Blindness Deafness logo

Blindness Deafness

Community
Hmbown
blindness-deafness

In D&D, Blindness/Deafness selectively removes one sense — the target can still act but loses critical awareness. The real-world version is selective channel muting: blocking a process from seeing certain inputs (input filtering, API response redaction), deafening it to specific signals (suppressing webhooks, ignoring certain event streams), or cutting telemetry so a system operates without awareness of a specific data source. Unlike containment (forcecage) which restricts everything, Blindness/Deafness surgically removes one information channel while leaving the rest intact.

Overview

PublisherHmbown
RepositoryWizards-of-the-Ghosts
Skill nameblindness-deafness
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 Blindness Deafness 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/containment-and-intervention/blindness-deafness .claude/skills/blindness-deafness
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Blindness Deafness 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 Blindness Deafness 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 Blindness Deafness 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.

Blindness/Deafness

Cut a system's eyes or ears — let it run, but blind to specific inputs or deaf to specific signals.

What This Skill Does

In D&D, Blindness/Deafness selectively removes one sense — the target can still act but loses critical awareness. The real-world version is selective channel muting: blocking a process from seeing certain inputs (input filtering, API response redaction), deafening it to specific signals (suppressing webhooks, ignoring certain event streams), or cutting telemetry so a system operates without awareness of a specific data source. Unlike containment (forcecage) which restricts everything, Blindness/Deafness surgically removes one information channel while leaving the rest intact. In this grimoire, Blindness/Deafness is treated as a literal spell with a shipping-now delivery profile. Canonical reference input: Blindness/Deafness (spell).

When To Use

  • A process should keep running, but one input, signal, or telemetry source needs to be removed from its awareness.
  • You need to suppress a specific webhook, event stream, API field, or sensor channel without containing the whole system.
  • You want to test or control behavior under selective sensory loss rather than full isolation.

Prerequisites

  • No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session.

Procedure

  1. Restate the target, the success condition, and any no-touch boundaries before taking action.
  2. Identify the exact channel to mute and the decisions the system currently makes from it.
  3. Verify the channel is not safety-critical or load-bearing for core correctness.
  4. Choose the muting mechanism: input filtering, response redaction, event suppression, or telemetry cutoff.
  5. Define restoration triggers, operators, and monitoring so everyone knows the system is partially blind or deaf.
  6. Return the channel-muting plan with expected behavioral changes and rollback steps.
  7. Stop for explicit confirmation before taking a live action that changes access, triggers an alert, or touches a real system boundary.
  8. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

  • A selective channel-muting plan naming exactly what input, signal, or telemetry was removed.
  • A dependency note explaining what decisions will proceed without that awareness channel.
  • Restoration triggers, rollback steps, and operator-facing documentation.

Pitfalls / Guardrails

  • Treat the live action surface as real operational work, not decorative lore.
  • Muting a channel the system needs for safety decisions is dangerous. Verify the blinded input is not load-bearing before cutting it.
  • Always document what was muted and set a restoration trigger. A system that forgets it is blind will make confident wrong decisions.

Verification

  • Check that the result includes every deliverable promised above.
  • Check that confirmed facts, assumptions, and inferences are visibly separated.
  • Check that the exact live target, confirmation gate, and rollback or recovery path are explicit.

Example Invocation

text
/blindness-deafness selectively blind or deafen this system to one input, signal, or telemetry source while keeping the rest of it running safely

Frequently asked questions

What does the Blindness Deafness AI skill do?

In D&D, Blindness/Deafness selectively removes one sense — the target can still act but loses critical awareness. The real-world version is selective channel muting: blocking a process from seeing certain inputs (input filtering, API response redaction), deafening it to specific signals (suppressing webhooks, ignoring certain event streams), or cutting telemetry so a system operates without awareness of a specific data source. Unlike containment (forcecage) which restricts everything, Blindness/Deafness surgically removes one information channel while leaving the rest intact.

Why use Blindness Deafness on TypingMind?

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

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

Which AI models can use Blindness Deafness?

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 Blindness Deafness?

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

Is the Blindness Deafness 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

Architecture Decision Records

affaan-m
CommunityPopular

コーディングセッション中にアーキテクチャ決定を構造化ADRとして記録し、自動的に決定の瞬間を検出し、コンテキスト、検討された代替案、根拠を記録します。今後の開発者がコードベースの形成理由を理解するためのADRログを維持します。

39.1K
261.1K
Instructions
View
affaan-m logo

Automation Audit Ops

affaan-m
CommunityPopular

ECC用の証拠ベースの自動化インベントリとオーバーラップ監査ワークフロー。ユーザーがどのジョブ、フック、コネクタ、MCPサーバー、またはラッパーがライブか、壊れているか、冗長であるか、修正前に不足しているかを知りたい場合に使用します。

39.1K
261.1K
Instructions
View
anthropics logo

Internal Comms

anthropics
OrganizationPopular

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal…

20.9K
176.9K
4 files
View
anthropics logo

Claude Opus 4 5 Migration

anthropics
OrganizationPopular

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string…

23.8K
146.3K
2 files
View

Set up your own AI workspace now

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