agentleFS
claude-worldclaude-world/claude-agent/.claude/skills/smart-bed/SKILL.md

smart-bed

Skill5 starsChanged 8 months agoMITView on GitHub

Control Eight Sleep Pod smart bed via CLI. Check bed status, set mattress temperature for each side, manage alarm schedules, and view sleep data. Use when user says "set bed temperature", "turn on bed heating", "check sleep score", "set alarm", or any Eight Sleep control request.

  • Installs packages

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check if CLI is installed first: which eightctl || python3 -c "import pyeight" 2>/dev/null

    line 124
  2. Distinctive:

    If not installed, show pip install command and stop

    line 125
  3. Very specific:

    If credentials not set, instruct user to set EIGHT_USER and EIGHT_PASS environment variables

    line 126
  4. Distinctive:

    If device is not online, suggest checking WiFi connection of the Pod

    line 129
  5. Distinctive:

    Keep responses concise: report what was set and current status

    line 130

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Smart Bed Control (Eight Sleep)

Control your Eight Sleep Pod mattress temperature and schedules.

Prerequisites

Install eightctl:

pip install eightctl
# GitHub: https://github.com/mezz64/pyeight (Python library)
# CLI wrapper: pip install eightctl

Or use the Python library directly:

pip install pyeight

First-time setup — set credentials:

export EIGHT_USER="your@email.com"
export EIGHT_PASS="yourpassword"
# Or create ~/.config/eightctl/config.yml

Requires an Eight Sleep account and active Pod subscription.

Commands

Status

eightctl status                 # Full device status
eightctl status --side left     # Left side only
eightctl status --side right    # Right side only
eightctl sleep-data             # Last night's sleep summary

Temperature Control

Temperature level: -100 (coldest) to +100 (hottest). Zero = neutral.

eightctl set-temp --side left --level 20    # Warm left side
eightctl set-temp --side right --level -30  # Cool right side
eightctl set-temp --side both --level 0     # Neutral both sides
eightctl off --side both                    # Turn off heating/cooling

Alarms

eightctl alarms                             # List all alarms
eightctl set-alarm --side left --time 07:00 # Set alarm (24h format)
eightctl delete-alarm --id [alarm_id]

Schedules

eightctl schedules              # List active schedules
eightctl schedule-status        # Show tonight's scheduled settings

Usage Examples

"Check bed status"

eightctl status

"Set my side (left) to level 30 for warmth"

eightctl set-temp --side left --level 30

"Cool down the right side to -20"

eightctl set-temp --side right --level -20

"Turn off the bed"

eightctl off --side both

"Set my alarm to 7am"

eightctl set-alarm --side left --time 07:00

"How did I sleep last night?"

eightctl sleep-data

Temperature Level Guide

LevelFeel
-100 to -50Very cold
-50 to -20Cool
-20 to 0Slightly cool / neutral
0 to 20Slightly warm
20 to 50Warm
50 to 100Hot

Rules

  • Check if CLI is installed first: which eightctl || python3 -c "import pyeight" 2>/dev/null
  • If not installed, show pip install command and stop
  • If credentials not set, instruct user to set EIGHT_USER and EIGHT_PASS environment variables
  • Temperature level is -100 to +100, NOT degrees Celsius/Fahrenheit — clarify if user asks "set to 25 degrees"
  • Side values: left, right, or both
  • If device is not online, suggest checking WiFi connection of the Pod
  • Keep responses concise: report what was set and current status

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.