agentsclimarketplace

Map personal knowledge

Skill hostile-shorepatrol81/polanyi-stack/skills/map-personal-knowledge

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 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.

What its author says it does

Copied from the file, not written here

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.

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

Gives 0 of the 12 instructions most note taking skills give in 326 tokens

Counted across 686 of the 876 authors here whose files we hold, read 2026-08-07

  • Include a visual element on every slidein 44 of 686, across 13 files
  • Use wikilinks for internal vault linksin 36 of 686, across 12 files
  • Commit to a single visual motif across every slidein 34 of 686, across 9 files
  • Use subagents to visually inspect rendered slidesin 31 of 686, across 7 files
  • Read pptxgenjs guide before creating presentations from scratchin 30 of 686, across 6 files
  • Keep 0.5 inch minimum marginsin 30 of 686, across 7 files
  • Re-verify affected slides after every fixin 27 of 686, across 5 files
  • Run content QA checks before declaring successin 26 of 686, across 3 files
  • Use Markdown links for external URLs onlyin 26 of 686, across 11 files
  • Pick a bold topic-specific color palettein 24 of 686, across 2 files
  • Read editing guide before editing existing presentationsin 23 of 686, across 1 file
  • Use one dominant color across all slidesin 23 of 686, across 1 file

Said here and by no other author read

  • trace every claim to specific dated entries
  • Begin from one concrete claim
  • Test the boundary of the claim
  • Separate levels of understanding
  • Produce the knowledge map
  • Return all five output items

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.