Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
"An agent learns by discovering reliable patterns: when I do X in context C, result R tends to follow."
Gary Drescher's Made-Up Minds (1991) provides a computational theory of how minds learn causal models of the world. Drescher was a student of Marvin Minsky at MIT, and his schema mechanism extends Piaget's developmental psychology into executable algorithms.
The Core Idea
A schema is a causal unit:
Context → Action → Result
The agent doesn't start with schemas. It discovers them through experience, noticing which actions reliably produce which results in which contexts.
Here schema means Drescher causal units (Context → Action → Result). That is not JSON Schema, OpenAPI, RELAX NG, XSD, or other interchange mechanisms. For the MOOLLM schemapedia (interchange, relational SQL/SQLite, frames, K-lines, SoM—same word, many senses), see schema (skills/schema/, schemas/registry.yml). For Minsky frames vs K-lines vs Drescher, see knowledge-frames.
Schema Components
Component
Description
MOOLLM Equivalent
Item
Atomic state element (ON/OFF/UNKNOWN)
YAML field, file existence
Action
Something the agent can do
Skill verb, procedure
Schema
Context → Action → Result
Documented procedure
Extended Context
Statistical tracking of context conditions
"Prerequisites" section
Extended Results
Statistical tracking of result conditions
"Side Effects" section
Synthetic Item
Discovered hidden state
Undocumented dependency
Composite Action
Chained sequence of actions
Multi-step procedure
Extended Context: Marginal Attribution
A schema might fail unpredictably. Extended Context tracks which conditions correlate with success:
# The schema "start pyvision" sometimes fails# Extended Context discovers: it fails when postgres isn't runningschema:action:start-pyvisioncontext: [] # Initially emptyresult: [pyvision-running]
extended_context:postgres-running:success_when_on:47# Succeeded 47 times when postgres was onsuccess_when_off:0# Never succeeded when postgres was offfailure_when_on:2# Failed 2 times even with postgresfailure_when_off:15# Failed 15 times without postgres# Discovery: postgres-running is a prerequisite!# Spin off new schema with explicit context:schema:action:start-pyvisioncontext: [postgres-running] # Now explicitresult: [pyvision-running]
This is marginal attribution -- discovering which items matter by tracking correlations.
Extended Results: Side Effect Discovery
Similarly, schemas track what else happens:
schema:action:ingest-videocontext: [video-exists]
result: [task-created]
extended_results:disk-space-decreased:on_after_success:47off_after_success:0# Discovery: ingesting uses disk space!
Side effects become explicit, documented, predictable.
Synthetic Items: Hidden State
Sometimes success depends on state the agent can't directly observe. Drescher's solution: invent a synthetic item as a hypothesis.
# The schema works sometimes, fails sometimes, no visible pattern# Hypothesis: there's hidden state we can't seesynthetic_item:name:"gpu-memory-available"host_schema:start-pyvision# If this schema succeeds, assume the item was ON# If it fails, assume the item was OFF
The synthetic item becomes a probe -- its state is inferred from schema success/failure.
Composite Actions: Planning
Once the agent has reliable schemas, it can chain them:
Henry Minsky (Marvin's son) implemented Drescher's schema mechanism in Python:
Class
Purpose
World
Central coordinator, tracks all items and schemas
Item
Atomic state element with ON/OFF/UNKNOWN values
Action
Primitive or composite action
Schema
The Context → Action → Result unit
ExtendedContext
Statistical tracking for context discovery
ExtendedResults
Statistical tracking for result discovery
DijkstraPlanner
Goal-directed planning through schema graph
Why LLMs Complete Drescher's Vision
Drescher's original implementation faced fundamental limitations that LLMs transcend:
1. The Symbol Grounding Problem
# Python: Items are opaque tokens
item_37 = Item("postgres-running") # What does this MEAN?# The system can correlate item_37 with success,# but has NO IDEA what "postgres" or "running" mean.
# YAML Jazz + LLM: Semantics are groundedpostgres-running:# The database engine that stores our task queue# Must be healthy before pyvision can claim tasks# Check with: docker exec edgebox-postgres pg_isready
The LLM understands that postgres is a database, that "running" means the process is alive. It can reason about items, not just correlate them.
2. Natural Language Context
% Prolog: Formal but opaque
schema(start_pyvision, [postgres_running], [pyvision_running]).
% Why? What's the relationship? Silent.
# YAML Jazz: Self-documenting causalityschema:action:start-pyvisioncontext:-postgres-running# pyvision needs postgres to claim tasks from the queue# without it, the worker has nothing to processresult:-pyvision-running
The LLM reads comments and understands the causal mechanism.
3. Empathic Pattern Recognition
# Python: Counting correlations
extended_context[item_id].success_when_on += 1# After 50 trials: item_37 correlates with success# But WHY? The system cannot say.
LLM: "I notice start-pyvision fails when postgres isn't running.
This makes sense -- pyvision queries the task table on startup.
The dependency is architectural, not coincidental."
The LLM doesn't just find correlations -- it understands mechanisms.
LLM: "Based on the postgres dependency, I should also check:
- Is there enough disk space for the database?
- Are the connection limits configured properly?
- Should we add a health check before starting?"
The LLM generalizes from specific observations to related concerns.
5. The Explanation Gap
;; Lisp: Can derive, cannot explain
(derive-plan goal: pyvision-running)
;; Returns: ((start-postgres) (start-pyvision))
;; But try asking it WHY this plan works...
# MOOLLM: Plans with explanationsplan:-action:start-postgresrationale:"pyvision needs the task queue"-action:start-pyvisionrationale:"now it can claim tasks"
6. Handling Novelty
# Python: Item not in vocabulary
item = world.get_item("kubernetes-pod-restarting")
# KeyError! Never seen this item.
LLM: "I haven't seen this exact item before, but I understand:
- 'kubernetes pod' is a containerized service
- 'restarting' suggests crash loops
- This is similar to 'pyvision crashing'
- Let me check the container logs..."
The Comparison
Aspect
Deterministic (Lisp/Prolog/Python)
LLM + YAML Jazz
Items
Opaque tokens
Grounded meanings
Patterns
Statistical correlation
Semantic understanding
Spin-offs
Mechanical refinement
Creative generalization
Explanations
None
Natural language
Novelty
Vocabulary-limited
Open-ended
Context
Formal predicates
Natural language + comments
Debugging
Trace execution
Ask "why did this fail?"
Drescher's Dream, Realized
Drescher was trying to build a system that learns causal models of the world. His mechanism was brilliant but limited by the symbolic substrate. The schema mechanism discovers that patterns exist, but cannot understand why.
"If you can observe patterns, you can discover causality.""If you track correlations, you can spin off knowledge.""The YAML provides the skeleton; the LLM provides the soul."
