Design embodied learning
Skill 11Yuxuanyang/polanyi-stack/skills/design-embodied-learning
The Polanyi stack for AI agents. Convert tacit knowledge, Polanyis paradox, and expert judgment into reusable agents and skills.
npx -y skills add 11Yuxuanyang/polanyi-stack --skill design-embodied-learningAssembled 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, 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:
- mimic: copy a known good move
- vary: change one variable while holding the principle
- 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