S4h Cognition Attention logo

S4h Cognition Attention

Organization
human-avatar
s4h-cognition-attention

Maps the attention economy of a mind or situation — what captures it, what depletes it, and how to protect it. Use when asked 'why can't I focus', 'attention keeps getting pulled away', 'how do I protect deep work', 'what's stealing my focus', 'I keep getting distracted', or when designing environments, workflows, or communications that need to respect cognitive bandwidth.

Overview

Publisherhuman-avatar
Repositoryskills-for-humanity
Skill names4h-cognition-attention
Stars
234
Forks
24
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

    Published by human-avatar on GitHub. Read the source before you install it.

Installation

Install the S4h Cognition Attention 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/human-avatar/skills-for-humanity/tree/main/skills/s4h-cognition-attention
  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/human-avatar/skills-for-humanity.git /tmp/skills-for-humanity
mkdir -p .claude/skills
cp -r /tmp/skills-for-humanity/skills/s4h-cognition-attention .claude/skills/s4h-cognition-attention
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable S4h Cognition Attention 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 S4h Cognition Attention 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 S4h Cognition Attention 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.

Cognition: Attention

Attention is the scarcest cognitive resource — and unlike memory or reasoning, it cannot be trained to be unlimited. It can only be allocated, protected, and defended. Most focus problems are not character failures; they are design failures. The environment, the workflow, or the communication system is structured in a way that systematically fragments attention and prevents sustained engagement with what matters most.

The attention economy framing, developed from William James's foundational work on voluntary and involuntary attention, treats focus as a resource subject to supply and demand. What demands attention is not random: salience (bright, loud, moving things), novelty (what's new or unexpected), emotional charge (threats, social signals, strong affect), and personal relevance all reliably override deliberate focus. Design your attention environment knowing what the competition is.

The key distinction: attention threats come in two forms. Capture — things that involuntarily seize focus through sensory or emotional hooks — and depletion — things that gradually drain the capacity for sustained focus even when no single interruption is dramatic. Both matter. Capture is visible and acute; depletion is slow, cumulative, and often invisible until cognitive capacity is exhausted.


Your Process

Step 1: Define the Attention Context Identify whose attention, in what context, for what purpose. Individual focus (a person trying to do deep work)? Group attention (a team, a meeting)? Communication attention (an audience you need to hold)? The diagnosis differs by context.

Framing check: Confirm the specific attention context before continuing. State what you've identified — whose attention, in what setting, and what the goal is — in one sentence, then use AskUserQuestion:

  • Question: "I'm reading this as: [your one-sentence framing of whose attention is at issue, in what context, and what you're trying to achieve]. Is that right?"
  • Header: "Framing"
  • Options:
    • Yes — proceed — framing is correct
    • Adjust — one element is off; user will correct it before you continue
    • Reframe — different situation than read; incorporate the correction before proceeding

Step 2: Map Attention Demands List everything currently competing for attention in this context. Separate into:

  • Legitimate demands: things that genuinely require attention and have claim to the time
  • Capture threats: involuntary hijacks — notifications, interruptions, ambient noise, social signals
  • Depletion sources: low-grade cognitive drains — ambient worry, unresolved decisions, low-priority tasks that create background anxiety, decision fatigue

Step 3: Assess Current Allocation Where is attention actually going versus where it should go? Estimate the proportion of cognitive bandwidth consumed by each category. Identify the gap between actual and ideal allocation.

Before narrowing: Use AskUserQuestion to confirm the demand map before proceeding to solutions:

  • Question: "I've mapped [N] attention demands across legitimate, capture, and depletion categories. Before I prioritise defences, are there any sources I've missed or any you'd flag as especially significant?"
  • Header: "Demand Map"
  • Options:
    • Proceed — the map looks complete
    • Add a demand — user will name a specific source to include
    • Correct a category — user will reclassify something

Step 4: Diagnose the Core Problem What is the primary failure mode? Choose the dominant one:

  • Environment design failure: physical or digital environment is structured to maximise interruption
  • Boundary failure: legitimate demands have no protective scheduling; everything competes in real time
  • Depletion spiral: low-level cognitive load is accumulating to the point where sustained attention becomes impossible
  • Capture vulnerability: specific high-salience threats (notifications, social media, email) are bypassing deliberate intent

Step 5: Design the Defence For each identified threat, prescribe a specific structural intervention. Defences fall into four types:

  • Elimination: remove the demand entirely (unsubscribe, turn off, delete)
  • Batching: process the demand in a designated window rather than on-demand (email twice daily, messages at noon)
  • Protection: create structural conditions where capture threats cannot reach (phone in another room, notifications off, closed door)
  • Offloading: capture open loops and unresolved items in a trusted external system to prevent background anxiety depletion (a task list, a decision log)

Human Check-in

Before proceeding, use the AskUserQuestion tool. State your interpretation of the situation in 1–2 sentences — what the core attention problem is and what the most significant threat is — then ask:

  • Question: "My read: [your 1–2 sentence interpretation]. How do you want to proceed?"
  • Header: "Scope"
  • Options:
    • Full analysis — Complete demand map, diagnosis, and full defence plan
    • Key threats only — Identify the top 3 attention threats and their defences
    • Environment redesign — Focus on structural changes to the physical or digital environment
    • Reframe — The read is off; correct it and the analysis will follow the corrected framing

Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis.

Output Format

Attention Demand Map

SourceTypeEstimated % of bandwidthLegitimacy

Core Problem: [dominant failure mode + brief explanation]

Defence Plan

ThreatDefence TypeSpecific Action

Priority Actions: [Ranked top 3 interventions — the highest-impact changes to make first]

Protected Time Structure: [Specific recommendation for how to schedule and protect focused work given the demands identified]


Notes

Attention management is not willpower management. Recommending that someone "just focus more" is the cognitive equivalent of recommending that someone "just be healthier." The leverage is in designing the environment and workflow, not in strengthening resolve against a hostile system. This skill should produce structural, actionable changes — not exhortations.

The nearest neighbor is /s4h-cognition-cognitive-load — which addresses working memory capacity within a focused session. Attention is the gateway problem (can you sustain engagement at all?); cognitive load is the capacity problem (can you hold the necessary complexity once you're engaged?). Both often need addressing together.

For the communication design case — holding an audience's attention — pair with /s4h-communication-audience-modeling.


What's Next

After delivering this output, use AskUserQuestion to offer the next move:

  • Question: "Attention map complete. What's next?"
  • Header: "Next"
  • Options:
    • /s4h-cognition-cognitive-load — Address working memory limits within the focused sessions you've now protected
    • /s4h-cognition-metacognition — Assess whether you're monitoring and adjusting your thinking well within those focused sessions
    • /s4h-mindset-flow — Design for flow states using the protected attention environment as a foundation
    • Done — Wrap up and synthesise what we have so far

Frequently asked questions

What does the S4h Cognition Attention AI skill do?

Maps the attention economy of a mind or situation — what captures it, what depletes it, and how to protect it. Use when asked 'why can't I focus', 'attention keeps getting pulled away', 'how do I protect deep work', 'what's stealing my focus', 'I keep getting distracted', or when designing environments, workflows, or communications that need to respect cognitive bandwidth.

Why use S4h Cognition Attention on TypingMind?

Because you install it once and use it with any model. S4h Cognition Attention 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 S4h Cognition Attention in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/human-avatar/skills-for-humanity/tree/main/skills/s4h-cognition-attention. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use S4h Cognition Attention?

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 S4h Cognition Attention?

As many as you like. As long as a model supports skills, you can use S4h Cognition Attention with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the S4h Cognition Attention AI skill free?

Yes. It is published on GitHub by human-avatar 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 👇