agentsclimarketplace

Design embodied learning

Skill hostile-shorepatrol81/polanyi-stack/skills/design-embodied-learning

Convert tacit expert knowledge into reusable AI agents, skills, and training workflows to scale reliable performance.

Install
npx -y skills add hostile-shorepatrol81/polanyi-stack --skill design-embodied-learning

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

Design embodied learning paths for tacit or judgment-heavy skills using scaffolded practice, simulation, and deliberate repetition. Use when the user wants to teach a skill through doing rather than lectures alone.

SKILL.md

1.9 KB, 360 tokens by cl100k_base, as published. Nobody here has run it

Design Embodied Learning

Core judgment: a tacit skill is learned by dwelling in practice, not by reading a slide deck.

Use When

  • The user wants to teach a craft, diagnostic, operational, or judgment-heavy skill
  • A team understands the theory but performance is still weak
  • The goal is to design drills, simulations, or practice ladders

Anchor the Learning Target

Define two things up front:

  • focal goal: the whole task or result the learner is trying to achieve
  • subsidiary cues: the details the learner must notice on the way there

Do not mix them. New learners usually need explicit cue attention before whole-task fluency.

Workflow

1. Choose the Real Task

Use a real task or a close simulation. Avoid abstract explanations as the main teaching surface.

2. Build the Practice Ladder

Use three stages:

  1. mimic: copy a known good move
  2. vary: change one variable while holding the principle
  3. create: handle a fresh case independently

If you need a format, read references/practice-ladder-template.md.

3. Tighten Feedback

For each stage, specify:

  • what the learner sees
  • what the learner does
  • what feedback arrives immediately
  • what counts as acceptable performance

4. Make Transfer Explicit

End with a new case that is similar in principle but different in surface form.

Learning is not complete until the learner can transfer.

Output

Return:

  • focal goal
  • subsidiary cues
  • practice ladder
  • feedback loop
  • exit criteria
  • transfer exercise

Do Not

  • teach a tacit skill as pure lecture
  • skip from explanation straight to independence
  • confuse repetition with deliberate practice

What ships with it: 1 file

453 B alongside SKILL.md

Gives 0 of the 12 instructions most design frontend skills give in 360 tokens

Counted across 1,169 of the 1,878 authors here whose files we hold, read 2026-08-07

  • Use CSS variables for color consistencyin 72 of 1169, across 23 files
  • Commit to one bold aesthetic direction before codingin 72 of 1169, across 27 files
  • Match implementation complexity to the aesthetic visionin 70 of 1169, across 20 files
  • Add atmospheric background effects and texturesin 57 of 1169, across 9 files
  • Use unexpected spatial compositions and layoutsin 56 of 1169, across 8 files
  • Implement real working codein 55 of 1169, across 7 files
  • Vary themes and aesthetics across different designsin 48 of 1169, across 7 files
  • Launch chromium in headless modein 47 of 1169, across 4 files
  • Close the browser when donein 47 of 1169, across 4 files
  • Run provided scripts with help flag firstin 47 of 1169, across 4 files
  • Wait for network idle statein 47 of 1169, across 4 files
  • Use descriptive selectors for elementsin 47 of 1169, across 4 files

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

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.