Agent skill
wev-verification
WEV Verification Skill
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/wev-verification
SKILL.md
WEV Verification Skill
Trit: -1 (MINUS - Validator)
GF(3) Triad: wev-verification (-1) ⊗ world-hopping (0) ⊗ alife (+1) = 0
Overview
World Extractable Value (WEV) verification connecting:
- Quadrant Chart (Colorable × Derangeable)
- Proof-of-Frog consensus
- Learning Agent reafference loops
- GF(3) conservation
WEV Formula
WEV = Σ(coordinated outcomes) - Σ(coordination costs)
Legacy: WEV = V - 0.5V - costs = 0.4V
GF(3): WEV = V + 0.1V - 0.01 = 1.09V
Advantage: 2.7x
Quadrant Classification
| Quadrant | Colorable | Derangeable | Examples |
|---|---|---|---|
| Q1 (OPTIMAL) | ✓ | ✓ | PR#18, Knight Tour |
| Q2 | ✓ | ✗ | Identity morphisms |
| Q3 (WORST) | ✗ | ✗ | Deadlock states |
| Q4 | ✗ | ✓ | Phase transitions |
Learning Agent Architecture
┌─────────────────────────────────────────┐
│ Reafference Loop │
├─────────────────────────────────────────┤
│ 1. Predict (Efference Copy) │
│ 2. Execute (Action) │
│ 3. Observe (Sensation) │
│ 4. Match? (Validate) │
│ 5. Update Model (Learn) │
└─────────────────────────────────────────┘
Usage
using .WEVVerification
# Quadrant verification
items = [
("PR#18", 0.85, 0.90),
("Knight Tour", 0.75, 0.85),
("Deadlock", 0.15, 0.15),
]
verify_quadrant(items)
# WEV comparison
comparison = compare_wev_legacy_vs_gf3(100.0)
println("Advantage: ", comparison.advantage)
# Learning agents
alice = LearningAgent(:alice, Int8(-1))
arbiter = LearningAgent(:arbiter, Int8(0))
bob = LearningAgent(:bob, Int8(1))
# Reafference loop
reafference_loop!(alice, action, world_state)
# Frog status
frog_status([alice, arbiter, bob])
Neighbors
High Affinity
world-hopping(0): Cross-world navigationalife(+1): Emergent behaviorcybernetic-immune(-1): Self/Non-Self
Example Triad
skills: [wev-verification, world-hopping, alife]
sum: (-1) + (0) + (+1) = 0 ✓ CONSERVED
References
- Block Science KOI
- von Holst (1950) - Reafference principle
- Powers (1973) - Perceptual Control Theory
Scientific Skill Interleaving
This skill connects to the K-Dense-AI/claude-scientific-skills ecosystem:
Graph Theory
- networkx [○] via bicomodule
- Universal graph hub
Bibliography References
category-theory: 139 citations in bib.duckdb
Cat# Integration
This skill maps to Cat# = Comod(P) as a bicomodule in the equipment structure:
Trit: 0 (ERGODIC)
Home: Prof
Poly Op: ⊗
Kan Role: Adj
Color: #26D826
GF(3) Naturality
The skill participates in triads satisfying:
(-1) + (0) + (+1) ≡ 0 (mod 3)
This ensures compositional coherence in the Cat# equipment structure.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?