agentsclimarketplace

Train attention switching

Skill 11Yuxuanyang/polanyi-stack/skills/train-attention-switching

The Polanyi stack for AI agents. Convert tacit knowledge, Polanyis paradox, and expert judgment into reusable agents and skills.

Install
npx -y skills add 11Yuxuanyang/polanyi-stack --skill train-attention-switching

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Train focal and subsidiary attention switching for diagnosis, debugging, design review, and other judgment-heavy work. Use when the user wants to improve how experts shift between the whole situation and local signals.

SKILL.md

1.8 KB, as published. Nobody here has run it

Train Attention Switching

Core judgment: expert performance depends on switching between the whole and the parts at the right moment.

Use When

  • The user wants to improve diagnosis, debugging, critique, or judgment quality
  • Errors come from tunnel vision or scattered attention
  • A learner needs help knowing what to focus on and when to zoom out

Define the Two Layers

  • focal awareness: the whole task, question, or outcome
  • subsidiary awareness: the local cues being relied on underneath

Do not collapse them into one list.

Workflow

1. Reconstruct a Real Episode

Use a real decision, review, diagnosis, or debugging session.

2. Mark the Attention Path

Identify:

  • the focal goal at each phase
  • the subsidiary cues being used
  • the switch trigger that changed attention
  • the false lure that stole attention

If you need a format, read references/attention-audit-template.md.

3. Expose the Miss

Ask:

  • what signal was present but ignored
  • what detail looked important but was misleading
  • what would have triggered an earlier zoom-out or zoom-in

4. Design Switching Drills

Create short drills that force the learner to:

  • name the focal goal before acting
  • list the cues they are relying on
  • state what would trigger a switch

Output

Return:

  • attention audit
  • cue hierarchy
  • switch triggers
  • common false lures
  • practice drill

Do Not

  • reduce the problem to "pay more attention"
  • review only the final decision without the attention path
  • train detail spotting without training when to return to the whole

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.