agentsclimarketplace

Map personal knowledge

Skill 11Yuxuanyang/polanyi-stack/skills/map-personal-knowledge

Map personal knowledge by separating direct understanding from borrowed language, hidden assumptions, and untested beliefs. Use when the user wants to audit whether someone truly understands a concept or judgment.From its SKILL.md

Install
npx -y skills add 11Yuxuanyang/polanyi-stack --skill map-personal-knowledge

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.

SKILL.md

1.7 KB, 326 tokens by cl100k_base, as published. Nobody here has run it

Map Personal Knowledge

Core judgment: knowledge is personal before it is formal. The question is not just "what do you know" but "what is this knowledge grounded in."

Use When

  • The user wants to distinguish real understanding from fluent repetition
  • A judgment sounds plausible but its basis is unclear
  • The goal is to surface assumptions, confidence gaps, and boundary conditions

Start with a Concrete Claim

Do not begin from a whole field. Begin from one claim, one model, or one decision.

Examples:

  • "This is a good diagnosis"
  • "This product strategy will work"
  • "I understand this framework"

Workflow

1. Trace the Source

For each important claim, ask where it comes from:

  • direct experience
  • observed examples
  • formal theory
  • authority or tradition
  • unexamined assumption

2. Test the Boundary

Ask:

  • when would this stop being true
  • what counterexample would weaken it
  • what hidden condition is doing most of the work

3. Separate Understanding Levels

Distinguish:

  • can restate
  • can explain in own words
  • can apply in a live case
  • can detect failure

4. Produce the Map

If you need a format, read references/knowledge-map-template.md.

Output

Return:

  • claim map
  • source of confidence
  • assumption list
  • blind spots
  • next validating action

Do Not

  • mistake vocabulary for understanding
  • treat confidence as evidence
  • keep the analysis purely abstract after finding a weak spot

What ships with it: 1 file

521 B alongside SKILL.md

Keep looking

Skills are one crate of 325,949. 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.