Design apprenticeship transfer
Skill hostile-shorepatrol81/polanyi-stack/skills/design-apprenticeship-transfer
Convert tacit expert knowledge into reusable AI agents, skills, and training workflows to scale reliable performance.
npx -y skills add hostile-shorepatrol81/polanyi-stack --skill design-apprenticeship-transferAssembled 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 apprenticeship and mentor-led transfer for tacit skills through shared work, observation rubrics, and transfer tests. Use when the user wants to build onboarding, pair practice, or expert-to-novice transmission.
SKILL.md
1.7 KB, 308 tokens by cl100k_base, as published. Nobody here has run it
Design Apprenticeship Transfer
Core judgment: tacit knowledge transfers through shared practice before it transfers through explanation.
Use When
- The user wants to build onboarding for judgment-heavy work
- A mentor, lead, clinician, or senior operator needs to train a novice
- Pairing exists, but improvement is inconsistent or impossible to evaluate
Use a Real Task
Pick a live task or a realistic simulation with stakes, constraints, and visible output.
Do not anchor the apprenticeship around passive watching alone.
Workflow
1. Build the Progression
Use this sequence:
- observe the expert on a real task
- shadow with commentary at key decision points
- assign partial ownership
- assign independent execution
- run a transfer test on a new case
2. Score What Matters
Evaluate:
- cue recognition
- decision quality
- handling of uncertainty
- escalation timing
- ability to transfer to a new case
If you need a format, read references/pairing-rubric-template.md.
3. Keep Feedback Local
Feedback should point to specific missed cues, weak decisions, or premature confidence.
Avoid vague comments like "needs more judgment."
Output
Return:
- apprenticeship plan
- stage progression
- observation rubric
- transfer test
- pass or fail criteria
Do Not
- confuse exposure with learning
- score only polish or confidence
- call it complete before a new-case transfer test
What ships with it: 1 file
529 B alongside SKILL.md
references/
Gives 0 of the 12 instructions most design frontend skills give in 308 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.