Educational philosophy — learn by building inspectable things
npx skills add https://github.com/DnfJeff/Expand-YOYR-MIND --skill constructionismこのコマンドをClaude Codeにコピー＆ペーストしてスキルをインストール
| name | constructionism |
| description | Educational philosophy — learn by building inspectable things |
| allowed-tools | [] |
| tier | 0 |
| protocol | CONSTRUCTIONISM |
| origin | Seymour Papert — Logo, Mindstorms (1980) |
| lineage | ["Seymour Papert — Constructionism, Logo, Mindstorms (1980)","Marvin Minsky — Society of Mind, K-lines (1986)"] |
| related | ["play-learn-lift","society-of-mind","leela-ai","manufacturing-intelligence","room","yaml-jazz","adventure","skill","schema-mechanism","debugging"] |
| tags | ["moollm","philosophy","education","papert","microworld","learning"] |
"If you can build it, you can understand it. If you can inspect it, you can trust it."
Seymour Papert's educational philosophy: you learn best by building things you can inspect and modify. Not passive consumption. Not abstract explanation. Construction.
Logo Microworlds — Children don't learn geometry from textbooks. They teach a turtle to draw shapes:
TO SQUARE :SIZE
REPEAT 4 [FORWARD :SIZE RIGHT 90]
END
The child:
| Logo | MOOLLM |
|---|---|
| Turtle | Agent/Character |
| Canvas | Room floor |
| Procedures | Skills |
| Variables | YAML state |
| Drawing | File creation |
Everything is inspectable. Open ROOM.yml — see the state. Read session-log.md — see the history. Modify character.yml — change the world.
Easy to start — no setup, just explore:
> LOOK
You are in the workshop.
> EXAMINE hammer
A simple claw hammer.
Unlimited complexity — build custom skills, complex pipelines, new protocols.
Many paths to many goals — adventure games, workflow automation, knowledge organization.
From Don's Logo Adventure:
Type
PRINT :ITEMSto see where everything is. TypeMAKE "RNUM 5to teleport to the treasure room. If you cheat, you win by learning Logo.
"Cheating" in MOOLLM:
> Open character.yml directly
> Add "magic_sword" to inventory
> You've learned YAML and file structure!
The system rewards curiosity with knowledge.
Don's Micropolis for OLPC applied the same philosophy to SimCity:
MOOLLM applies this to LLM agents:
cities/downtown/
├── ROOM.yml # Room metadata
├── city.save # Micropolis save file
├── state.yml # Extracted game state
├── newspaper/ # Generated stories
├── advisors/ # Expert cards
└── session-log.md
LLM reads state, plays the game, summons advisors.
Constructionism in action:
You don't design skills in the abstract. You build them from experience.
Gary Drescher's Made-Up Minds (1991) extends constructionism into a computational theory of how minds learn causal models. Drescher was a student of Minsky at MIT.
See: ../schema-mechanism/ for the full treatment.
A schema is a causal unit: Context → Action → Result
The agent discovers schemas through experience, refining them via marginal attribution -- tracking which conditions correlate with success.
| Schema Mechanism | PLAY-LEARN-LIFT |
|---|---|
| ACT + OBSERVE | PLAY |
| ATTRIBUTE (marginal attribution) | LEARN |
| SPIN OFF (refine schemas) | LIFT |
| Aspect | Deterministic | LLM + YAML Jazz |
|---|---|---|
| Items | Opaque tokens | Grounded meanings |
| Patterns | Statistical correlation | Semantic understanding |
| Spin-offs | Mechanical | Creative generalization |
| Explanations | None | Natural language |
"The YAML provides the skeleton; the LLM provides the soul."
"If you can build it, you can understand it." "If you can inspect it, you can trust it." "The filesystem IS the microworld."
See also: schema-mechanism for Drescher's computational extension.
Protocol names ARE K-lines.
Be conservative in what you send, liberal in what you accept.
Rules persuade. Structure IS argument. Design consciously.
Objects clone from prototypes, not instances from classes
Survive first. Be correct later.
Survive first. Be correct later.