token>.
  6. If everything else fails, run python scripts/find_dirigera_ip.py --try-generate-token and follow the prompt.

Hub Connection

import dirigera

hub = dirigera.Hub(
    token="token",
    ip_address="ip_address"
)

CRITICAL: Attribute Access

Device state is in .attributes, not top-level.

# CORRECT
light.attributes.is_on
light.attributes.light_level

# WRONG - raises AttributeError
light.is_on
light.light_level

Top-level: device.id, device.is_reachable, device.room State: device.attributes.is_on, device.attributes.light_level

Quick Commands

Discovery

lights = hub.get_lights()
outlets = hub.get_outlets()
controllers = hub.get_controllers()
scenes = hub.get_scenes()

Light Control

light = hub.get_light_by_name(lamp_name="bedroom light")

# Check reachability first
if light.is_reachable:
    light.set_light(lamp_on=True)
    light.set_light_level(light_level=75)
    light.set_color_temperature(color_temp=2700)  # Warm white

# Reload after changes
light.reload()

Outlet Control

outlet = hub.get_outlet_by_name(outlet_name="living room")
outlet.set_on(outlet_on=True)
outlet.reload()

Scene Triggering

scene = hub.get_scene_by_name(scene_name="Sove tid")
scene.trigger()

Check Capabilities

# Verify device supports feature before using
if 'colorTemperature' in light.capabilities.can_receive:
    light.set_color_temperature(color_temp=3000)

Common Patterns

See references/patterns.md for room-based control, batch operations, status reports, and battery monitoring.

Helper Scripts

Use scripts/helpers.py for common operations: get lights by room, check battery levels, find unreachable devices.

Complete Reference

See references/api.md for:

  • Complete attribute reference
  • All control methods
  • Device capabilities
  • Color temperature/hue values
  • Troubleshooting

Best Practices

  1. Always check device.is_reachable before control
  2. Call device.reload() after control commands
  3. Use .attributes for all state access
  4. Add 0.5s delays between rapid commands
  5. Check capabilities before using features

You might also like

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

1,6851,428

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

1,2631,324

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

1,5331,147

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

1,355809

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

1,263727

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

1,481684