Sleep logo

Sleep

Community
Hmbown
sleep

Sleep = temporary, reversible suspension with guaranteed state preservation. The target stops acting but wakes up intact. No data loss, no corruption, no permanent change.

Overview

PublisherHmbown
RepositoryWizards-of-the-Ghosts
Skill namesleep
Stars
106
Forks
10
Bundled files
Instructions only
LicenseCC0-1.0
Links
Skill sourceRepository
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Hmbown on GitHub. Read the source before you install it.

Installation

Install the Sleep 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.
  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/Hmbown/Wizards-of-the-Ghosts.git /tmp/Wizards-of-the-Ghosts
mkdir -p .claude/skills
cp -r /tmp/Wizards-of-the-Ghosts/generated/hermes/influence-and-behavior/sleep .claude/skills/sleep
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sleep 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 Sleep 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 Sleep 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.

Sleep

Put processes, notifications, or systems into graceful suspension.

What This Skill Does

Sleep = temporary, reversible suspension with guaranteed state preservation. The target stops acting but wakes up intact. No data loss, no corruption, no permanent change. In this grimoire, Sleep is treated as a hybrid spell with a shipping-now delivery profile. Canonical reference input: Sleep (spell).

When To Use

  • Keywords: pause, suspend, hibernate, DND, maintenance window, cooldown, quiet mode, silence temporarily, freeze (with resume), graceful degradation
  • Patterns requiring all three:
  • Something must stop acting for a defined period
  • State/queue/context must be preserved during the stop
  • A wake condition exists (timer, threshold, manual trigger, external event)

Prerequisites

  • Environment variables available to Hermes: HA_URL, HA_TOKEN.
  • Primary credential or token: HA_TOKEN.
  • Binaries on PATH: curl.

Setup

  1. Confirm the required environment variables are available inside the active Hermes runtime, not just in a shell profile.
  2. Verify the required binaries resolve on PATH before you rely on them in a procedure.
  3. Choose a non-production or low-risk target first if the skill can page, unlock, alert, or touch a live integration.

Procedure

  1. Restate the target, the success condition, and any no-touch boundaries before taking action.
  2. Identify the sleeper: What exact process, channel, service, or workflow stops?
  3. Define the boundary: What stops, what keeps running, what queues for later?
  4. Set the wake condition: Timer? Manual trigger? Threshold? External event? Must have one.
  5. Verify state preservation: Confirm nothing is lost—only deferred. List what persists.
  6. Return the plan: Sleep configuration + wake conditions + state-preservation checklist.
  7. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

  • Sleep configuration: what suspends, what stays active, what queues
  • Wake conditions: how/when resume happens
  • State-preservation checklist: confirmation nothing is lost

Pitfalls / Guardrails

  • Keep the theatrical framing, but name the concrete mechanism that makes the skill useful right now.
  • Do not use for: "Permanently decommission" / "never come back" → Kill, not Sleep
  • Do not use for: "Shut it down right now" / "pull offline" / "kill it" → Kill, not Sleep
  • Do not use for: "Lock their credentials" / "prevent any further queries" → Access control, not Sleep
  • Do not use for: "Paralyze a competing process" / "hard block" → Resource blocking, not Sleep
  • Do not use for: "Team-wide agreement" / "communication norms" → Policy, not Sleep
  • Do not use for: "Reduce fan noise" / "HVAC configuration" → Hardware config, not Sleep
  • Do not use for: No wake condition defined → Bug, not Sleep (ask for one)
  • Do not rely on a live integration until credentials, target scope, and rollback expectations are verified.

Verification

  • Check that the result includes every deliverable promised above.
  • Check that confirmed facts, assumptions, and inferences are visibly separated.
  • Check which parts are concrete actions versus framing, so the user can tell what is real now.
  • Check the required environment variables and binaries in the active Hermes runtime before trusting the procedure on a live target.

Example Invocation

text
/sleep design a graceful suspension plan for this [system/process/notification channel]. Define what stops, what queues, and how it wakes up

Frequently asked questions

What does the Sleep AI skill do?

Sleep = temporary, reversible suspension with guaranteed state preservation. The target stops acting but wakes up intact. No data loss, no corruption, no permanent change.

Why use Sleep on TypingMind?

Because you install it once and use it with any model. Sleep 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 Sleep in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Hmbown/Wizards-of-the-Ghosts/tree/main/generated/hermes/influence-and-behavior/sleep. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Sleep?

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 Sleep?

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

Is the Sleep AI skill free?

Yes. It is published on GitHub by Hmbown under the CC0-1.0 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.

Related AI Skills

View all
affaan-m logo

Kotlin Patterns

affaan-m
CommunityPopular

Patrones idiomáticos de Kotlin, buenas prácticas y convenciones para construir aplicaciones Kotlin robustas, eficientes y mantenibles con coroutines, null safety y builders de DSL.

39.1K
261.1K
Instructions
View
affaan-m logo

Kotlin Testing

affaan-m
CommunityPopular

Patrones de pruebas Kotlin con Kotest, MockK, pruebas de coroutines, pruebas basadas en propiedades y cobertura con Kover. Sigue la metodología TDD con prácticas idiomáticas de Kotlin.

39.1K
261.1K
Instructions
View
affaan-m logo

Laravel Patterns

affaan-m
CommunityPopular

Patrones de arquitectura Laravel, routing/controladores, Eloquent ORM, capas de servicio, colas, eventos, caché y API resources para aplicaciones en producción.

39.1K
261.1K
Instructions
View
affaan-m logo

Laravel Security

affaan-m
CommunityPopular

Buenas prácticas de seguridad en Laravel para autenticación/autorización, validación, CSRF, asignación masiva, subida de archivos, secretos, limitación de velocidad y despliegue seguro.

39.1K
261.1K
Instructions
View

Set up your own AI workspace now

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